github-starred/TinyTorch
2
0
Fork 0
mirror of https://github.com/MLSysBook/TinyTorch.git synced 2026-04-30 10:13:57 -05:00
Code Issues 7 Packages Projects Releases Wiki Activity

🏗️ Restructure repository for optimal student/instructor experience

Browse Source 
- Move development artifacts to development/archived/ directory
- Remove NBGrader artifacts (assignments/, testing/, gradebook.db, logs)
- Update root README.md to match actual repository structure
- Provide clear navigation paths for instructors and students
- Remove outdated documentation references
- Clean root directory while preserving essential files
- Maintain all functionality while improving organization

Repository is now optimally structured for classroom use with clear entry points:
- Instructors: docs/INSTRUCTOR_GUIDE.md
- Students: docs/STUDENT_GUIDE.md
- Developers: docs/development/

✅ All functionality verified working after restructuring
This commit is contained in:
Vijay Janapa Reddi
2025-07-12 11:17:36 -04:00
parent bf97b9af96
commit 27208e3492
29 changed files with 1325 additions and 6500 deletions
Download Patch File Download Diff File Expand all files Collapse all files

229
README.md
View File

@@ -1,6 +1,6 @@
# Tiny🔥Torch: Build ML Systems from Scratch # Tiny🔥Torch: Build ML Systems from Scratch
> A hands-on systems course where you implement every component of a modern ML system > A hands-on ML Systems course where students implement every component from scratch
[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/) [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE) [![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
@@ -8,150 +8,153 @@
> **Disclaimer**: TinyTorch is an educational framework developed independently and is not affiliated with or endorsed by Meta or the PyTorch project. > **Disclaimer**: TinyTorch is an educational framework developed independently and is not affiliated with or endorsed by Meta or the PyTorch project.
**Tiny🔥Torch** is a hands-on companion to [*Machine Learning Systems*](https://mlsysbook.ai), providing practical coding exercises that complement the book's theoretical foundations. Rather than just learning *about* ML systems, you'll build one from scratch—implementing everything from tensors and autograd to hardware-aware optimization and deployment systems. **Tiny🔥Torch** is a complete ML Systems course where students build their own machine learning framework from scratch. Rather than just learning *about* ML systems, students implement every component and then use their own implementation to solve real problems.
## 🎯 What You'll Build ## 🚀 **Quick Start - Choose Your Path**
By completing this course, you will have implemented a complete ML system: ### **👨‍🏫 For Instructors**
**[📖 Instructor Guide](docs/INSTRUCTOR_GUIDE.md)** - Complete teaching guide with verified modules, class structure, and commands
- 6+ weeks of proven curriculum content
- Verified module status and teaching sequence
- Class session structure and troubleshooting guide
**Core Framework** → **Training Pipeline** → **Production System** ### **👨‍🎓 For Students**
- ✅ Tensors with automatic differentiation **[🔥 Student Guide](docs/STUDENT_GUIDE.md)** - Complete learning path with clear workflow
- ✅ Neural network layers (MLP, CNN, Transformer) - Step-by-step progress tracker
- ✅ Training loops with optimizers (SGD, Adam) - 5-step daily workflow for each module
- ✅ Data loading and preprocessing pipelines - Getting help and study tips
- ✅ Model compression (pruning, quantization)
- ✅ Performance profiling and optimization
- ✅ Production deployment and monitoring
## 🚀 Quick Start ### **🛠️ For Developers**
**[📚 Documentation](docs/)** - Complete documentation including pedagogy and development guides
**Ready to build? Choose your path:** ## 🎯 **What Students Build**
### 🏃‍♂️ I want to start building now By completing TinyTorch, students implement a complete ML framework:
→ **[QUICKSTART.md](QUICKSTART.md)** - Get coding in 10 minutes
### 📚 I want to understand the full course structure - ✅ **Activation functions** (ReLU, Sigmoid, Tanh)
→ **[PROJECT_GUIDE.md](PROJECT_GUIDE.md)** - Complete learning roadmap - ✅ **Neural network layers** (Dense, Conv2D)
- ✅ **Network architectures** (Sequential, MLP)
- ✅ **Data loading** (CIFAR-10 pipeline)
- ✅ **Development workflow** (export, test, use)
- 🚧 **Tensor operations** (arithmetic, broadcasting)
- 🚧 **Automatic differentiation** (backpropagation)
- 🚧 **Training systems** (optimizers, loss functions)
### 🔍 I want to see the course in action ## 🎓 **Learning Philosophy: Build → Use → Understand → Repeat**
→ **[modules/setup/](modules/setup/)** - Browse the first module
## 🎓 Learning Approach Students experience the complete cycle:
1. **Build**: Implement `ReLU()` function from scratch
2. **Use**: Import `from tinytorch.core.activations import ReLU` with their own code
3. **Understand**: See how it works in real neural networks
4. **Repeat**: Each module builds on previous implementations
**Module-First Development**: Each module is self-contained with its own notebook, tests, and learning objectives. You'll work in Jupyter notebooks using the [nbdev](https://nbdev.fast.ai/) workflow to build a real Python package. ## 📊 **Current Status** (Ready for Classroom Use)
**The Cycle**: `Write Code → Export → Test → Next Module` ### **✅ Fully Working Modules** (6+ weeks of content)
- **00_setup** (20/20 tests) - Development workflow & CLI tools
- **02_activations** (24/24 tests) - ReLU, Sigmoid, Tanh functions
- **03_layers** (17/22 tests) - Dense layers & neural building blocks
- **04_networks** (20/25 tests) - Sequential networks & MLPs
- **06_dataloader** (15/15 tests) - CIFAR-10 data loading
- **05_cnn** (2/2 tests) - Convolution operations
### **🚧 In Development**
- **01_tensor** (22/33 tests) - Tensor arithmetic
- **07-13** - Advanced features (autograd, training, MLOps)
## 🚀 **Quick Commands**
### **System Status**
```bash ```bash
# The rhythm you'll use for every module tito system info # Check system and module status
jupyter lab tensor_dev.ipynb # Write & test interactively tito system doctor # Verify environment setup
python bin/tito.py sync # Export to Python package tito module status # View all module progress
python bin/tito.py test # Verify implementation
``` ```
## 📚 Course Structure ### **Student Workflow**
| Phase | Modules | What You'll Build |
|-------|---------|-------------------|
| **Foundation** | Setup, Tensor, Autograd | Core mathematical engine |
| **Neural Networks** | MLP, CNN | Learning algorithms |
| **Training Systems** | Data, Training, Config | End-to-end pipelines |
| **Production** | Profiling, Compression, MLOps | Real-world deployment |
**Total Time**: 40-80 hours over several weeks • **Prerequisites**: Python basics
## 🛠️ Key Commands
```bash ```bash
python bin/tito.py info # Check progress cd modules/00_setup # Navigate to first module
python bin/tito.py sync # Export notebooks jupyter lab setup_dev.py # Open development notebook
python bin/tito.py test --module [name] # Test implementation python -m pytest tests/ -v # Run tests
python bin/tito module export 00_setup # Export to package
``` ```
## 🌟 Why Tiny🔥Torch? ### **Verify Implementation**
```bash
# Use student's own implementations
python -c "from tinytorch.core.utils import hello_tinytorch; hello_tinytorch()"
python -c "from tinytorch.core.activations import ReLU; print(ReLU()([-1, 0, 1]))"
```
**Systems Engineering Principles**: Learn to design ML systems from first principles ## 🌟 **Why Build from Scratch?**
**Hardware-Software Co-design**: Understand how algorithms map to computational resources
**Performance-Aware Development**: Build systems optimized for real-world constraints
**End-to-End Systems**: From mathematical foundations to production deployment
## 📖 Educational Approach **Even in the age of AI-generated code, building systems from scratch remains educationally essential:**
**Companion to [Machine Learning Systems](https://mlsysbook.ai)**: This course provides hands-on implementation exercises that bring the book's concepts to life through code. - **Understanding vs. Using**: AI shows *what* works, TinyTorch teaches *why* it works
- **Systems Literacy**: Debugging real ML requires understanding abstractions like autograd and data loaders
- **AI-Augmented Engineers**: The best engineers collaborate with AI tools, not rely on them blindly
- **Intentional Design**: Systems thinking about memory, performance, and architecture can't be outsourced
**Learning by Building**: Following the educational philosophy of [Karpathy's micrograd](https://github.com/karpathy/micrograd), we learn complex systems by implementing them from scratch. ## 🏗️ **Repository Structure**
**Real-World Systems**: Drawing from production [PyTorch](https://pytorch.org/) and [JAX](https://jax.readthedocs.io/) architectures to understand industry-proven design patterns. ```
TinyTorch/
├── README.md # This file - main entry point
├── docs/
│ ├── INSTRUCTOR_GUIDE.md # Complete teaching guide
│ ├── STUDENT_GUIDE.md # Complete learning path
│ └── [detailed docs] # Pedagogy and development guides
├── modules/
│ ├── 00_setup/ # Development workflow
│ ├── 01_tensor/ # Tensor operations
│ ├── 02_activations/ # Activation functions
│ ├── 03_layers/ # Neural network layers
│ ├── 04_networks/ # Network architectures
│ ├── 05_cnn/ # Convolution operations
│ ├── 06_dataloader/ # Data loading pipeline
│ └── 07-13/ # Advanced features
├── tinytorch/ # The actual Python package
├── bin/ # CLI tools (tito)
└── tests/ # Integration tests
```
## 🤔 Frequently Asked Questions ## 📚 **Educational Approach**
<details> ### **Real Data, Real Systems**
<summary><strong>Why should students build TinyTorch if AI agents can already generate similar code?</strong></summary> - Work with CIFAR-10 (10,000 real images)
- Production-style code organization
- Performance and engineering considerations
Even though large language models can generate working ML code, building systems from scratch remains *pedagogically essential*: ### **Immediate Feedback**
- Tests provide instant verification
- Students see their code working quickly
- Progress is visible and measurable
- **Understanding vs. Using**: AI-generated code shows what works, but not *why* it works. TinyTorch teaches students to reason through tensor operations, memory flows, and training logic. ### **Progressive Complexity**
- **Systems Literacy**: Debugging and designing real ML pipelines requires understanding abstractions like autograd, data loaders, and parameter updates, not just calling APIs. - Start simple (activation functions)
- **AI-Augmented Engineers**: The best AI engineers will *collaborate with* AI tools, not rely on them blindly. TinyTorch trains students to read, verify, and modify generated code responsibly. - Build complexity gradually (layers → networks → training)
- **Intentional Design**: Systems thinking can’t be outsourced. TinyTorch helps learners internalize how decisions about data layout, execution, and precision affect performance. - Connect to real ML engineering practices
</details> ## 🤝 **Contributing**
<details> We welcome contributions! See our [development documentation](docs/development/) for guidelines on creating new modules or improving existing ones.
<summary><strong>Why not just study the PyTorch or TensorFlow source code instead?</strong></summary>
Industrial frameworks are optimized for scale, not clarity. They contain thousands of lines of code, hardware-specific kernels, and complex abstractions. ## 📄 **License**
TinyTorch, by contrast, is intentionally **minimal** and **educational** — like building a kernel in an operating systems course. It helps learners understand the essential components and build an end-to-end pipeline from first principles.
</details>
<details>
<summary><strong>Isn't it more efficient to just teach ML theory and use existing frameworks?</strong></summary>
Teaching only the math without implementation leaves students unable to debug or extend real-world systems. TinyTorch bridges that gap by making ML systems tangible:
- Students learn by doing, not just reading.
- Implementing backpropagation or a training loop exposes hidden assumptions and tradeoffs.
- Understanding how layers are built gives deeper insight into model behavior and performance.
</details>
<details>
<summary><strong>Why use TinyML in a Machine Learning Systems course?</strong></summary>
TinyML makes systems concepts concrete. By running ML models on constrained hardware, students encounter the real-world limits of memory, compute, latency, and energy — exactly the challenges modern ML engineers face at scale.
- ⚙️ **Hardware constraints** expose architectural tradeoffs that are hidden in cloud settings.
- 🧠 **Systems thinking** is deepened by understanding how models interact with sensors, microcontrollers, and execution runtimes.
- 🌍 **End-to-end ML** becomes tangible — from data ingestion to inference.
TinyML isn’t about toy problems — it’s about simplifying to the point of *clarity*, not abstraction. Students see the full system pipeline, not just the cloud endpoint.
</details>
<details>
<summary><strong>What do the hardware kits add to the learning experience?</strong></summary>
The hardware kits are where learning becomes **hands-on and embodied**. They bring several pedagogical advantages:
- 🔌 **Physicality**: Students see real data flowing through sensors and watch ML models respond — not just print outputs.
- 🧪 **Experimentation**: Kits enable tinkering with latency, power, and model size in ways that are otherwise abstract.
- 🚀 **Creativity**: Students can build real applications — from gesture detection to keyword spotting — using what they learned in TinyTorch.
The kits act as *debuggable, inspectable deployment targets*. They reveal what’s easy vs. hard in ML deployment — and why hardware-aware design matters.
</details>
---
## 🤝 Contributing
We welcome contributions! Whether you're a student who found a bug or an instructor wanting to add modules, see our [Contributing Guide](CONTRIBUTING.md).
## 📄 License
Apache License 2.0 - see the [LICENSE](LICENSE) file for details. Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
--- ---
**Ready to start building?** → [**QUICKSTART.md**](QUICKSTART.md) 🚀 ## 🎉 **Ready to Start?**
### **Instructors**
1. Read the [📖 Instructor Guide](docs/INSTRUCTOR_GUIDE.md)
2. Test your setup: `tito system doctor`
3. Start with: `cd modules/00_setup && jupyter lab setup_dev.py`
### **Students**
1. Read the [🔥 Student Guide](docs/STUDENT_GUIDE.md)
2. Begin with: `cd modules/00_setup && jupyter lab setup_dev.py`
3. Follow the 5-step workflow for each module
**🚀 TinyTorch is ready for classroom use with 6+ weeks of proven curriculum content!**

674
assignments/source/00_setup/00_setup.ipynb
View File

@@ -1,674 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "e3fcd475",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"# Module 0: Setup - Tiny\ud83d\udd25Torch Development Workflow (Enhanced for NBGrader)\n",
"\n",
"Welcome to TinyTorch! This module teaches you the development workflow you'll use throughout the course.\n",
"\n",
"## Learning Goals\n",
"- Understand the nbdev notebook-to-Python workflow\n",
"- Write your first TinyTorch code\n",
"- Run tests and use the CLI tools\n",
"- Get comfortable with the development rhythm\n",
"\n",
"## The TinyTorch Development Cycle\n",
"\n",
"1. **Write code** in this notebook using `#| export` \n",
"2. **Export code** with `python bin/tito.py sync --module setup`\n",
"3. **Run tests** with `python bin/tito.py test --module setup`\n",
"4. **Check progress** with `python bin/tito.py info`\n",
"\n",
"## New: NBGrader Integration\n",
"This module is also configured for automated grading with **100 points total**:\n",
"- Basic Functions: 30 points\n",
"- SystemInfo Class: 35 points \n",
"- DeveloperProfile Class: 35 points\n",
"\n",
"Let's get started!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fba821b3",
"metadata": {},
"outputs": [],
"source": [
"#| default_exp core.utils"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "16465d62",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"# Setup imports and environment\n",
"import sys\n",
"import platform\n",
"from datetime import datetime\n",
"import os\n",
"from pathlib import Path\n",
"\n",
"print(\"\ud83d\udd25 TinyTorch Development Environment\")\n",
"print(f\"Python {sys.version}\")\n",
"print(f\"Platform: {platform.system()} {platform.release()}\")\n",
"print(f\"Started: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\")"
]
},
{
"cell_type": "markdown",
"id": "64d86ea8",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 1: Basic Functions (30 Points)\n",
"\n",
"Let's start with simple functions that form the foundation of TinyTorch."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ab7eb118",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"def hello_tinytorch():\n",
" \"\"\"\n",
" A simple hello world function for TinyTorch.\n",
" \n",
" Display TinyTorch ASCII art and welcome message.\n",
" Load the flame art from tinytorch_flame.txt file with graceful fallback.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Load ASCII art from tinytorch_flame.txt file with graceful fallback\n",
" #| solution_test: Function should display ASCII art and welcome message\n",
" #| difficulty: easy\n",
" #| points: 10\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
"\n",
"def add_numbers(a, b):\n",
" \"\"\"\n",
" Add two numbers together.\n",
" \n",
" This is the foundation of all mathematical operations in ML.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use the + operator to add two numbers\n",
" #| solution_test: add_numbers(2, 3) should return 5\n",
" #| difficulty: easy\n",
" #| points: 10\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end"
]
},
{
"cell_type": "markdown",
"id": "4b7256a9",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Hidden Tests: Basic Functions (10 Points)\n",
"\n",
"These tests verify the basic functionality and award points automatically."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2fc78732",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"### BEGIN HIDDEN TESTS\n",
"def test_hello_tinytorch():\n",
" \"\"\"Test hello_tinytorch function (5 points)\"\"\"\n",
" import io\n",
" import sys\n",
" \n",
" # Capture output\n",
" captured_output = io.StringIO()\n",
" sys.stdout = captured_output\n",
" \n",
" try:\n",
" hello_tinytorch()\n",
" output = captured_output.getvalue()\n",
" \n",
" # Check that some output was produced\n",
" assert len(output) > 0, \"Function should produce output\"\n",
" assert \"TinyTorch\" in output, \"Output should contain 'TinyTorch'\"\n",
" \n",
" finally:\n",
" sys.stdout = sys.__stdout__\n",
"\n",
"def test_add_numbers():\n",
" \"\"\"Test add_numbers function (5 points)\"\"\"\n",
" # Test basic addition\n",
" assert add_numbers(2, 3) == 5, \"add_numbers(2, 3) should return 5\"\n",
" assert add_numbers(0, 0) == 0, \"add_numbers(0, 0) should return 0\"\n",
" assert add_numbers(-1, 1) == 0, \"add_numbers(-1, 1) should return 0\"\n",
" \n",
" # Test with floats\n",
" assert add_numbers(2.5, 3.5) == 6.0, \"add_numbers(2.5, 3.5) should return 6.0\"\n",
" \n",
" # Test with negative numbers\n",
" assert add_numbers(-5, -3) == -8, \"add_numbers(-5, -3) should return -8\"\n",
"### END HIDDEN TESTS"
]
},
{
"cell_type": "markdown",
"id": "d457e1bf",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 2: SystemInfo Class (35 Points)\n",
"\n",
"Let's create a class that collects and displays system information."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c78b6a2e",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"class SystemInfo:\n",
" \"\"\"\n",
" Simple system information class.\n",
" \n",
" Collects and displays Python version, platform, and machine information.\n",
" \"\"\"\n",
" \n",
" def __init__(self):\n",
" \"\"\"\n",
" Initialize system information collection.\n",
" \n",
" Collect Python version, platform, and machine information.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use sys.version_info, platform.system(), and platform.machine()\n",
" #| solution_test: Should store Python version, platform, and machine info\n",
" #| difficulty: medium\n",
" #| points: 15\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def __str__(self):\n",
" \"\"\"\n",
" Return human-readable system information.\n",
" \n",
" Format system info as a readable string.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Format as \"Python X.Y on Platform (Machine)\"\n",
" #| solution_test: Should return formatted string with version and platform\n",
" #| difficulty: easy\n",
" #| points: 10\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def is_compatible(self):\n",
" \"\"\"\n",
" Check if system meets minimum requirements.\n",
" \n",
" Check if Python version is >= 3.8\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Compare self.python_version with (3, 8) tuple\n",
" #| solution_test: Should return True for Python >= 3.8\n",
" #| difficulty: medium\n",
" #| points: 10\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end"
]
},
{
"cell_type": "markdown",
"id": "9aceffc4",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Hidden Tests: SystemInfo Class (35 Points)\n",
"\n",
"These tests verify the SystemInfo class implementation."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e7738e0f",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"### BEGIN HIDDEN TESTS\n",
"def test_systeminfo_init():\n",
" \"\"\"Test SystemInfo initialization (15 points)\"\"\"\n",
" info = SystemInfo()\n",
" \n",
" # Check that attributes are set\n",
" assert hasattr(info, 'python_version'), \"Should have python_version attribute\"\n",
" assert hasattr(info, 'platform'), \"Should have platform attribute\"\n",
" assert hasattr(info, 'machine'), \"Should have machine attribute\"\n",
" \n",
" # Check types\n",
" assert isinstance(info.python_version, tuple), \"python_version should be tuple\"\n",
" assert isinstance(info.platform, str), \"platform should be string\"\n",
" assert isinstance(info.machine, str), \"machine should be string\"\n",
" \n",
" # Check values are reasonable\n",
" assert len(info.python_version) >= 2, \"python_version should have at least major.minor\"\n",
" assert len(info.platform) > 0, \"platform should not be empty\"\n",
"\n",
"def test_systeminfo_str():\n",
" \"\"\"Test SystemInfo string representation (10 points)\"\"\"\n",
" info = SystemInfo()\n",
" str_repr = str(info)\n",
" \n",
" # Check that the string contains expected elements\n",
" assert \"Python\" in str_repr, \"String should contain 'Python'\"\n",
" assert str(info.python_version.major) in str_repr, \"String should contain major version\"\n",
" assert str(info.python_version.minor) in str_repr, \"String should contain minor version\"\n",
" assert info.platform in str_repr, \"String should contain platform\"\n",
" assert info.machine in str_repr, \"String should contain machine\"\n",
"\n",
"def test_systeminfo_compatibility():\n",
" \"\"\"Test SystemInfo compatibility check (10 points)\"\"\"\n",
" info = SystemInfo()\n",
" compatibility = info.is_compatible()\n",
" \n",
" # Check that it returns a boolean\n",
" assert isinstance(compatibility, bool), \"is_compatible should return boolean\"\n",
" \n",
" # Check that it's reasonable (we're running Python >= 3.8)\n",
" assert compatibility == True, \"Should return True for Python >= 3.8\"\n",
"### END HIDDEN TESTS"
]
},
{
"cell_type": "markdown",
"id": "da0fd46d",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 3: DeveloperProfile Class (35 Points)\n",
"\n",
"Let's create a personalized developer profile system."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c7cd22cd",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"class DeveloperProfile:\n",
" \"\"\"\n",
" Developer profile for personalizing TinyTorch experience.\n",
" \n",
" Stores and displays developer information with ASCII art.\n",
" \"\"\"\n",
" \n",
" @staticmethod\n",
" def _load_default_flame():\n",
" \"\"\"\n",
" Load the default TinyTorch flame ASCII art from file.\n",
" \n",
" Load from tinytorch_flame.txt with graceful fallback.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use Path and file operations with try/except for fallback\n",
" #| solution_test: Should load ASCII art from file or provide fallback\n",
" #| difficulty: hard\n",
" #| points: 5\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def __init__(self, name=\"Vijay Janapa Reddi\", affiliation=\"Harvard University\", \n",
" email=\"vj@eecs.harvard.edu\", github_username=\"profvjreddi\", ascii_art=None):\n",
" \"\"\"\n",
" Initialize developer profile.\n",
" \n",
" Store developer information with sensible defaults.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Store all parameters as instance attributes, use _load_default_flame for ascii_art if None\n",
" #| solution_test: Should store all developer information\n",
" #| difficulty: medium\n",
" #| points: 15\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def __str__(self):\n",
" \"\"\"\n",
" Return formatted developer information.\n",
" \n",
" Format as professional signature.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Format as \"\ud83d\udc68\u200d\ud83d\udcbb Name | Affiliation | @username\"\n",
" #| solution_test: Should return formatted string with name, affiliation, and username\n",
" #| difficulty: easy\n",
" #| points: 5\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def get_signature(self):\n",
" \"\"\"\n",
" Get a short signature for code headers.\n",
" \n",
" Return concise signature like \"Built by Name (@github)\"\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Format as \"Built by Name (@username)\"\n",
" #| solution_test: Should return signature with name and username\n",
" #| difficulty: easy\n",
" #| points: 5\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def get_ascii_art(self):\n",
" \"\"\"\n",
" Get ASCII art for the profile.\n",
" \n",
" Return custom ASCII art or default flame.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Simply return self.ascii_art\n",
" #| solution_test: Should return stored ASCII art\n",
" #| difficulty: easy\n",
" #| points: 5\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end"
]
},
{
"cell_type": "markdown",
"id": "c58a5de4",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Hidden Tests: DeveloperProfile Class (35 Points)\n",
"\n",
"These tests verify the DeveloperProfile class implementation."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a74d8133",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"### BEGIN HIDDEN TESTS\n",
"def test_developer_profile_init():\n",
" \"\"\"Test DeveloperProfile initialization (15 points)\"\"\"\n",
" # Test with defaults\n",
" profile = DeveloperProfile()\n",
" \n",
" assert hasattr(profile, 'name'), \"Should have name attribute\"\n",
" assert hasattr(profile, 'affiliation'), \"Should have affiliation attribute\"\n",
" assert hasattr(profile, 'email'), \"Should have email attribute\"\n",
" assert hasattr(profile, 'github_username'), \"Should have github_username attribute\"\n",
" assert hasattr(profile, 'ascii_art'), \"Should have ascii_art attribute\"\n",
" \n",
" # Check default values\n",
" assert profile.name == \"Vijay Janapa Reddi\", \"Should have default name\"\n",
" assert profile.affiliation == \"Harvard University\", \"Should have default affiliation\"\n",
" assert profile.email == \"vj@eecs.harvard.edu\", \"Should have default email\"\n",
" assert profile.github_username == \"profvjreddi\", \"Should have default username\"\n",
" assert profile.ascii_art is not None, \"Should have ASCII art\"\n",
" \n",
" # Test with custom values\n",
" custom_profile = DeveloperProfile(\n",
" name=\"Test User\",\n",
" affiliation=\"Test University\",\n",
" email=\"test@test.com\",\n",
" github_username=\"testuser\",\n",
" ascii_art=\"Custom Art\"\n",
" )\n",
" \n",
" assert custom_profile.name == \"Test User\", \"Should store custom name\"\n",
" assert custom_profile.affiliation == \"Test University\", \"Should store custom affiliation\"\n",
" assert custom_profile.email == \"test@test.com\", \"Should store custom email\"\n",
" assert custom_profile.github_username == \"testuser\", \"Should store custom username\"\n",
" assert custom_profile.ascii_art == \"Custom Art\", \"Should store custom ASCII art\"\n",
"\n",
"def test_developer_profile_str():\n",
" \"\"\"Test DeveloperProfile string representation (5 points)\"\"\"\n",
" profile = DeveloperProfile()\n",
" str_repr = str(profile)\n",
" \n",
" assert \"\ud83d\udc68\u200d\ud83d\udcbb\" in str_repr, \"Should contain developer emoji\"\n",
" assert profile.name in str_repr, \"Should contain name\"\n",
" assert profile.affiliation in str_repr, \"Should contain affiliation\"\n",
" assert f\"@{profile.github_username}\" in str_repr, \"Should contain @username\"\n",
"\n",
"def test_developer_profile_signature():\n",
" \"\"\"Test DeveloperProfile signature (5 points)\"\"\"\n",
" profile = DeveloperProfile()\n",
" signature = profile.get_signature()\n",
" \n",
" assert \"Built by\" in signature, \"Should contain 'Built by'\"\n",
" assert profile.name in signature, \"Should contain name\"\n",
" assert f\"@{profile.github_username}\" in signature, \"Should contain @username\"\n",
"\n",
"def test_developer_profile_ascii_art():\n",
" \"\"\"Test DeveloperProfile ASCII art (5 points)\"\"\"\n",
" profile = DeveloperProfile()\n",
" ascii_art = profile.get_ascii_art()\n",
" \n",
" assert isinstance(ascii_art, str), \"ASCII art should be string\"\n",
" assert len(ascii_art) > 0, \"ASCII art should not be empty\"\n",
" assert \"TinyTorch\" in ascii_art, \"ASCII art should contain 'TinyTorch'\"\n",
"\n",
"def test_default_flame_loading():\n",
" \"\"\"Test default flame loading (5 points)\"\"\"\n",
" flame_art = DeveloperProfile._load_default_flame()\n",
" \n",
" assert isinstance(flame_art, str), \"Flame art should be string\"\n",
" assert len(flame_art) > 0, \"Flame art should not be empty\"\n",
" assert \"TinyTorch\" in flame_art, \"Flame art should contain 'TinyTorch'\"\n",
"### END HIDDEN TESTS"
]
},
{
"cell_type": "markdown",
"id": "2959453c",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Test Your Implementation\n",
"\n",
"Run these cells to test your implementation:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "75574cd6",
"metadata": {},
"outputs": [],
"source": [
"# Test basic functions\n",
"print(\"Testing Basic Functions:\")\n",
"try:\n",
" hello_tinytorch()\n",
" print(f\"2 + 3 = {add_numbers(2, 3)}\")\n",
" print(\"\u2705 Basic functions working!\")\n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e5d4a310",
"metadata": {},
"outputs": [],
"source": [
"# Test SystemInfo\n",
"print(\"\\nTesting SystemInfo:\")\n",
"try:\n",
" info = SystemInfo()\n",
" print(f\"System: {info}\")\n",
" print(f\"Compatible: {info.is_compatible()}\")\n",
" print(\"\u2705 SystemInfo working!\")\n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9cd31f75",
"metadata": {},
"outputs": [],
"source": [
"# Test DeveloperProfile\n",
"print(\"\\nTesting DeveloperProfile:\")\n",
"try:\n",
" profile = DeveloperProfile()\n",
" print(f\"Profile: {profile}\")\n",
" print(f\"Signature: {profile.get_signature()}\")\n",
" print(\"\u2705 DeveloperProfile working!\")\n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")"
]
},
{
"cell_type": "markdown",
"id": "95483816",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## \ud83c\udf89 Module Complete!\n",
"\n",
"You've successfully implemented the setup module with **100 points total**:\n",
"\n",
"### Point Breakdown:\n",
"- **hello_tinytorch()**: 10 points\n",
"- **add_numbers()**: 10 points \n",
"- **Basic function tests**: 10 points\n",
"- **SystemInfo.__init__()**: 15 points\n",
"- **SystemInfo.__str__()**: 10 points\n",
"- **SystemInfo.is_compatible()**: 10 points\n",
"- **DeveloperProfile.__init__()**: 15 points\n",
"- **DeveloperProfile methods**: 20 points\n",
"\n",
"### What's Next:\n",
"1. Export your code: `tito sync --module setup`\n",
"2. Run tests: `tito test --module setup`\n",
"3. Generate assignment: `tito nbgrader generate --module setup`\n",
"4. Move to Module 1: Tensor!\n",
"\n",
"### NBGrader Features:\n",
"- \u2705 Automatic grading with 100 points\n",
"- \u2705 Partial credit for each component\n",
"- \u2705 Hidden tests for comprehensive validation\n",
"- \u2705 Immediate feedback for students\n",
"- \u2705 Compatible with existing TinyTorch workflow\n",
"\n",
"Happy building! \ud83d\udd25"
]
}
],
"metadata": {
"jupytext": {
"main_language": "python"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

480
assignments/source/01_tensor/01_tensor.ipynb
View File

@@ -1,480 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "0cf257dc",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"# Module 1: Tensor - Enhanced with nbgrader Support\n",
"\n",
"This is an enhanced version of the tensor module that demonstrates dual-purpose content creation:\n",
"- **Self-learning**: Rich educational content with guided implementation\n",
"- **Auto-grading**: nbgrader-compatible assignments with hidden tests\n",
"\n",
"## Dual System Benefits\n",
"\n",
"1. **Single Source**: One file generates both learning and assignment materials\n",
"2. **Consistent Quality**: Same instructor solutions in both contexts\n",
"3. **Flexible Assessment**: Choose between self-paced learning or formal grading\n",
"4. **Scalable**: Handle large courses with automated feedback\n",
"\n",
"## How It Works\n",
"\n",
"- **TinyTorch markers**: `#| exercise_start/end` for educational content\n",
"- **nbgrader markers**: `### BEGIN/END SOLUTION` for auto-grading\n",
"- **Hidden tests**: `### BEGIN/END HIDDEN TESTS` for automatic verification\n",
"- **Dual generation**: One command creates both student notebooks and assignments"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dbe77981",
"metadata": {},
"outputs": [],
"source": [
"#| default_exp core.tensor"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7dc4f1a0",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"import numpy as np\n",
"from typing import Union, List, Tuple, Optional"
]
},
{
"cell_type": "markdown",
"id": "1765d8cb",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Enhanced Tensor Class\n",
"\n",
"This implementation shows how to create dual-purpose educational content:\n",
"\n",
"### For Self-Learning Students\n",
"- Rich explanations and step-by-step guidance\n",
"- Detailed hints and examples\n",
"- Progressive difficulty with scaffolding\n",
"\n",
"### For Formal Assessment\n",
"- Auto-graded with hidden tests\n",
"- Immediate feedback on correctness\n",
"- Partial credit for complex methods"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aff9a0f2",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"class Tensor:\n",
" \"\"\"\n",
" TinyTorch Tensor: N-dimensional array with ML operations.\n",
" \n",
" This enhanced version demonstrates dual-purpose educational content\n",
" suitable for both self-learning and formal assessment.\n",
" \"\"\"\n",
" \n",
" def __init__(self, data: Union[int, float, List, np.ndarray], dtype: Optional[str] = None):\n",
" \"\"\"\n",
" Create a new tensor from data.\n",
" \n",
" Args:\n",
" data: Input data (scalar, list, or numpy array)\n",
" dtype: Data type ('float32', 'int32', etc.). Defaults to auto-detect.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use np.array() to convert input data to numpy array\n",
" #| solution_test: tensor.shape should match input shape\n",
" #| difficulty: easy\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" if isinstance(data, (int, float)):\n",
" self._data = np.array(data)\n",
" elif isinstance(data, list):\n",
" self._data = np.array(data)\n",
" elif isinstance(data, np.ndarray):\n",
" self._data = data.copy()\n",
" else:\n",
" self._data = np.array(data)\n",
" \n",
" # Apply dtype conversion if specified\n",
" if dtype is not None:\n",
" self._data = self._data.astype(dtype)\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" @property\n",
" def data(self) -> np.ndarray:\n",
" \"\"\"Access underlying numpy array.\"\"\"\n",
" #| exercise_start\n",
" #| hint: Return the stored numpy array (_data attribute)\n",
" #| solution_test: tensor.data should return numpy array\n",
" #| difficulty: easy\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" @property\n",
" def shape(self) -> Tuple[int, ...]:\n",
" \"\"\"Get tensor shape.\"\"\"\n",
" #| exercise_start\n",
" #| hint: Use the .shape attribute of the numpy array\n",
" #| solution_test: tensor.shape should return tuple of dimensions\n",
" #| difficulty: easy\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" @property\n",
" def size(self) -> int:\n",
" \"\"\"Get total number of elements.\"\"\"\n",
" #| exercise_start\n",
" #| hint: Use the .size attribute of the numpy array\n",
" #| solution_test: tensor.size should return total element count\n",
" #| difficulty: easy\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" @property\n",
" def dtype(self) -> np.dtype:\n",
" \"\"\"Get data type as numpy dtype.\"\"\"\n",
" #| exercise_start\n",
" #| hint: Use the .dtype attribute of the numpy array\n",
" #| solution_test: tensor.dtype should return numpy dtype\n",
" #| difficulty: easy\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def __repr__(self) -> str:\n",
" \"\"\"String representation of the tensor.\"\"\"\n",
" #| exercise_start\n",
" #| hint: Format as \"Tensor([data], shape=shape, dtype=dtype)\"\n",
" #| solution_test: repr should include data, shape, and dtype\n",
" #| difficulty: medium\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" return f\"Tensor({data_str}, shape={self.shape}, dtype={self.dtype})\"\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def add(self, other: 'Tensor') -> 'Tensor':\n",
" \"\"\"\n",
" Add two tensors element-wise.\n",
" \n",
" Args:\n",
" other: Another tensor to add\n",
" \n",
" Returns:\n",
" New tensor with element-wise sum\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use numpy's + operator for element-wise addition\n",
" #| solution_test: result should be new Tensor with correct values\n",
" #| difficulty: medium\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" return Tensor(result_data)\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def multiply(self, other: 'Tensor') -> 'Tensor':\n",
" \"\"\"\n",
" Multiply two tensors element-wise.\n",
" \n",
" Args:\n",
" other: Another tensor to multiply\n",
" \n",
" Returns:\n",
" New tensor with element-wise product\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use numpy's * operator for element-wise multiplication\n",
" #| solution_test: result should be new Tensor with correct values\n",
" #| difficulty: medium\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" return Tensor(result_data)\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end\n",
" \n",
" def matmul(self, other: 'Tensor') -> 'Tensor':\n",
" \"\"\"\n",
" Matrix multiplication of two tensors.\n",
" \n",
" Args:\n",
" other: Another tensor for matrix multiplication\n",
" \n",
" Returns:\n",
" New tensor with matrix product\n",
" \n",
" Raises:\n",
" ValueError: If shapes are incompatible for matrix multiplication\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Use np.dot() for matrix multiplication, check shapes first\n",
" #| solution_test: result should handle shape validation and matrix multiplication\n",
" #| difficulty: hard\n",
" \n",
" ### BEGIN SOLUTION\n",
" # YOUR CODE HERE\n",
" raise NotImplementedError()\n",
" if len(self.shape) != 2 or len(other.shape) != 2:\n",
" raise ValueError(\"Matrix multiplication requires 2D tensors\")\n",
" \n",
" if self.shape[1] != other.shape[0]:\n",
" raise ValueError(f\"Cannot multiply shapes {self.shape} and {other.shape}\")\n",
" \n",
" result_data = np.dot(self._data, other._data)\n",
" return Tensor(result_data)\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end"
]
},
{
"cell_type": "markdown",
"id": "90c887d9",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Hidden Tests for Auto-Grading\n",
"\n",
"These tests are hidden from students but used for automatic grading.\n",
"They provide comprehensive coverage and immediate feedback."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "67d0055f",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"### BEGIN HIDDEN TESTS\n",
"def test_tensor_creation_basic():\n",
" \"\"\"Test basic tensor creation (2 points)\"\"\"\n",
" t = Tensor([1, 2, 3])\n",
" assert t.shape == (3,)\n",
" assert t.data.tolist() == [1, 2, 3]\n",
" assert t.size == 3\n",
"\n",
"def test_tensor_creation_scalar():\n",
" \"\"\"Test scalar tensor creation (2 points)\"\"\"\n",
" t = Tensor(5)\n",
" assert t.shape == ()\n",
" assert t.data.item() == 5\n",
" assert t.size == 1\n",
"\n",
"def test_tensor_creation_2d():\n",
" \"\"\"Test 2D tensor creation (2 points)\"\"\"\n",
" t = Tensor([[1, 2], [3, 4]])\n",
" assert t.shape == (2, 2)\n",
" assert t.data.tolist() == [[1, 2], [3, 4]]\n",
" assert t.size == 4\n",
"\n",
"def test_tensor_dtype():\n",
" \"\"\"Test dtype handling (2 points)\"\"\"\n",
" t = Tensor([1, 2, 3], dtype='float32')\n",
" assert t.dtype == np.float32\n",
" assert t.data.dtype == np.float32\n",
"\n",
"def test_tensor_properties():\n",
" \"\"\"Test tensor properties (2 points)\"\"\"\n",
" t = Tensor([[1, 2, 3], [4, 5, 6]])\n",
" assert t.shape == (2, 3)\n",
" assert t.size == 6\n",
" assert isinstance(t.data, np.ndarray)\n",
"\n",
"def test_tensor_repr():\n",
" \"\"\"Test string representation (2 points)\"\"\"\n",
" t = Tensor([1, 2, 3])\n",
" repr_str = repr(t)\n",
" assert \"Tensor\" in repr_str\n",
" assert \"shape\" in repr_str\n",
" assert \"dtype\" in repr_str\n",
"\n",
"def test_tensor_add():\n",
" \"\"\"Test tensor addition (3 points)\"\"\"\n",
" t1 = Tensor([1, 2, 3])\n",
" t2 = Tensor([4, 5, 6])\n",
" result = t1.add(t2)\n",
" assert result.data.tolist() == [5, 7, 9]\n",
" assert result.shape == (3,)\n",
"\n",
"def test_tensor_multiply():\n",
" \"\"\"Test tensor multiplication (3 points)\"\"\"\n",
" t1 = Tensor([1, 2, 3])\n",
" t2 = Tensor([4, 5, 6])\n",
" result = t1.multiply(t2)\n",
" assert result.data.tolist() == [4, 10, 18]\n",
" assert result.shape == (3,)\n",
"\n",
"def test_tensor_matmul():\n",
" \"\"\"Test matrix multiplication (4 points)\"\"\"\n",
" t1 = Tensor([[1, 2], [3, 4]])\n",
" t2 = Tensor([[5, 6], [7, 8]])\n",
" result = t1.matmul(t2)\n",
" expected = [[19, 22], [43, 50]]\n",
" assert result.data.tolist() == expected\n",
" assert result.shape == (2, 2)\n",
"\n",
"def test_tensor_matmul_error():\n",
" \"\"\"Test matrix multiplication error handling (2 points)\"\"\"\n",
" t1 = Tensor([[1, 2, 3]]) # Shape (1, 3)\n",
" t2 = Tensor([[4, 5]]) # Shape (1, 2)\n",
" \n",
" try:\n",
" t1.matmul(t2)\n",
" assert False, \"Should have raised ValueError\"\n",
" except ValueError as e:\n",
" assert \"Cannot multiply shapes\" in str(e)\n",
"\n",
"def test_tensor_immutability():\n",
" \"\"\"Test that operations create new tensors (2 points)\"\"\"\n",
" t1 = Tensor([1, 2, 3])\n",
" t2 = Tensor([4, 5, 6])\n",
" original_data = t1.data.copy()\n",
" \n",
" result = t1.add(t2)\n",
" \n",
" # Original tensor should be unchanged\n",
" assert np.array_equal(t1.data, original_data)\n",
" # Result should be different object\n",
" assert result is not t1\n",
" assert result.data is not t1.data\n",
"\n",
"### END HIDDEN TESTS"
]
},
{
"cell_type": "markdown",
"id": "636ac01d",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Usage Examples\n",
"\n",
"### Self-Learning Mode\n",
"Students work through the educational content step by step:\n",
"\n",
"```python\n",
"# Create tensors\n",
"t1 = Tensor([1, 2, 3])\n",
"t2 = Tensor([4, 5, 6])\n",
"\n",
"# Basic operations\n",
"result = t1.add(t2)\n",
"print(f\"Addition: {result}\")\n",
"\n",
"# Matrix operations\n",
"matrix1 = Tensor([[1, 2], [3, 4]])\n",
"matrix2 = Tensor([[5, 6], [7, 8]])\n",
"product = matrix1.matmul(matrix2)\n",
"print(f\"Matrix multiplication: {product}\")\n",
"```\n",
"\n",
"### Assignment Mode\n",
"Students submit implementations that are automatically graded:\n",
"\n",
"1. **Immediate feedback**: Know if implementation is correct\n",
"2. **Partial credit**: Earn points for each working method\n",
"3. **Hidden tests**: Comprehensive coverage beyond visible examples\n",
"4. **Error handling**: Points for proper edge case handling\n",
"\n",
"### Benefits of Dual System\n",
"\n",
"1. **Single source**: One implementation serves both purposes\n",
"2. **Consistent quality**: Same instructor solutions everywhere\n",
"3. **Flexible assessment**: Choose the right tool for each situation\n",
"4. **Scalable**: Handle large courses with automated feedback\n",
"\n",
"This approach transforms TinyTorch from a learning framework into a complete course management solution."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cd296b25",
"metadata": {},
"outputs": [],
"source": [
"# Test the implementation\n",
"if __name__ == \"__main__\":\n",
" # Basic testing\n",
" t1 = Tensor([1, 2, 3])\n",
" t2 = Tensor([4, 5, 6])\n",
" \n",
" print(f\"t1: {t1}\")\n",
" print(f\"t2: {t2}\")\n",
" print(f\"t1 + t2: {t1.add(t2)}\")\n",
" print(f\"t1 * t2: {t1.multiply(t2)}\")\n",
" \n",
" # Matrix multiplication\n",
" m1 = Tensor([[1, 2], [3, 4]])\n",
" m2 = Tensor([[5, 6], [7, 8]])\n",
" print(f\"Matrix multiplication: {m1.matmul(m2)}\")\n",
" \n",
" print(\"\u2705 Enhanced tensor module working!\") "
]
}
],
"metadata": {
"jupytext": {
"main_language": "python"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

1143
assignments/source/02_activations/02_activations.ipynb
View File

File diff suppressed because it is too large Load Diff

797
assignments/source/03_layers/03_layers.ipynb
View File

@@ -1,797 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "0a3df1fa",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"# Module 2: Layers - Neural Network Building Blocks\n",
"\n",
"Welcome to the Layers module! This is where neural networks begin. You'll implement the fundamental building blocks that transform tensors.\n",
"\n",
"## Learning Goals\n",
"- Understand layers as functions that transform tensors: `y = f(x)`\n",
"- Implement Dense layers with linear transformations: `y = Wx + b`\n",
"- Use activation functions from the activations module for nonlinearity\n",
"- See how neural networks are just function composition\n",
"- Build intuition before diving into training\n",
"\n",
"## Build \u2192 Use \u2192 Understand\n",
"1. **Build**: Dense layers using activation functions as building blocks\n",
"2. **Use**: Transform tensors and see immediate results\n",
"3. **Understand**: How neural networks transform information\n",
"\n",
"## Module Dependencies\n",
"This module builds on the **activations** module:\n",
"- **activations** \u2192 **layers** \u2192 **networks**\n",
"- Clean separation of concerns: math functions \u2192 layer building blocks \u2192 full networks"
]
},
{
"cell_type": "markdown",
"id": "7ad0cde1",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## \ud83d\udce6 Where This Code Lives in the Final Package\n",
"\n",
"**Learning Side:** You work in `modules/03_layers/layers_dev.py` \n",
"**Building Side:** Code exports to `tinytorch.core.layers`\n",
"\n",
"```python\n",
"# Final package structure:\n",
"from tinytorch.core.layers import Dense, Conv2D # All layers together!\n",
"from tinytorch.core.activations import ReLU, Sigmoid, Tanh\n",
"from tinytorch.core.tensor import Tensor\n",
"```\n",
"\n",
"**Why this matters:**\n",
"- **Learning:** Focused modules for deep understanding\n",
"- **Production:** Proper organization like PyTorch's `torch.nn`\n",
"- **Consistency:** All layers (Dense, Conv2D) live together in `core.layers`"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5e2b163c",
"metadata": {},
"outputs": [],
"source": [
"#| default_exp core.layers\n",
"\n",
"# Setup and imports\n",
"import numpy as np\n",
"import sys\n",
"from typing import Union, Optional, Callable\n",
"import math"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "75eb63f1",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"import numpy as np\n",
"import math\n",
"import sys\n",
"from typing import Union, Optional, Callable\n",
"\n",
"# Import from the main package (rock solid foundation)\n",
"from tinytorch.core.tensor import Tensor\n",
"from tinytorch.core.activations import ReLU, Sigmoid, Tanh\n",
"\n",
"# print(\"\ud83d\udd25 TinyTorch Layers Module\")\n",
"# print(f\"NumPy version: {np.__version__}\")\n",
"# print(f\"Python version: {sys.version_info.major}.{sys.version_info.minor}\")\n",
"# print(\"Ready to build neural network layers!\")"
]
},
{
"cell_type": "markdown",
"id": "0d8689a4",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Step 1: What is a Layer?\n",
"\n",
"### Definition\n",
"A **layer** is a function that transforms tensors. Think of it as a mathematical operation that takes input data and produces output data:\n",
"\n",
"```\n",
"Input Tensor \u2192 Layer \u2192 Output Tensor\n",
"```\n",
"\n",
"### Why Layers Matter in Neural Networks\n",
"Layers are the fundamental building blocks of all neural networks because:\n",
"- **Modularity**: Each layer has a specific job (linear transformation, nonlinearity, etc.)\n",
"- **Composability**: Layers can be combined to create complex functions\n",
"- **Learnability**: Each layer has parameters that can be learned from data\n",
"- **Interpretability**: Different layers learn different features\n",
"\n",
"### The Fundamental Insight\n",
"**Neural networks are just function composition!**\n",
"```\n",
"x \u2192 Layer1 \u2192 Layer2 \u2192 Layer3 \u2192 y\n",
"```\n",
"\n",
"Each layer transforms the data, and the final output is the composition of all these transformations.\n",
"\n",
"### Real-World Examples\n",
"- **Dense Layer**: Learns linear relationships between features\n",
"- **Convolutional Layer**: Learns spatial patterns in images\n",
"- **Recurrent Layer**: Learns temporal patterns in sequences\n",
"- **Activation Layer**: Adds nonlinearity to make networks powerful\n",
"\n",
"### Visual Intuition\n",
"```\n",
"Input: [1, 2, 3] (3 features)\n",
"Dense Layer: y = Wx + b\n",
"Weights W: [[0.1, 0.2, 0.3],\n",
" [0.4, 0.5, 0.6]] (2\u00d73 matrix)\n",
"Bias b: [0.1, 0.2] (2 values)\n",
"Output: [0.1*1 + 0.2*2 + 0.3*3 + 0.1,\n",
" 0.4*1 + 0.5*2 + 0.6*3 + 0.2] = [1.4, 3.2]\n",
"```\n",
"\n",
"Let's start with the most important layer: **Dense** (also called Linear or Fully Connected)."
]
},
{
"cell_type": "markdown",
"id": "16017609",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 2: Understanding Matrix Multiplication\n",
"\n",
"Before we build layers, let's understand the core operation: **matrix multiplication**. This is what powers all neural network computations.\n",
"\n",
"### Why Matrix Multiplication Matters\n",
"- **Efficiency**: Process multiple inputs at once\n",
"- **Parallelization**: GPU acceleration works great with matrix operations\n",
"- **Batch processing**: Handle multiple samples simultaneously\n",
"- **Mathematical foundation**: Linear algebra is the language of neural networks\n",
"\n",
"### The Math Behind It\n",
"For matrices A (m\u00d7n) and B (n\u00d7p), the result C (m\u00d7p) is:\n",
"```\n",
"C[i,j] = sum(A[i,k] * B[k,j] for k in range(n))\n",
"```\n",
"\n",
"### Visual Example\n",
"```\n",
"A = [[1, 2], B = [[5, 6],\n",
" [3, 4]] [7, 8]]\n",
"\n",
"C = A @ B = [[1*5 + 2*7, 1*6 + 2*8],\n",
" [3*5 + 4*7, 3*6 + 4*8]]\n",
" = [[19, 22],\n",
" [43, 50]]\n",
"```\n",
"\n",
"Let's implement this step by step!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "40630d5d",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray:\n",
" \"\"\"\n",
" Naive matrix multiplication using explicit for-loops.\n",
" \n",
" This helps you understand what matrix multiplication really does!\n",
" \n",
" Args:\n",
" A: Matrix of shape (m, n)\n",
" B: Matrix of shape (n, p)\n",
" \n",
" Returns:\n",
" Matrix of shape (m, p) where C[i,j] = sum(A[i,k] * B[k,j] for k in range(n))\n",
" \n",
" TODO: Implement matrix multiplication using three nested for-loops.\n",
" \n",
" APPROACH:\n",
" 1. Get the dimensions: m, n from A and n2, p from B\n",
" 2. Check that n == n2 (matrices must be compatible)\n",
" 3. Create output matrix C of shape (m, p) filled with zeros\n",
" 4. Use three nested loops:\n",
" - i loop: rows of A (0 to m-1)\n",
" - j loop: columns of B (0 to p-1) \n",
" - k loop: shared dimension (0 to n-1)\n",
" 5. For each (i,j), compute: C[i,j] += A[i,k] * B[k,j]\n",
" \n",
" EXAMPLE:\n",
" A = [[1, 2], B = [[5, 6],\n",
" [3, 4]] [7, 8]]\n",
" \n",
" C[0,0] = A[0,0]*B[0,0] + A[0,1]*B[1,0] = 1*5 + 2*7 = 19\n",
" C[0,1] = A[0,0]*B[0,1] + A[0,1]*B[1,1] = 1*6 + 2*8 = 22\n",
" C[1,0] = A[1,0]*B[0,0] + A[1,1]*B[1,0] = 3*5 + 4*7 = 43\n",
" C[1,1] = A[1,0]*B[0,1] + A[1,1]*B[1,1] = 3*6 + 4*8 = 50\n",
" \n",
" HINTS:\n",
" - Start with C = np.zeros((m, p))\n",
" - Use three nested for loops: for i in range(m): for j in range(p): for k in range(n):\n",
" - Accumulate the sum: C[i,j] += A[i,k] * B[k,j]\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "445593e1",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| hide\n",
"#| export\n",
"def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray:\n",
" \"\"\"\n",
" Naive matrix multiplication using explicit for-loops.\n",
" \n",
" This helps you understand what matrix multiplication really does!\n",
" \"\"\"\n",
" m, n = A.shape\n",
" n2, p = B.shape\n",
" assert n == n2, f\"Matrix shapes don't match: A({m},{n}) @ B({n2},{p})\"\n",
" \n",
" C = np.zeros((m, p))\n",
" for i in range(m):\n",
" for j in range(p):\n",
" for k in range(n):\n",
" C[i, j] += A[i, k] * B[k, j]\n",
" return C"
]
},
{
"cell_type": "markdown",
"id": "e23b8269",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"### \ud83e\uddea Test Your Matrix Multiplication"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "48fadbe0",
"metadata": {},
"outputs": [],
"source": [
"# Test matrix multiplication\n",
"print(\"Testing matrix multiplication...\")\n",
"\n",
"try:\n",
" # Test case 1: Simple 2x2 matrices\n",
" A = np.array([[1, 2], [3, 4]], dtype=np.float32)\n",
" B = np.array([[5, 6], [7, 8]], dtype=np.float32)\n",
" \n",
" result = matmul_naive(A, B)\n",
" expected = np.array([[19, 22], [43, 50]], dtype=np.float32)\n",
" \n",
" print(f\"\u2705 Matrix A:\\n{A}\")\n",
" print(f\"\u2705 Matrix B:\\n{B}\")\n",
" print(f\"\u2705 Your result:\\n{result}\")\n",
" print(f\"\u2705 Expected:\\n{expected}\")\n",
" \n",
" assert np.allclose(result, expected), \"\u274c Result doesn't match expected!\"\n",
" print(\"\ud83c\udf89 Matrix multiplication works!\")\n",
" \n",
" # Test case 2: Compare with NumPy\n",
" numpy_result = A @ B\n",
" assert np.allclose(result, numpy_result), \"\u274c Doesn't match NumPy result!\"\n",
" print(\"\u2705 Matches NumPy implementation!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Make sure to implement matmul_naive above!\")"
]
},
{
"cell_type": "markdown",
"id": "3df7433e",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 3: Building the Dense Layer\n",
"\n",
"Now let's build the **Dense layer**, the most fundamental building block of neural networks. A Dense layer performs a linear transformation: `y = Wx + b`\n",
"\n",
"### What is a Dense Layer?\n",
"- **Linear transformation**: `y = Wx + b`\n",
"- **W**: Weight matrix (learnable parameters)\n",
"- **x**: Input tensor\n",
"- **b**: Bias vector (learnable parameters)\n",
"- **y**: Output tensor\n",
"\n",
"### Why Dense Layers Matter\n",
"- **Universal approximation**: Can approximate any function with enough neurons\n",
"- **Feature learning**: Each neuron learns a different feature\n",
"- **Nonlinearity**: When combined with activation functions, becomes very powerful\n",
"- **Foundation**: All other layers build on this concept\n",
"\n",
"### The Math\n",
"For input x of shape (batch_size, input_size):\n",
"- **W**: Weight matrix of shape (input_size, output_size)\n",
"- **b**: Bias vector of shape (output_size)\n",
"- **y**: Output of shape (batch_size, output_size)\n",
"\n",
"### Visual Example\n",
"```\n",
"Input: x = [1, 2, 3] (3 features)\n",
"Weights: W = [[0.1, 0.2], Bias: b = [0.1, 0.2]\n",
" [0.3, 0.4],\n",
" [0.5, 0.6]]\n",
"\n",
"Step 1: Wx = [0.1*1 + 0.3*2 + 0.5*3, 0.2*1 + 0.4*2 + 0.6*3]\n",
" = [2.2, 3.2]\n",
"\n",
"Step 2: y = Wx + b = [2.2 + 0.1, 3.2 + 0.2] = [2.3, 3.4]\n",
"```\n",
"\n",
"Let's implement this!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c98c433e",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"class Dense:\n",
" \"\"\"\n",
" Dense (Linear) Layer: y = Wx + b\n",
" \n",
" The fundamental building block of neural networks.\n",
" Performs linear transformation: matrix multiplication + bias addition.\n",
" \n",
" Args:\n",
" input_size: Number of input features\n",
" output_size: Number of output features\n",
" use_bias: Whether to include bias term (default: True)\n",
" use_naive_matmul: Whether to use naive matrix multiplication (for learning)\n",
" \n",
" TODO: Implement the Dense layer with weight initialization and forward pass.\n",
" \n",
" APPROACH:\n",
" 1. Store layer parameters (input_size, output_size, use_bias, use_naive_matmul)\n",
" 2. Initialize weights with small random values (Xavier/Glorot initialization)\n",
" 3. Initialize bias to zeros (if use_bias=True)\n",
" 4. Implement forward pass using matrix multiplication and bias addition\n",
" \n",
" EXAMPLE:\n",
" layer = Dense(input_size=3, output_size=2)\n",
" x = Tensor([[1, 2, 3]]) # batch_size=1, input_size=3\n",
" y = layer(x) # shape: (1, 2)\n",
" \n",
" HINTS:\n",
" - Use np.random.randn() for random initialization\n",
" - Scale weights by sqrt(2/(input_size + output_size)) for Xavier init\n",
" - Store weights and bias as numpy arrays\n",
" - Use matmul_naive or @ operator based on use_naive_matmul flag\n",
" \"\"\"\n",
" \n",
" def __init__(self, input_size: int, output_size: int, use_bias: bool = True, \n",
" use_naive_matmul: bool = False):\n",
" \"\"\"\n",
" Initialize Dense layer with random weights.\n",
" \n",
" Args:\n",
" input_size: Number of input features\n",
" output_size: Number of output features\n",
" use_bias: Whether to include bias term\n",
" use_naive_matmul: Use naive matrix multiplication (for learning)\n",
" \n",
" TODO: \n",
" 1. Store layer parameters (input_size, output_size, use_bias, use_naive_matmul)\n",
" 2. Initialize weights with small random values\n",
" 3. Initialize bias to zeros (if use_bias=True)\n",
" \n",
" STEP-BY-STEP:\n",
" 1. Store the parameters as instance variables\n",
" 2. Calculate scale factor for Xavier initialization: sqrt(2/(input_size + output_size))\n",
" 3. Initialize weights: np.random.randn(input_size, output_size) * scale\n",
" 4. If use_bias=True, initialize bias: np.zeros(output_size)\n",
" 5. If use_bias=False, set bias to None\n",
" \n",
" EXAMPLE:\n",
" Dense(3, 2) creates:\n",
" - weights: shape (3, 2) with small random values\n",
" - bias: shape (2,) with zeros\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")\n",
" \n",
" def forward(self, x: Tensor) -> Tensor:\n",
" \"\"\"\n",
" Forward pass: y = Wx + b\n",
" \n",
" Args:\n",
" x: Input tensor of shape (batch_size, input_size)\n",
" \n",
" Returns:\n",
" Output tensor of shape (batch_size, output_size)\n",
" \n",
" TODO: Implement matrix multiplication and bias addition\n",
" - Use self.use_naive_matmul to choose between NumPy and naive implementation\n",
" - If use_naive_matmul=True, use matmul_naive(x.data, self.weights)\n",
" - If use_naive_matmul=False, use x.data @ self.weights\n",
" - Add bias if self.use_bias=True\n",
" \n",
" STEP-BY-STEP:\n",
" 1. Perform matrix multiplication: Wx\n",
" - If use_naive_matmul: result = matmul_naive(x.data, self.weights)\n",
" - Else: result = x.data @ self.weights\n",
" 2. Add bias if use_bias: result += self.bias\n",
" 3. Return Tensor(result)\n",
" \n",
" EXAMPLE:\n",
" Input x: Tensor([[1, 2, 3]]) # shape (1, 3)\n",
" Weights: shape (3, 2)\n",
" Output: Tensor([[val1, val2]]) # shape (1, 2)\n",
" \n",
" HINTS:\n",
" - x.data gives you the numpy array\n",
" - self.weights is your weight matrix\n",
" - Use broadcasting for bias addition: result + self.bias\n",
" - Return Tensor(result) to wrap the result\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")\n",
" \n",
" def __call__(self, x: Tensor) -> Tensor:\n",
" \"\"\"Make layer callable: layer(x) same as layer.forward(x)\"\"\"\n",
" return self.forward(x)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2afc2026",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| hide\n",
"#| export\n",
"class Dense:\n",
" \"\"\"\n",
" Dense (Linear) Layer: y = Wx + b\n",
" \n",
" The fundamental building block of neural networks.\n",
" Performs linear transformation: matrix multiplication + bias addition.\n",
" \"\"\"\n",
" \n",
" def __init__(self, input_size: int, output_size: int, use_bias: bool = True, \n",
" use_naive_matmul: bool = False):\n",
" \"\"\"\n",
" Initialize Dense layer with random weights.\n",
" \n",
" Args:\n",
" input_size: Number of input features\n",
" output_size: Number of output features\n",
" use_bias: Whether to include bias term\n",
" use_naive_matmul: Use naive matrix multiplication (for learning)\n",
" \"\"\"\n",
" # Store parameters\n",
" self.input_size = input_size\n",
" self.output_size = output_size\n",
" self.use_bias = use_bias\n",
" self.use_naive_matmul = use_naive_matmul\n",
" \n",
" # Xavier/Glorot initialization\n",
" scale = np.sqrt(2.0 / (input_size + output_size))\n",
" self.weights = np.random.randn(input_size, output_size).astype(np.float32) * scale\n",
" \n",
" # Initialize bias\n",
" if use_bias:\n",
" self.bias = np.zeros(output_size, dtype=np.float32)\n",
" else:\n",
" self.bias = None\n",
" \n",
" def forward(self, x: Tensor) -> Tensor:\n",
" \"\"\"\n",
" Forward pass: y = Wx + b\n",
" \n",
" Args:\n",
" x: Input tensor of shape (batch_size, input_size)\n",
" \n",
" Returns:\n",
" Output tensor of shape (batch_size, output_size)\n",
" \"\"\"\n",
" # Matrix multiplication\n",
" if self.use_naive_matmul:\n",
" result = matmul_naive(x.data, self.weights)\n",
" else:\n",
" result = x.data @ self.weights\n",
" \n",
" # Add bias\n",
" if self.use_bias:\n",
" result += self.bias\n",
" \n",
" return Tensor(result)\n",
" \n",
" def __call__(self, x: Tensor) -> Tensor:\n",
" \"\"\"Make layer callable: layer(x) same as layer.forward(x)\"\"\"\n",
" return self.forward(x)"
]
},
{
"cell_type": "markdown",
"id": "81d084d3",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"### \ud83e\uddea Test Your Dense Layer"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "24a4e96b",
"metadata": {},
"outputs": [],
"source": [
"# Test Dense layer\n",
"print(\"Testing Dense layer...\")\n",
"\n",
"try:\n",
" # Test basic Dense layer\n",
" layer = Dense(input_size=3, output_size=2, use_bias=True)\n",
" x = Tensor([[1, 2, 3]]) # batch_size=1, input_size=3\n",
" \n",
" print(f\"\u2705 Input shape: {x.shape}\")\n",
" print(f\"\u2705 Layer weights shape: {layer.weights.shape}\")\n",
" print(f\"\u2705 Layer bias shape: {layer.bias.shape}\")\n",
" \n",
" y = layer(x)\n",
" print(f\"\u2705 Output shape: {y.shape}\")\n",
" print(f\"\u2705 Output: {y}\")\n",
" \n",
" # Test without bias\n",
" layer_no_bias = Dense(input_size=2, output_size=1, use_bias=False)\n",
" x2 = Tensor([[1, 2]])\n",
" y2 = layer_no_bias(x2)\n",
" print(f\"\u2705 No bias output: {y2}\")\n",
" \n",
" # Test naive matrix multiplication\n",
" layer_naive = Dense(input_size=2, output_size=2, use_naive_matmul=True)\n",
" x3 = Tensor([[1, 2]])\n",
" y3 = layer_naive(x3)\n",
" print(f\"\u2705 Naive matmul output: {y3}\")\n",
" \n",
" print(\"\\n\ud83c\udf89 All Dense layer tests passed!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Make sure to implement the Dense layer above!\")"
]
},
{
"cell_type": "markdown",
"id": "a527c61e",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Step 4: Composing Layers with Activations\n",
"\n",
"Now let's see how layers work together! A neural network is just layers composed with activation functions.\n",
"\n",
"### Why Layer Composition Matters\n",
"- **Nonlinearity**: Activation functions make networks powerful\n",
"- **Feature learning**: Each layer learns different levels of features\n",
"- **Universal approximation**: Can approximate any function\n",
"- **Modularity**: Easy to experiment with different architectures\n",
"\n",
"### The Pattern\n",
"```\n",
"Input \u2192 Dense \u2192 Activation \u2192 Dense \u2192 Activation \u2192 Output\n",
"```\n",
"\n",
"### Real-World Example\n",
"```\n",
"Input: [1, 2, 3] (3 features)\n",
"Dense(3\u21922): [1.4, 2.8] (linear transformation)\n",
"ReLU: [1.4, 2.8] (nonlinearity)\n",
"Dense(2\u21921): [3.2] (final prediction)\n",
"```\n",
"\n",
"Let's build a simple network!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "db3611ff",
"metadata": {},
"outputs": [],
"source": [
"# Test layer composition\n",
"print(\"Testing layer composition...\")\n",
"\n",
"try:\n",
" # Create a simple network: Dense \u2192 ReLU \u2192 Dense\n",
" dense1 = Dense(input_size=3, output_size=2)\n",
" relu = ReLU()\n",
" dense2 = Dense(input_size=2, output_size=1)\n",
" \n",
" # Test input\n",
" x = Tensor([[1, 2, 3]])\n",
" print(f\"\u2705 Input: {x}\")\n",
" \n",
" # Forward pass through the network\n",
" h1 = dense1(x)\n",
" print(f\"\u2705 After Dense1: {h1}\")\n",
" \n",
" h2 = relu(h1)\n",
" print(f\"\u2705 After ReLU: {h2}\")\n",
" \n",
" y = dense2(h2)\n",
" print(f\"\u2705 Final output: {y}\")\n",
" \n",
" print(\"\\n\ud83c\udf89 Layer composition works!\")\n",
" print(\"This is how neural networks work: layers + activations!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Make sure all your layers and activations are working!\")"
]
},
{
"cell_type": "markdown",
"id": "69f75a1f",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Step 5: Performance Comparison\n",
"\n",
"Let's compare our naive matrix multiplication with NumPy's optimized version to understand why optimization matters in ML.\n",
"\n",
"### Why Performance Matters\n",
"- **Training time**: Neural networks train for hours/days\n",
"- **Inference speed**: Real-time applications need fast predictions\n",
"- **GPU utilization**: Optimized operations use hardware efficiently\n",
"- **Scalability**: Large models need efficient implementations"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "25fc59d6",
"metadata": {},
"outputs": [],
"source": [
"# Performance comparison\n",
"print(\"Comparing naive vs NumPy matrix multiplication...\")\n",
"\n",
"try:\n",
" import time\n",
" \n",
" # Create test matrices\n",
" A = np.random.randn(100, 100).astype(np.float32)\n",
" B = np.random.randn(100, 100).astype(np.float32)\n",
" \n",
" # Time naive implementation\n",
" start_time = time.time()\n",
" result_naive = matmul_naive(A, B)\n",
" naive_time = time.time() - start_time\n",
" \n",
" # Time NumPy implementation\n",
" start_time = time.time()\n",
" result_numpy = A @ B\n",
" numpy_time = time.time() - start_time\n",
" \n",
" print(f\"\u2705 Naive time: {naive_time:.4f} seconds\")\n",
" print(f\"\u2705 NumPy time: {numpy_time:.4f} seconds\")\n",
" print(f\"\u2705 Speedup: {naive_time/numpy_time:.1f}x faster\")\n",
" \n",
" # Verify correctness\n",
" assert np.allclose(result_naive, result_numpy), \"Results don't match!\"\n",
" print(\"\u2705 Results are identical!\")\n",
" \n",
" print(\"\\n\ud83d\udca1 This is why we use optimized libraries in production!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")"
]
},
{
"cell_type": "markdown",
"id": "ca2216d4",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## \ud83c\udfaf Module Summary\n",
"\n",
"Congratulations! You've built the foundation of neural network layers:\n",
"\n",
"### What You've Accomplished\n",
"\u2705 **Matrix Multiplication**: Understanding the core operation \n",
"\u2705 **Dense Layer**: Linear transformation with weights and bias \n",
"\u2705 **Layer Composition**: Combining layers with activations \n",
"\u2705 **Performance Awareness**: Understanding optimization importance \n",
"\u2705 **Testing**: Immediate feedback on your implementations \n",
"\n",
"### Key Concepts You've Learned\n",
"- **Layers** are functions that transform tensors\n",
"- **Matrix multiplication** powers all neural network computations\n",
"- **Dense layers** perform linear transformations: `y = Wx + b`\n",
"- **Layer composition** creates complex functions from simple building blocks\n",
"- **Performance** matters for real-world ML applications\n",
"\n",
"### What's Next\n",
"In the next modules, you'll build on this foundation:\n",
"- **Networks**: Compose layers into complete models\n",
"- **Training**: Learn parameters with gradients and optimization\n",
"- **Convolutional layers**: Process spatial data like images\n",
"- **Recurrent layers**: Process sequential data like text\n",
"\n",
"### Real-World Connection\n",
"Your Dense layer is now ready to:\n",
"- Learn patterns in data through weight updates\n",
"- Transform features for classification and regression\n",
"- Serve as building blocks for complex architectures\n",
"- Integrate with the rest of the TinyTorch ecosystem\n",
"\n",
"**Ready for the next challenge?** Let's move on to building complete neural networks!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b8fef297",
"metadata": {},
"outputs": [],
"source": [
"# Final verification\n",
"print(\"\\n\" + \"=\"*50)\n",
"print(\"\ud83c\udf89 LAYERS MODULE COMPLETE!\")\n",
"print(\"=\"*50)\n",
"print(\"\u2705 Matrix multiplication understanding\")\n",
"print(\"\u2705 Dense layer implementation\")\n",
"print(\"\u2705 Layer composition with activations\")\n",
"print(\"\u2705 Performance awareness\")\n",
"print(\"\u2705 Comprehensive testing\")\n",
"print(\"\\n\ud83d\ude80 Ready to build networks in the next module!\") "
]
}
],
"metadata": {
"jupytext": {
"main_language": "python"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

1437
assignments/source/04_networks/04_networks.ipynb
View File

File diff suppressed because it is too large Load Diff

816
assignments/source/05_cnn/05_cnn.ipynb
View File

@@ -1,816 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ca53839c",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"# Module X: CNN - Convolutional Neural Networks\n",
"\n",
"Welcome to the CNN module! Here you'll implement the core building block of modern computer vision: the convolutional layer.\n",
"\n",
"## Learning Goals\n",
"- Understand the convolution operation (sliding window, local connectivity, weight sharing)\n",
"- Implement Conv2D with explicit for-loops\n",
"- Visualize how convolution builds feature maps\n",
"- Compose Conv2D with other layers to build a simple ConvNet\n",
"- (Stretch) Explore stride, padding, pooling, and multi-channel input\n",
"\n",
"## Build \u2192 Use \u2192 Understand\n",
"1. **Build**: Conv2D layer using sliding window convolution\n",
"2. **Use**: Transform images and see feature maps\n",
"3. **Understand**: How CNNs learn spatial patterns"
]
},
{
"cell_type": "markdown",
"id": "9e0d8f02",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## \ud83d\udce6 Where This Code Lives in the Final Package\n",
"\n",
"**Learning Side:** You work in `modules/cnn/cnn_dev.py` \n",
"**Building Side:** Code exports to `tinytorch.core.layers`\n",
"\n",
"```python\n",
"# Final package structure:\n",
"from tinytorch.core.layers import Dense, Conv2D # Both layers together!\n",
"from tinytorch.core.activations import ReLU\n",
"from tinytorch.core.tensor import Tensor\n",
"```\n",
"\n",
"**Why this matters:**\n",
"- **Learning:** Focused modules for deep understanding\n",
"- **Production:** Proper organization like PyTorch's `torch.nn`\n",
"- **Consistency:** All layers (Dense, Conv2D) live together in `core.layers`"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fbd717db",
"metadata": {},
"outputs": [],
"source": [
"#| default_exp core.cnn"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7f22e530",
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"import numpy as np\n",
"from typing import List, Tuple, Optional\n",
"from tinytorch.core.tensor import Tensor\n",
"\n",
"# Setup and imports (for development)\n",
"import matplotlib.pyplot as plt\n",
"from tinytorch.core.layers import Dense\n",
"from tinytorch.core.activations import ReLU"
]
},
{
"cell_type": "markdown",
"id": "f99723c8",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 1: What is Convolution?\n",
"\n",
"### Definition\n",
"A **convolutional layer** applies a small filter (kernel) across the input, producing a feature map. This operation captures local patterns and is the foundation of modern vision models.\n",
"\n",
"### Why Convolution Matters in Computer Vision\n",
"- **Local connectivity**: Each output value depends only on a small region of the input\n",
"- **Weight sharing**: The same filter is applied everywhere (translation invariance)\n",
"- **Spatial hierarchy**: Multiple layers build increasingly complex features\n",
"- **Parameter efficiency**: Much fewer parameters than fully connected layers\n",
"\n",
"### The Fundamental Insight\n",
"**Convolution is pattern matching!** The kernel learns to detect specific patterns:\n",
"- **Edge detectors**: Find boundaries between objects\n",
"- **Texture detectors**: Recognize surface patterns\n",
"- **Shape detectors**: Identify geometric forms\n",
"- **Feature detectors**: Combine simple patterns into complex features\n",
"\n",
"### Real-World Examples\n",
"- **Image processing**: Detect edges, blur, sharpen\n",
"- **Computer vision**: Recognize objects, faces, text\n",
"- **Medical imaging**: Detect tumors, analyze scans\n",
"- **Autonomous driving**: Identify traffic signs, pedestrians\n",
"\n",
"### Visual Intuition\n",
"```\n",
"Input Image: Kernel: Output Feature Map:\n",
"[1, 2, 3] [1, 0] [1*1+2*0+4*0+5*(-1), 2*1+3*0+5*0+6*(-1)]\n",
"[4, 5, 6] [0, -1] [4*1+5*0+7*0+8*(-1), 5*1+6*0+8*0+9*(-1)]\n",
"[7, 8, 9]\n",
"```\n",
"\n",
"The kernel slides across the input, computing dot products at each position.\n",
"\n",
"### The Math Behind It\n",
"For input I (H\u00d7W) and kernel K (kH\u00d7kW), the output O (out_H\u00d7out_W) is:\n",
"```\n",
"O[i,j] = sum(I[i+di, j+dj] * K[di, dj] for di in range(kH), dj in range(kW))\n",
"```\n",
"\n",
"Let's implement this step by step!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aa4af055",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:\n",
" \"\"\"\n",
" Naive 2D convolution (single channel, no stride, no padding).\n",
" \n",
" Args:\n",
" input: 2D input array (H, W)\n",
" kernel: 2D filter (kH, kW)\n",
" Returns:\n",
" 2D output array (H-kH+1, W-kW+1)\n",
" \n",
" TODO: Implement the sliding window convolution using for-loops.\n",
" \n",
" APPROACH:\n",
" 1. Get input dimensions: H, W = input.shape\n",
" 2. Get kernel dimensions: kH, kW = kernel.shape\n",
" 3. Calculate output dimensions: out_H = H - kH + 1, out_W = W - kW + 1\n",
" 4. Create output array: np.zeros((out_H, out_W))\n",
" 5. Use nested loops to slide the kernel:\n",
" - i loop: output rows (0 to out_H-1)\n",
" - j loop: output columns (0 to out_W-1)\n",
" - di loop: kernel rows (0 to kH-1)\n",
" - dj loop: kernel columns (0 to kW-1)\n",
" 6. For each (i,j), compute: output[i,j] += input[i+di, j+dj] * kernel[di, dj]\n",
" \n",
" EXAMPLE:\n",
" Input: [[1, 2, 3], Kernel: [[1, 0],\n",
" [4, 5, 6], [0, -1]]\n",
" [7, 8, 9]]\n",
" \n",
" Output[0,0] = 1*1 + 2*0 + 4*0 + 5*(-1) = 1 - 5 = -4\n",
" Output[0,1] = 2*1 + 3*0 + 5*0 + 6*(-1) = 2 - 6 = -4\n",
" Output[1,0] = 4*1 + 5*0 + 7*0 + 8*(-1) = 4 - 8 = -4\n",
" Output[1,1] = 5*1 + 6*0 + 8*0 + 9*(-1) = 5 - 9 = -4\n",
" \n",
" HINTS:\n",
" - Start with output = np.zeros((out_H, out_W))\n",
" - Use four nested loops: for i in range(out_H): for j in range(out_W): for di in range(kH): for dj in range(kW):\n",
" - Accumulate the sum: output[i,j] += input[i+di, j+dj] * kernel[di, dj]\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d83b2c10",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| hide\n",
"#| export\n",
"def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:\n",
" H, W = input.shape\n",
" kH, kW = kernel.shape\n",
" out_H, out_W = H - kH + 1, W - kW + 1\n",
" output = np.zeros((out_H, out_W), dtype=input.dtype)\n",
" for i in range(out_H):\n",
" for j in range(out_W):\n",
" for di in range(kH):\n",
" for dj in range(kW):\n",
" output[i, j] += input[i + di, j + dj] * kernel[di, dj]\n",
" return output"
]
},
{
"cell_type": "markdown",
"id": "454a6bad",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"### \ud83e\uddea Test Your Conv2D Implementation\n",
"\n",
"Try your function on this simple example:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7705032a",
"metadata": {},
"outputs": [],
"source": [
"# Test case for conv2d_naive\n",
"input = np.array([\n",
" [1, 2, 3],\n",
" [4, 5, 6],\n",
" [7, 8, 9]\n",
"], dtype=np.float32)\n",
"kernel = np.array([\n",
" [1, 0],\n",
" [0, -1]\n",
"], dtype=np.float32)\n",
"\n",
"expected = np.array([\n",
" [1*1+2*0+4*0+5*(-1), 2*1+3*0+5*0+6*(-1)],\n",
" [4*1+5*0+7*0+8*(-1), 5*1+6*0+8*0+9*(-1)]\n",
"], dtype=np.float32)\n",
"\n",
"try:\n",
" output = conv2d_naive(input, kernel)\n",
" print(\"\u2705 Input:\\n\", input)\n",
" print(\"\u2705 Kernel:\\n\", kernel)\n",
" print(\"\u2705 Your output:\\n\", output)\n",
" print(\"\u2705 Expected:\\n\", expected)\n",
" assert np.allclose(output, expected), \"\u274c Output does not match expected!\"\n",
" print(\"\ud83c\udf89 conv2d_naive works!\")\n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Make sure to implement conv2d_naive above!\")"
]
},
{
"cell_type": "markdown",
"id": "53449e22",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Step 2: Understanding What Convolution Does\n",
"\n",
"Let's visualize how different kernels detect different patterns:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "05a1ce2c",
"metadata": {},
"outputs": [],
"source": [
"# Visualize different convolution kernels\n",
"print(\"Visualizing different convolution kernels...\")\n",
"\n",
"try:\n",
" # Test different kernels\n",
" test_input = np.array([\n",
" [1, 1, 1, 0, 0],\n",
" [1, 1, 1, 0, 0],\n",
" [1, 1, 1, 0, 0],\n",
" [0, 0, 0, 0, 0],\n",
" [0, 0, 0, 0, 0]\n",
" ], dtype=np.float32)\n",
" \n",
" # Edge detection kernel (horizontal)\n",
" edge_kernel = np.array([\n",
" [1, 1, 1],\n",
" [0, 0, 0],\n",
" [-1, -1, -1]\n",
" ], dtype=np.float32)\n",
" \n",
" # Sharpening kernel\n",
" sharpen_kernel = np.array([\n",
" [0, -1, 0],\n",
" [-1, 5, -1],\n",
" [0, -1, 0]\n",
" ], dtype=np.float32)\n",
" \n",
" # Test edge detection\n",
" edge_output = conv2d_naive(test_input, edge_kernel)\n",
" print(\"\u2705 Edge detection kernel:\")\n",
" print(\" Detects horizontal edges (boundaries between light and dark)\")\n",
" print(\" Output:\\n\", edge_output)\n",
" \n",
" # Test sharpening\n",
" sharpen_output = conv2d_naive(test_input, sharpen_kernel)\n",
" print(\"\u2705 Sharpening kernel:\")\n",
" print(\" Enhances edges and details\")\n",
" print(\" Output:\\n\", sharpen_output)\n",
" \n",
" print(\"\\n\ud83d\udca1 Different kernels detect different patterns!\")\n",
" print(\" Neural networks learn these kernels automatically!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")"
]
},
{
"cell_type": "markdown",
"id": "0b33791b",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 3: Conv2D Layer Class\n",
"\n",
"Now let's wrap your convolution function in a layer class for use in networks. This makes it consistent with other layers like Dense.\n",
"\n",
"### Why Layer Classes Matter\n",
"- **Consistent API**: Same interface as Dense layers\n",
"- **Learnable parameters**: Kernels can be learned from data\n",
"- **Composability**: Can be combined with other layers\n",
"- **Integration**: Works seamlessly with the rest of TinyTorch\n",
"\n",
"### The Pattern\n",
"```\n",
"Input Tensor \u2192 Conv2D \u2192 Output Tensor\n",
"```\n",
"\n",
"Just like Dense layers, but with spatial operations instead of linear transformations."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "118ba687",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"class Conv2D:\n",
" \"\"\"\n",
" 2D Convolutional Layer (single channel, single filter, no stride/pad).\n",
" \n",
" Args:\n",
" kernel_size: (kH, kW) - size of the convolution kernel\n",
" \n",
" TODO: Initialize a random kernel and implement the forward pass using conv2d_naive.\n",
" \n",
" APPROACH:\n",
" 1. Store kernel_size as instance variable\n",
" 2. Initialize random kernel with small values\n",
" 3. Implement forward pass using conv2d_naive function\n",
" 4. Return Tensor wrapped around the result\n",
" \n",
" EXAMPLE:\n",
" layer = Conv2D(kernel_size=(2, 2))\n",
" x = Tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) # shape (3, 3)\n",
" y = layer(x) # shape (2, 2)\n",
" \n",
" HINTS:\n",
" - Store kernel_size as (kH, kW)\n",
" - Initialize kernel with np.random.randn(kH, kW) * 0.1 (small values)\n",
" - Use conv2d_naive(x.data, self.kernel) in forward pass\n",
" - Return Tensor(result) to wrap the result\n",
" \"\"\"\n",
" def __init__(self, kernel_size: Tuple[int, int]):\n",
" \"\"\"\n",
" Initialize Conv2D layer with random kernel.\n",
" \n",
" Args:\n",
" kernel_size: (kH, kW) - size of the convolution kernel\n",
" \n",
" TODO: \n",
" 1. Store kernel_size as instance variable\n",
" 2. Initialize random kernel with small values\n",
" 3. Scale kernel values to prevent large outputs\n",
" \n",
" STEP-BY-STEP:\n",
" 1. Store kernel_size as self.kernel_size\n",
" 2. Unpack kernel_size into kH, kW\n",
" 3. Initialize kernel: np.random.randn(kH, kW) * 0.1\n",
" 4. Convert to float32 for consistency\n",
" \n",
" EXAMPLE:\n",
" Conv2D((2, 2)) creates:\n",
" - kernel: shape (2, 2) with small random values\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")\n",
" \n",
" def forward(self, x: Tensor) -> Tensor:\n",
" \"\"\"\n",
" Forward pass: apply convolution to input.\n",
" \n",
" Args:\n",
" x: Input tensor of shape (H, W)\n",
" \n",
" Returns:\n",
" Output tensor of shape (H-kH+1, W-kW+1)\n",
" \n",
" TODO: Implement convolution using conv2d_naive function.\n",
" \n",
" STEP-BY-STEP:\n",
" 1. Use conv2d_naive(x.data, self.kernel)\n",
" 2. Return Tensor(result)\n",
" \n",
" EXAMPLE:\n",
" Input x: Tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) # shape (3, 3)\n",
" Kernel: shape (2, 2)\n",
" Output: Tensor([[val1, val2], [val3, val4]]) # shape (2, 2)\n",
" \n",
" HINTS:\n",
" - x.data gives you the numpy array\n",
" - self.kernel is your learned kernel\n",
" - Use conv2d_naive(x.data, self.kernel)\n",
" - Return Tensor(result) to wrap the result\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")\n",
" \n",
" def __call__(self, x: Tensor) -> Tensor:\n",
" \"\"\"Make layer callable: layer(x) same as layer.forward(x)\"\"\"\n",
" return self.forward(x)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3e18c382",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| hide\n",
"#| export\n",
"class Conv2D:\n",
" def __init__(self, kernel_size: Tuple[int, int]):\n",
" self.kernel_size = kernel_size\n",
" kH, kW = kernel_size\n",
" # Initialize with small random values\n",
" self.kernel = np.random.randn(kH, kW).astype(np.float32) * 0.1\n",
" \n",
" def forward(self, x: Tensor) -> Tensor:\n",
" return Tensor(conv2d_naive(x.data, self.kernel))\n",
" \n",
" def __call__(self, x: Tensor) -> Tensor:\n",
" return self.forward(x)"
]
},
{
"cell_type": "markdown",
"id": "e288fb18",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"### \ud83e\uddea Test Your Conv2D Layer"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2f1a4a6a",
"metadata": {},
"outputs": [],
"source": [
"# Test Conv2D layer\n",
"print(\"Testing Conv2D layer...\")\n",
"\n",
"try:\n",
" # Test basic Conv2D layer\n",
" conv = Conv2D(kernel_size=(2, 2))\n",
" x = Tensor(np.array([\n",
" [1, 2, 3],\n",
" [4, 5, 6],\n",
" [7, 8, 9]\n",
" ], dtype=np.float32))\n",
" \n",
" print(f\"\u2705 Input shape: {x.shape}\")\n",
" print(f\"\u2705 Kernel shape: {conv.kernel.shape}\")\n",
" print(f\"\u2705 Kernel values:\\n{conv.kernel}\")\n",
" \n",
" y = conv(x)\n",
" print(f\"\u2705 Output shape: {y.shape}\")\n",
" print(f\"\u2705 Output: {y}\")\n",
" \n",
" # Test with different kernel size\n",
" conv2 = Conv2D(kernel_size=(3, 3))\n",
" y2 = conv2(x)\n",
" print(f\"\u2705 3x3 kernel output shape: {y2.shape}\")\n",
" \n",
" print(\"\\n\ud83c\udf89 Conv2D layer works!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Make sure to implement the Conv2D layer above!\")"
]
},
{
"cell_type": "markdown",
"id": "97939763",
"metadata": {
"cell_marker": "\"\"\"",
"lines_to_next_cell": 1
},
"source": [
"## Step 4: Building a Simple ConvNet\n",
"\n",
"Now let's compose Conv2D layers with other layers to build a complete convolutional neural network!\n",
"\n",
"### Why ConvNets Matter\n",
"- **Spatial hierarchy**: Each layer learns increasingly complex features\n",
"- **Parameter sharing**: Same kernel applied everywhere (efficiency)\n",
"- **Translation invariance**: Can recognize objects regardless of position\n",
"- **Real-world success**: Power most modern computer vision systems\n",
"\n",
"### The Architecture\n",
"```\n",
"Input Image \u2192 Conv2D \u2192 ReLU \u2192 Flatten \u2192 Dense \u2192 Output\n",
"```\n",
"\n",
"This simple architecture can learn to recognize patterns in images!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "51631fe6",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| export\n",
"def flatten(x: Tensor) -> Tensor:\n",
" \"\"\"\n",
" Flatten a 2D tensor to 1D (for connecting to Dense).\n",
" \n",
" TODO: Implement flattening operation.\n",
" \n",
" APPROACH:\n",
" 1. Get the numpy array from the tensor\n",
" 2. Use .flatten() to convert to 1D\n",
" 3. Add batch dimension with [None, :]\n",
" 4. Return Tensor wrapped around the result\n",
" \n",
" EXAMPLE:\n",
" Input: Tensor([[1, 2], [3, 4]]) # shape (2, 2)\n",
" Output: Tensor([[1, 2, 3, 4]]) # shape (1, 4)\n",
" \n",
" HINTS:\n",
" - Use x.data.flatten() to get 1D array\n",
" - Add batch dimension: result[None, :]\n",
" - Return Tensor(result)\n",
" \"\"\"\n",
" raise NotImplementedError(\"Student implementation required\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7e8f2b50",
"metadata": {
"lines_to_next_cell": 1
},
"outputs": [],
"source": [
"#| hide\n",
"#| export\n",
"def flatten(x: Tensor) -> Tensor:\n",
" \"\"\"Flatten a 2D tensor to 1D (for connecting to Dense).\"\"\"\n",
" return Tensor(x.data.flatten()[None, :])"
]
},
{
"cell_type": "markdown",
"id": "7bdb9f80",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"### \ud83e\uddea Test Your Flatten Function"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c6d92ebc",
"metadata": {},
"outputs": [],
"source": [
"# Test flatten function\n",
"print(\"Testing flatten function...\")\n",
"\n",
"try:\n",
" # Test flattening\n",
" x = Tensor([[1, 2, 3], [4, 5, 6]]) # shape (2, 3)\n",
" flattened = flatten(x)\n",
" \n",
" print(f\"\u2705 Input shape: {x.shape}\")\n",
" print(f\"\u2705 Flattened shape: {flattened.shape}\")\n",
" print(f\"\u2705 Flattened values: {flattened}\")\n",
" \n",
" # Verify the flattening worked correctly\n",
" expected = np.array([[1, 2, 3, 4, 5, 6]])\n",
" assert np.allclose(flattened.data, expected), \"\u274c Flattening incorrect!\"\n",
" print(\"\u2705 Flattening works correctly!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Make sure to implement the flatten function above!\")"
]
},
{
"cell_type": "markdown",
"id": "9804128d",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Step 5: Composing a Complete ConvNet\n",
"\n",
"Now let's build a simple convolutional neural network that can process images!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d60d05b9",
"metadata": {},
"outputs": [],
"source": [
"# Compose a simple ConvNet\n",
"print(\"Building a simple ConvNet...\")\n",
"\n",
"try:\n",
" # Create network components\n",
" conv = Conv2D((2, 2))\n",
" relu = ReLU()\n",
" dense = Dense(input_size=4, output_size=1) # 4 features from 2x2 output\n",
" \n",
" # Test input (small 3x3 \"image\")\n",
" x = Tensor(np.random.randn(3, 3).astype(np.float32))\n",
" print(f\"\u2705 Input shape: {x.shape}\")\n",
" print(f\"\u2705 Input: {x}\")\n",
" \n",
" # Forward pass through the network\n",
" conv_out = conv(x)\n",
" print(f\"\u2705 After Conv2D: {conv_out}\")\n",
" \n",
" relu_out = relu(conv_out)\n",
" print(f\"\u2705 After ReLU: {relu_out}\")\n",
" \n",
" flattened = flatten(relu_out)\n",
" print(f\"\u2705 After flatten: {flattened}\")\n",
" \n",
" final_out = dense(flattened)\n",
" print(f\"\u2705 Final output: {final_out}\")\n",
" \n",
" print(\"\\n\ud83c\udf89 Simple ConvNet works!\")\n",
" print(\"This network can learn to recognize patterns in images!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")\n",
" print(\"Check your Conv2D, flatten, and Dense implementations!\")"
]
},
{
"cell_type": "markdown",
"id": "9fe4faf0",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## Step 6: Understanding the Power of Convolution\n",
"\n",
"Let's see how convolution captures different types of patterns:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "434133c2",
"metadata": {},
"outputs": [],
"source": [
"# Demonstrate pattern detection\n",
"print(\"Demonstrating pattern detection...\")\n",
"\n",
"try:\n",
" # Create a simple \"image\" with a pattern\n",
" image = np.array([\n",
" [0, 0, 0, 0, 0],\n",
" [0, 1, 1, 1, 0],\n",
" [0, 1, 1, 1, 0],\n",
" [0, 1, 1, 1, 0],\n",
" [0, 0, 0, 0, 0]\n",
" ], dtype=np.float32)\n",
" \n",
" # Different kernels detect different patterns\n",
" edge_kernel = np.array([\n",
" [1, 1, 1],\n",
" [1, -8, 1],\n",
" [1, 1, 1]\n",
" ], dtype=np.float32)\n",
" \n",
" blur_kernel = np.array([\n",
" [1/9, 1/9, 1/9],\n",
" [1/9, 1/9, 1/9],\n",
" [1/9, 1/9, 1/9]\n",
" ], dtype=np.float32)\n",
" \n",
" # Test edge detection\n",
" edge_result = conv2d_naive(image, edge_kernel)\n",
" print(\"\u2705 Edge detection:\")\n",
" print(\" Detects boundaries around the white square\")\n",
" print(\" Result:\\n\", edge_result)\n",
" \n",
" # Test blurring\n",
" blur_result = conv2d_naive(image, blur_kernel)\n",
" print(\"\u2705 Blurring:\")\n",
" print(\" Smooths the image\")\n",
" print(\" Result:\\n\", blur_result)\n",
" \n",
" print(\"\\n\ud83d\udca1 Different kernels = different feature detectors!\")\n",
" print(\" Neural networks learn these automatically from data!\")\n",
" \n",
"except Exception as e:\n",
" print(f\"\u274c Error: {e}\")"
]
},
{
"cell_type": "markdown",
"id": "80938b52",
"metadata": {
"cell_marker": "\"\"\""
},
"source": [
"## \ud83c\udfaf Module Summary\n",
"\n",
"Congratulations! You've built the foundation of convolutional neural networks:\n",
"\n",
"### What You've Accomplished\n",
"\u2705 **Convolution Operation**: Understanding the sliding window mechanism \n",
"\u2705 **Conv2D Layer**: Learnable convolutional layer implementation \n",
"\u2705 **Pattern Detection**: Visualizing how kernels detect different features \n",
"\u2705 **ConvNet Architecture**: Composing Conv2D with other layers \n",
"\u2705 **Real-world Applications**: Understanding computer vision applications \n",
"\n",
"### Key Concepts You've Learned\n",
"- **Convolution** is pattern matching with sliding windows\n",
"- **Local connectivity** means each output depends on a small input region\n",
"- **Weight sharing** makes CNNs parameter-efficient\n",
"- **Spatial hierarchy** builds complex features from simple patterns\n",
"- **Translation invariance** allows recognition regardless of position\n",
"\n",
"### What's Next\n",
"In the next modules, you'll build on this foundation:\n",
"- **Advanced CNN features**: Stride, padding, pooling\n",
"- **Multi-channel convolution**: RGB images, multiple filters\n",
"- **Training**: Learning kernels from data\n",
"- **Real applications**: Image classification, object detection\n",
"\n",
"### Real-World Connection\n",
"Your Conv2D layer is now ready to:\n",
"- Learn edge detectors, texture recognizers, and shape detectors\n",
"- Process real images for computer vision tasks\n",
"- Integrate with the rest of the TinyTorch ecosystem\n",
"- Scale to complex architectures like ResNet, VGG, etc.\n",
"\n",
"**Ready for the next challenge?** Let's move on to training these networks!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "03f153f1",
"metadata": {},
"outputs": [],
"source": [
"# Final verification\n",
"print(\"\\n\" + \"=\"*50)\n",
"print(\"\ud83c\udf89 CNN MODULE COMPLETE!\")\n",
"print(\"=\"*50)\n",
"print(\"\u2705 Convolution operation understanding\")\n",
"print(\"\u2705 Conv2D layer implementation\")\n",
"print(\"\u2705 Pattern detection visualization\")\n",
"print(\"\u2705 ConvNet architecture composition\")\n",
"print(\"\u2705 Real-world computer vision context\")\n",
"print(\"\\n\ud83d\ude80 Ready to train networks in the next module!\") "
]
}
],
"metadata": {
"jupytext": {
"main_language": "python"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

0
IMPLEMENTATION_SUMMARY.md → development/archived/IMPLEMENTATION_SUMMARY.md
View File

0
MODULE_MIGRATION_STRATEGY.md → development/archived/MODULE_MIGRATION_STRATEGY.md
View File

0
NBGRADER_INTEGRATION_COMPLETE.md → development/archived/NBGRADER_INTEGRATION_COMPLETE.md
View File

0
NBGRADER_INTEGRATION_PLAN.md → development/archived/NBGRADER_INTEGRATION_PLAN.md
View File

0
TINYTORCH_NBGRADER_PROPOSAL.md → development/archived/TINYTORCH_NBGRADER_PROPOSAL.md
View File

0
quickstart.md → development/archived/quickstart.md
View File

288
docs/students/project-guide.md
View File

@@ -1,288 +0,0 @@
# 🔥 TinyTorch Project Guide
**Building Machine Learning Systems from Scratch**
This guide helps you navigate through the complete TinyTorch course. Each module builds progressively toward a complete ML system using a notebook-first development approach with nbdev.
## 🎯 Module Progress Tracker
Track your progress through the course:
- [ ] **Module 0: Setup** - Environment & CLI setup
- [ ] **Module 1: Tensor** - Core tensor operations
- [ ] **Module 2: Layers** - Neural network layers
- [ ] **Module 3: Networks** - Complete model architectures
- [ ] **Module 4: Autograd** - Automatic differentiation
- [ ] **Module 5: DataLoader** - Data loading pipeline
- [ ] **Module 6: Training** - Training loop & optimization
- [ ] **Module 7: Config** - Configuration system
- [ ] **Module 8: Profiling** - Performance profiling
- [ ] **Module 9: Compression** - Model compression
- [ ] **Module 10: Kernels** - Custom compute kernels
- [ ] **Module 11: Benchmarking** - Performance benchmarking
- [ ] **Module 12: MLOps** - Production monitoring
## 🚀 Getting Started
### First Time Setup
1. **Clone the repository**
2. **Go to**: [`modules/setup/README.md`](../../modules/setup/README.md)
3. **Follow all setup instructions**
4. **Verify with**: `tito system doctor`
### Daily Workflow
```bash
cd TinyTorch
source .venv/bin/activate # Always activate first!
tito system info # Check system status
```
## 📋 Module Development Workflow
Each module follows this pattern:
1. **Read overview**: `modules/[name]/README.md`
2. **Work in Python file**: `modules/[name]/[name]_dev.py`
3. **Export code**: `tito package sync`
4. **Run tests**: `tito module test --module [name]`
5. **Move to next module when tests pass**
## 📚 Module Details
### 🔧 Module 0: Setup
**Goal**: Get your development environment ready
**Time**: 30 minutes
**Location**: [`modules/setup/`](../../modules/setup/)
**Key Tasks**:
- [ ] Create virtual environment
- [ ] Install dependencies
- [ ] Implement `hello_tinytorch()` function
- [ ] Pass all setup tests
- [ ] Learn the `tito` CLI
**Verification**:
```bash
tito system doctor # Should show all ✅
tito module test --module setup
```
---
### 🔢 Module 1: Tensor
**Goal**: Build the core tensor system
**Prerequisites**: Module 0 complete
**Location**: [`modules/tensor/`](../../modules/tensor/)
**Key Tasks**:
- [ ] Implement `Tensor` class
- [ ] Basic operations (add, mul, reshape)
- [ ] Memory management
- [ ] Shape validation
- [ ] Broadcasting support
**Verification**:
```bash
tito module test --module tensor
```
---
### 🧠 Module 2: Layers
**Goal**: Build neural network layers
**Prerequisites**: Module 1 complete
**Location**: [`modules/layers/`](../../modules/layers/)
**Key Tasks**:
- [ ] Implement `Linear` layer
- [ ] Activation functions (ReLU, Sigmoid)
- [ ] Forward pass implementation
- [ ] Parameter management
- [ ] Layer composition
**Verification**:
```bash
tito module test --module layers
```
---
### 🖼️ Module 3: Networks
**Goal**: Build complete neural networks
**Prerequisites**: Module 2 complete
**Location**: [`modules/networks/`](../../modules/networks/)
**Key Tasks**:
- [ ] Implement `Sequential` container
- [ ] CNN architectures
- [ ] Model saving/loading
- [ ] Train on CIFAR-10
**Target**: >80% accuracy on CIFAR-10
---
### ⚡ Module 4: Autograd
**Goal**: Automatic differentiation engine
**Prerequisites**: Module 3 complete
**Location**: [`modules/autograd/`](../../modules/autograd/)
**Key Tasks**:
- [ ] Computational graph construction
- [ ] Backward pass automation
- [ ] Gradient checking
- [ ] Memory efficient gradients
**Verification**: All gradient checks pass
---
### 📊 Module 5: DataLoader
**Goal**: Efficient data loading
**Prerequisites**: Module 4 complete
**Location**: [`modules/dataloader/`](../../modules/dataloader/)
**Key Tasks**:
- [ ] Custom `DataLoader` implementation
- [ ] Batch processing
- [ ] Data transformations
- [ ] Multi-threaded loading
---
### 🎯 Module 6: Training
**Goal**: Complete training system
**Prerequisites**: Module 5 complete
**Location**: [`modules/training/`](../../modules/training/)
**Key Tasks**:
- [ ] Training loop implementation
- [ ] SGD optimizer
- [ ] Adam optimizer
- [ ] Learning rate scheduling
- [ ] Metric tracking
---
### ⚙️ Module 7: Config
**Goal**: Configuration management
**Prerequisites**: Module 6 complete
**Location**: [`modules/config/`](../../modules/config/)
**Key Tasks**:
- [ ] YAML configuration system
- [ ] Experiment logging
- [ ] Reproducible training
- [ ] Hyperparameter management
---
### 📊 Module 8: Profiling
**Goal**: Performance measurement
**Prerequisites**: Module 7 complete
**Location**: [`modules/profiling/`](../../modules/profiling/)
**Key Tasks**:
- [ ] Memory profiler
- [ ] Compute profiler
- [ ] Bottleneck identification
- [ ] Performance visualizations
---
### 🗜️ Module 9: Compression
**Goal**: Model compression techniques
**Prerequisites**: Module 8 complete
**Location**: [`modules/compression/`](../../modules/compression/)
**Key Tasks**:
- [ ] Pruning implementation
- [ ] Quantization
- [ ] Knowledge distillation
- [ ] Compression benchmarks
---
### ⚡ Module 10: Kernels
**Goal**: Custom compute kernels
**Prerequisites**: Module 9 complete
**Location**: [`modules/kernels/`](../../modules/kernels/)
**Key Tasks**:
- [ ] CUDA kernel implementation
- [ ] Performance optimization
- [ ] Memory coalescing
- [ ] Kernel benchmarking
---
### 📈 Module 11: Benchmarking
**Goal**: Performance benchmarking
**Prerequisites**: Module 10 complete
**Location**: [`modules/benchmarking/`](../../modules/benchmarking/)
**Key Tasks**:
- [ ] Benchmarking framework
- [ ] Performance comparisons
- [ ] Scaling analysis
- [ ] Optimization recommendations
---
### 🚀 Module 12: MLOps
**Goal**: Production monitoring
**Prerequisites**: Module 11 complete
**Location**: [`modules/mlops/`](../../modules/mlops/)
**Key Tasks**:
- [ ] Model monitoring
- [ ] Performance tracking
- [ ] Alert systems
- [ ] Production deployment
## 🛠️ Essential Commands
### **System Commands**
```bash
tito system info # System information and course navigation
tito system doctor # Environment diagnosis
tito system jupyter # Start Jupyter Lab
```
### **Module Development**
```bash
tito module status # Check all module status
tito module test --module X # Test specific module
tito module test --all # Test all modules
tito module notebooks --module X # Convert Python to notebook
```
### **Package Management**
```bash
tito package sync # Export all notebooks to package
tito package sync --module X # Export specific module
tito package reset # Reset package to clean state
```
## 🎯 **Success Criteria**
Each module is complete when:
- [ ] **All tests pass**: `tito module test --module [name]`
- [ ] **Code exports**: `tito package sync --module [name]`
- [ ] **Understanding verified**: Can explain key concepts and trade-offs
- [ ] **Ready for next**: Prerequisites met for following modules
## 🆘 **Getting Help**
### **Troubleshooting**
- **Environment Issues**: `tito system doctor`
- **Module Status**: `tito module status --details`
- **Integration Issues**: Check `tito system info`
### **Resources**
- **Course Overview**: [Main README](../../README.md)
- **Development Guide**: [Module Development](../development/module-development-guide.md)
- **Quick Reference**: [Commands and Patterns](../development/quick-module-reference.md)
---
**💡 Pro Tip**: Use `tito module status` regularly to track your progress and see which modules are ready to work on next!

BIN
gradebook.db
View File

Binary file not shown.

BIN
gradebook.db.2025-07-12-090245.534037
View File

Binary file not shown.

65
modules/00_setup/setup_dev_enhanced.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "e3fcd475", "id": "cbc9ef5f",
"metadata": { "metadata": {
"cell_marker": "\"\"\"" "cell_marker": "\"\"\""
}, },
@@ -36,7 +36,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "fba821b3", "id": "43560ba3",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -46,7 +46,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "16465d62", "id": "516d08d6",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -66,7 +66,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "64d86ea8", "id": "97f21ddb",
"metadata": { "metadata": {
"cell_marker": "\"\"\"", "cell_marker": "\"\"\"",
"lines_to_next_cell": 1 "lines_to_next_cell": 1
@@ -80,7 +80,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "ab7eb118", "id": "caeb1865",
"metadata": { "metadata": {
"lines_to_next_cell": 1 "lines_to_next_cell": 1
}, },
@@ -156,7 +156,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "4b7256a9", "id": "053a090e",
"metadata": { "metadata": {
"cell_marker": "\"\"\"", "cell_marker": "\"\"\"",
"lines_to_next_cell": 1 "lines_to_next_cell": 1
@@ -170,7 +170,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "2fc78732", "id": "347431b1",
"metadata": { "metadata": {
"lines_to_next_cell": 1 "lines_to_next_cell": 1
}, },
@@ -214,7 +214,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "d457e1bf", "id": "300543ef",
"metadata": { "metadata": {
"cell_marker": "\"\"\"", "cell_marker": "\"\"\"",
"lines_to_next_cell": 1 "lines_to_next_cell": 1
@@ -228,7 +228,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "c78b6a2e", "id": "f3d01818",
"metadata": { "metadata": {
"lines_to_next_cell": 1 "lines_to_next_cell": 1
}, },
@@ -301,7 +301,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "9aceffc4", "id": "70543e35",
"metadata": { "metadata": {
"cell_marker": "\"\"\"", "cell_marker": "\"\"\"",
"lines_to_next_cell": 1 "lines_to_next_cell": 1
@@ -315,7 +315,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "e7738e0f", "id": "a837a39f",
"metadata": { "metadata": {
"lines_to_next_cell": 1 "lines_to_next_cell": 1
}, },
@@ -367,7 +367,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "da0fd46d", "id": "4884a585",
"metadata": { "metadata": {
"cell_marker": "\"\"\"", "cell_marker": "\"\"\"",
"lines_to_next_cell": 1 "lines_to_next_cell": 1
@@ -381,7 +381,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "c7cd22cd", "id": "446836a3",
"metadata": { "metadata": {
"lines_to_next_cell": 1 "lines_to_next_cell": 1
}, },
@@ -538,12 +538,37 @@
" return self.ascii_art\n", " return self.ascii_art\n",
" ### END SOLUTION\n", " ### END SOLUTION\n",
" \n", " \n",
" #| exercise_end\n",
"\n",
" def get_full_profile(self):\n",
" \"\"\"\n",
" Get complete profile with ASCII art.\n",
" \n",
" Return full profile display including ASCII art and all details.\n",
" \"\"\"\n",
" #| exercise_start\n",
" #| hint: Format with ASCII art, then developer details with emojis\n",
" #| solution_test: Should return complete profile with ASCII art and details\n",
" #| difficulty: medium\n",
" #| points: 10\n",
" \n",
" ### BEGIN SOLUTION\n",
" return f\"\"\"{self.ascii_art}\n",
" \n",
"👨‍💻 Developer: {self.name}\n",
"🏛️ Affiliation: {self.affiliation}\n",
"📧 Email: {self.email}\n",
"🐙 GitHub: @{self.github_username}\n",
"🔥 Ready to build ML systems from scratch!\n",
"\"\"\"\n",
" ### END SOLUTION\n",
" \n",
" #| exercise_end" " #| exercise_end"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "c58a5de4", "id": "be5ec710",
"metadata": { "metadata": {
"cell_marker": "\"\"\"", "cell_marker": "\"\"\"",
"lines_to_next_cell": 1 "lines_to_next_cell": 1
@@ -557,7 +582,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "a74d8133", "id": "29f9103e",
"metadata": { "metadata": {
"lines_to_next_cell": 1 "lines_to_next_cell": 1
}, },
@@ -637,7 +662,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "2959453c", "id": "f5335cd2",
"metadata": { "metadata": {
"cell_marker": "\"\"\"" "cell_marker": "\"\"\""
}, },
@@ -650,7 +675,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "75574cd6", "id": "d979356d",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -667,7 +692,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "e5d4a310", "id": "f07fe977",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -685,7 +710,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "9cd31f75", "id": "92619faf",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -702,7 +727,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "95483816", "id": "eb20d3cd",
"metadata": { "metadata": {
"cell_marker": "\"\"\"" "cell_marker": "\"\"\""
}, },

25
modules/00_setup/setup_dev_enhanced.py
View File

@@ -455,6 +455,31 @@ class DeveloperProfile:
#| exercise_end #| exercise_end
def get_full_profile(self):
"""
Get complete profile with ASCII art.
Return full profile display including ASCII art and all details.
"""
#| exercise_start
#| hint: Format with ASCII art, then developer details with emojis
#| solution_test: Should return complete profile with ASCII art and details
#| difficulty: medium
#| points: 10
### BEGIN SOLUTION
return f"""{self.ascii_art}
👨‍💻 Developer: {self.name}
🏛️ Affiliation: {self.affiliation}
📧 Email: {self.email}
🐙 GitHub: @{self.github_username}
🔥 Ready to build ML systems from scratch!
"""
### END SOLUTION
#| exercise_end
# %% [markdown] # %% [markdown]
""" """
## Hidden Tests: DeveloperProfile Class (35 Points) ## Hidden Tests: DeveloperProfile Class (35 Points)

5
modules/00_setup/tests/test_setup.py
View File

@@ -7,6 +7,7 @@ import pytest
import numpy as np import numpy as np
import sys import sys
import os import os
from pathlib import Path
# Import from the main package (rock solid foundation) # Import from the main package (rock solid foundation)
from tinytorch.core.utils import hello_tinytorch, add_numbers, SystemInfo, DeveloperProfile from tinytorch.core.utils import hello_tinytorch, add_numbers, SystemInfo, DeveloperProfile
@@ -25,8 +26,8 @@ class TestSetupFunctions:
hello_tinytorch() hello_tinytorch()
captured = capsys.readouterr() captured = capsys.readouterr()
# Should print the branding text # Should print the branding text (flexible matching for unicode)
assert "Tiny🔥Torch" in captured.out assert "TinyTorch" in captured.out or "Tiny🔥Torch" in captured.out
assert "Build ML Systems from Scratch!" in captured.out assert "Build ML Systems from Scratch!" in captured.out
def test_add_numbers_basic(self): def test_add_numbers_basic(self):

3
modules/04_networks/tests/test_networks.py
View File

@@ -20,7 +20,8 @@ from tinytorch.core.activations import ReLU, Sigmoid, Tanh
# Import the networks module # Import the networks module
try: try:
from modules.04_networks.networks_dev import ( # Import from the exported package
from tinytorch.core.networks import (
Sequential, Sequential,
create_mlp, create_mlp,
create_classification_network, create_classification_network,

14
modules/05_cnn/tests/test_cnn.py
View File

@@ -1,6 +1,18 @@
import numpy as np import numpy as np
import pytest import pytest
from modules.cnn.cnn_dev import conv2d_naive, Conv2D import sys
from pathlib import Path
# Add the CNN module to the path
sys.path.append(str(Path(__file__).parent.parent))
try:
# Import from the exported package
from tinytorch.core.cnn import conv2d_naive, Conv2D
except ImportError:
# Fallback for when module isn't exported yet
from cnn_dev import conv2d_naive, Conv2D
from tinytorch.core.tensor import Tensor from tinytorch.core.tensor import Tensor
def test_conv2d_naive_small(): def test_conv2d_naive_small():

1
modules/06_dataloader/tests/test_dataloader.py
View File

@@ -9,6 +9,7 @@ import sys
import os import os
import tempfile import tempfile
import shutil import shutil
import pickle
from pathlib import Path from pathlib import Path
from unittest.mock import patch, MagicMock from unittest.mock import patch, MagicMock

105
tinytorch/_modidx.py
View File

@@ -5,36 +5,42 @@ d = { 'settings': { 'branch': 'main',
'doc_host': 'https://tinytorch.github.io', 'doc_host': 'https://tinytorch.github.io',
'git_url': 'https://github.com/tinytorch/TinyTorch/', 'git_url': 'https://github.com/tinytorch/TinyTorch/',
'lib_path': 'tinytorch'}, 'lib_path': 'tinytorch'},
'syms': { 'tinytorch.core.activations': { 'tinytorch.core.activations.ReLU': ( 'activations/activations_dev.html#relu', 'syms': { 'tinytorch.core.activations': { 'tinytorch.core.activations.ReLU': ( '02_activations/activations_dev.html#relu',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.ReLU.__call__': ( 'activations/activations_dev.html#relu.__call__', 'tinytorch.core.activations.ReLU.__call__': ( '02_activations/activations_dev.html#relu.__call__',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.ReLU.forward': ( 'activations/activations_dev.html#relu.forward', 'tinytorch.core.activations.ReLU.forward': ( '02_activations/activations_dev.html#relu.forward',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Sigmoid': ( 'activations/activations_dev.html#sigmoid', 'tinytorch.core.activations.Sigmoid': ( '02_activations/activations_dev.html#sigmoid',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Sigmoid.__call__': ( 'activations/activations_dev.html#sigmoid.__call__', 'tinytorch.core.activations.Sigmoid.__call__': ( '02_activations/activations_dev.html#sigmoid.__call__',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Sigmoid.forward': ( 'activations/activations_dev.html#sigmoid.forward', 'tinytorch.core.activations.Sigmoid.forward': ( '02_activations/activations_dev.html#sigmoid.forward',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Softmax': ( 'activations/activations_dev.html#softmax', 'tinytorch.core.activations.Softmax': ( '02_activations/activations_dev.html#softmax',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Softmax.__call__': ( 'activations/activations_dev.html#softmax.__call__', 'tinytorch.core.activations.Softmax.__call__': ( '02_activations/activations_dev.html#softmax.__call__',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Softmax.forward': ( 'activations/activations_dev.html#softmax.forward', 'tinytorch.core.activations.Softmax.forward': ( '02_activations/activations_dev.html#softmax.forward',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Tanh': ( 'activations/activations_dev.html#tanh', 'tinytorch.core.activations.Tanh': ( '02_activations/activations_dev.html#tanh',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Tanh.__call__': ( 'activations/activations_dev.html#tanh.__call__', 'tinytorch.core.activations.Tanh.__call__': ( '02_activations/activations_dev.html#tanh.__call__',
'tinytorch/core/activations.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.activations.Tanh.forward': ( 'activations/activations_dev.html#tanh.forward', 'tinytorch.core.activations.Tanh.forward': ( '02_activations/activations_dev.html#tanh.forward',
'tinytorch/core/activations.py')}, 'tinytorch/core/activations.py'),
'tinytorch.core.cnn': { 'tinytorch.core.cnn.Conv2D': ('cnn/cnn_dev.html#conv2d', 'tinytorch/core/cnn.py'), 'tinytorch.core.activations._should_show_plots': ( '02_activations/activations_dev.html#_should_show_plots',
'tinytorch.core.cnn.Conv2D.__call__': ('cnn/cnn_dev.html#conv2d.__call__', 'tinytorch/core/cnn.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.cnn.Conv2D.__init__': ('cnn/cnn_dev.html#conv2d.__init__', 'tinytorch/core/cnn.py'), 'tinytorch.core.activations.visualize_activation_function': ( '02_activations/activations_dev.html#visualize_activation_function',
'tinytorch.core.cnn.Conv2D.forward': ('cnn/cnn_dev.html#conv2d.forward', 'tinytorch/core/cnn.py'), 'tinytorch/core/activations.py'),
'tinytorch.core.cnn.conv2d_naive': ('cnn/cnn_dev.html#conv2d_naive', 'tinytorch/core/cnn.py'), 'tinytorch.core.activations.visualize_activation_on_data': ( '02_activations/activations_dev.html#visualize_activation_on_data',
'tinytorch.core.cnn.flatten': ('cnn/cnn_dev.html#flatten', 'tinytorch/core/cnn.py')}, 'tinytorch/core/activations.py')},
'tinytorch.core.cnn': { 'tinytorch.core.cnn.Conv2D': ('05_cnn/cnn_dev.html#conv2d', 'tinytorch/core/cnn.py'),
'tinytorch.core.cnn.Conv2D.__call__': ('05_cnn/cnn_dev.html#conv2d.__call__', 'tinytorch/core/cnn.py'),
'tinytorch.core.cnn.Conv2D.__init__': ('05_cnn/cnn_dev.html#conv2d.__init__', 'tinytorch/core/cnn.py'),
'tinytorch.core.cnn.Conv2D.forward': ('05_cnn/cnn_dev.html#conv2d.forward', 'tinytorch/core/cnn.py'),
'tinytorch.core.cnn.conv2d_naive': ('05_cnn/cnn_dev.html#conv2d_naive', 'tinytorch/core/cnn.py'),
'tinytorch.core.cnn.flatten': ('05_cnn/cnn_dev.html#flatten', 'tinytorch/core/cnn.py')},
'tinytorch.core.dataloader': { 'tinytorch.core.dataloader.CIFAR10Dataset': ( 'dataloader/dataloader_dev.html#cifar10dataset', 'tinytorch.core.dataloader': { 'tinytorch.core.dataloader.CIFAR10Dataset': ( 'dataloader/dataloader_dev.html#cifar10dataset',
'tinytorch/core/dataloader.py'), 'tinytorch/core/dataloader.py'),
'tinytorch.core.dataloader.CIFAR10Dataset.__getitem__': ( 'dataloader/dataloader_dev.html#cifar10dataset.__getitem__', 'tinytorch.core.dataloader.CIFAR10Dataset.__getitem__': ( 'dataloader/dataloader_dev.html#cifar10dataset.__getitem__',
@@ -79,54 +85,59 @@ d = { 'settings': { 'branch': 'main',
'tinytorch/core/dataloader.py'), 'tinytorch/core/dataloader.py'),
'tinytorch.core.dataloader.create_data_pipeline': ( 'dataloader/dataloader_dev.html#create_data_pipeline', 'tinytorch.core.dataloader.create_data_pipeline': ( 'dataloader/dataloader_dev.html#create_data_pipeline',
'tinytorch/core/dataloader.py')}, 'tinytorch/core/dataloader.py')},
'tinytorch.core.layers': { 'tinytorch.core.layers.Dense': ('layers/layers_dev.html#dense', 'tinytorch/core/layers.py'), 'tinytorch.core.layers': { 'tinytorch.core.layers.Dense': ('03_layers/layers_dev.html#dense', 'tinytorch/core/layers.py'),
'tinytorch.core.layers.Dense.__call__': ( 'layers/layers_dev.html#dense.__call__', 'tinytorch.core.layers.Dense.__call__': ( '03_layers/layers_dev.html#dense.__call__',
'tinytorch/core/layers.py'), 'tinytorch/core/layers.py'),
'tinytorch.core.layers.Dense.__init__': ( 'layers/layers_dev.html#dense.__init__', 'tinytorch.core.layers.Dense.__init__': ( '03_layers/layers_dev.html#dense.__init__',
'tinytorch/core/layers.py'), 'tinytorch/core/layers.py'),
'tinytorch.core.layers.Dense.forward': ( 'layers/layers_dev.html#dense.forward', 'tinytorch.core.layers.Dense.forward': ( '03_layers/layers_dev.html#dense.forward',
'tinytorch/core/layers.py'), 'tinytorch/core/layers.py'),
'tinytorch.core.layers.matmul_naive': ( 'layers/layers_dev.html#matmul_naive', 'tinytorch.core.layers.matmul_naive': ( '03_layers/layers_dev.html#matmul_naive',
'tinytorch/core/layers.py')}, 'tinytorch/core/layers.py')},
'tinytorch.core.networks': { 'tinytorch.core.networks.Sequential': ( 'networks/networks_dev.html#sequential', 'tinytorch.core.networks': { 'tinytorch.core.networks.Sequential': ( '04_networks/networks_dev.html#sequential',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.Sequential.__call__': ( 'networks/networks_dev.html#sequential.__call__', 'tinytorch.core.networks.Sequential.__call__': ( '04_networks/networks_dev.html#sequential.__call__',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.Sequential.__init__': ( 'networks/networks_dev.html#sequential.__init__', 'tinytorch.core.networks.Sequential.__init__': ( '04_networks/networks_dev.html#sequential.__init__',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.Sequential.forward': ( 'networks/networks_dev.html#sequential.forward', 'tinytorch.core.networks.Sequential.forward': ( '04_networks/networks_dev.html#sequential.forward',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks._should_show_plots': ( 'networks/networks_dev.html#_should_show_plots', 'tinytorch.core.networks._should_show_plots': ( '04_networks/networks_dev.html#_should_show_plots',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.analyze_network_behavior': ( 'networks/networks_dev.html#analyze_network_behavior', 'tinytorch.core.networks.analyze_network_behavior': ( '04_networks/networks_dev.html#analyze_network_behavior',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.compare_networks': ( 'networks/networks_dev.html#compare_networks', 'tinytorch.core.networks.compare_networks': ( '04_networks/networks_dev.html#compare_networks',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.create_classification_network': ( 'networks/networks_dev.html#create_classification_network', 'tinytorch.core.networks.create_classification_network': ( '04_networks/networks_dev.html#create_classification_network',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.create_mlp': ( 'networks/networks_dev.html#create_mlp', 'tinytorch.core.networks.create_mlp': ( '04_networks/networks_dev.html#create_mlp',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.create_regression_network': ( 'networks/networks_dev.html#create_regression_network', 'tinytorch.core.networks.create_regression_network': ( '04_networks/networks_dev.html#create_regression_network',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.visualize_data_flow': ( 'networks/networks_dev.html#visualize_data_flow', 'tinytorch.core.networks.visualize_data_flow': ( '04_networks/networks_dev.html#visualize_data_flow',
'tinytorch/core/networks.py'), 'tinytorch/core/networks.py'),
'tinytorch.core.networks.visualize_network_architecture': ( 'networks/networks_dev.html#visualize_network_architecture', 'tinytorch.core.networks.visualize_network_architecture': ( '04_networks/networks_dev.html#visualize_network_architecture',
'tinytorch/core/networks.py')}, 'tinytorch/core/networks.py')},
'tinytorch.core.tensor': { 'tinytorch.core.tensor.Tensor': ('tensor/tensor_dev.html#tensor', 'tinytorch/core/tensor.py'), 'tinytorch.core.tensor': { 'tinytorch.core.tensor.Tensor': ( '01_tensor/tensor_dev_enhanced.html#tensor',
'tinytorch.core.tensor.Tensor.__init__': ( 'tensor/tensor_dev.html#tensor.__init__', 'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.__init__': ( '01_tensor/tensor_dev_enhanced.html#tensor.__init__',
'tinytorch/core/tensor.py'), 'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.__repr__': ( 'tensor/tensor_dev.html#tensor.__repr__', 'tinytorch.core.tensor.Tensor.__repr__': ( '01_tensor/tensor_dev_enhanced.html#tensor.__repr__',
'tinytorch/core/tensor.py'), 'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.data': ( 'tensor/tensor_dev.html#tensor.data', 'tinytorch.core.tensor.Tensor.add': ( '01_tensor/tensor_dev_enhanced.html#tensor.add',
'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.data': ( '01_tensor/tensor_dev_enhanced.html#tensor.data',
'tinytorch/core/tensor.py'), 'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.dtype': ( 'tensor/tensor_dev.html#tensor.dtype', 'tinytorch.core.tensor.Tensor.dtype': ( '01_tensor/tensor_dev_enhanced.html#tensor.dtype',
'tinytorch/core/tensor.py'), 'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.shape': ( 'tensor/tensor_dev.html#tensor.shape', 'tinytorch.core.tensor.Tensor.matmul': ( '01_tensor/tensor_dev_enhanced.html#tensor.matmul',
'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.multiply': ( '01_tensor/tensor_dev_enhanced.html#tensor.multiply',
'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.shape': ( '01_tensor/tensor_dev_enhanced.html#tensor.shape',
'tinytorch/core/tensor.py'), 'tinytorch/core/tensor.py'),
'tinytorch.core.tensor.Tensor.size': ( 'tensor/tensor_dev.html#tensor.size', 'tinytorch.core.tensor.Tensor.size': ( '01_tensor/tensor_dev_enhanced.html#tensor.size',
'tinytorch/core/tensor.py'), 'tinytorch/core/tensor.py')},
'tinytorch.core.tensor._add_arithmetic_methods': ( 'tensor/tensor_dev.html#_add_arithmetic_methods',
'tinytorch/core/tensor.py')},
'tinytorch.core.utils': { 'tinytorch.core.utils.DeveloperProfile': ( '00_setup/setup_dev_enhanced.html#developerprofile', 'tinytorch.core.utils': { 'tinytorch.core.utils.DeveloperProfile': ( '00_setup/setup_dev_enhanced.html#developerprofile',
'tinytorch/core/utils.py'), 'tinytorch/core/utils.py'),
'tinytorch.core.utils.DeveloperProfile.__init__': ( '00_setup/setup_dev_enhanced.html#developerprofile.__init__', 'tinytorch.core.utils.DeveloperProfile.__init__': ( '00_setup/setup_dev_enhanced.html#developerprofile.__init__',
@@ -137,6 +148,8 @@ d = { 'settings': { 'branch': 'main',
'tinytorch/core/utils.py'), 'tinytorch/core/utils.py'),
'tinytorch.core.utils.DeveloperProfile.get_ascii_art': ( '00_setup/setup_dev_enhanced.html#developerprofile.get_ascii_art', 'tinytorch.core.utils.DeveloperProfile.get_ascii_art': ( '00_setup/setup_dev_enhanced.html#developerprofile.get_ascii_art',
'tinytorch/core/utils.py'), 'tinytorch/core/utils.py'),
'tinytorch.core.utils.DeveloperProfile.get_full_profile': ( '00_setup/setup_dev_enhanced.html#developerprofile.get_full_profile',
'tinytorch/core/utils.py'),
'tinytorch.core.utils.DeveloperProfile.get_signature': ( '00_setup/setup_dev_enhanced.html#developerprofile.get_signature', 'tinytorch.core.utils.DeveloperProfile.get_signature': ( '00_setup/setup_dev_enhanced.html#developerprofile.get_signature',
'tinytorch/core/utils.py'), 'tinytorch/core/utils.py'),
'tinytorch.core.utils.SystemInfo': ( '00_setup/setup_dev_enhanced.html#systeminfo', 'tinytorch.core.utils.SystemInfo': ( '00_setup/setup_dev_enhanced.html#systeminfo',

272
tinytorch/core/activations.py
View File

@@ -1,9 +1,9 @@
# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/activations/activations_dev.ipynb. # AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/02_activations/activations_dev.ipynb.
# %% auto 0 # %% auto 0
__all__ = ['ReLU', 'Sigmoid', 'Tanh', 'Softmax'] __all__ = ['visualize_activation_function', 'visualize_activation_on_data', 'ReLU', 'Sigmoid', 'Tanh', 'Softmax']
# %% ../../modules/activations/activations_dev.ipynb 5 # %% ../../modules/02_activations/activations_dev.ipynb 2
import math import math
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
@@ -11,157 +11,265 @@ import os
import sys import sys
from typing import Union, List from typing import Union, List
# Import our Tensor class # Import our Tensor class from the main package (rock solid foundation)
from tinytorch.core.tensor import Tensor from .tensor import Tensor
# %% ../../modules/activations/activations_dev.ipynb 5 # %% ../../modules/02_activations/activations_dev.ipynb 3
def _should_show_plots():
"""Check if we should show plots (disable during testing)"""
# Check multiple conditions that indicate we're in test mode
is_pytest = (
'pytest' in sys.modules or
'test' in sys.argv or
os.environ.get('PYTEST_CURRENT_TEST') is not None or
any('test' in arg for arg in sys.argv) or
any('pytest' in arg for arg in sys.argv)
)
# Show plots in development mode (when not in test mode)
return not is_pytest
# %% ../../modules/02_activations/activations_dev.ipynb 4
def visualize_activation_function(activation_fn, name: str, x_range: tuple = (-5, 5), num_points: int = 100):
"""Visualize an activation function's behavior"""
if not _should_show_plots():
return
try:
# Generate input values
x_vals = np.linspace(x_range[0], x_range[1], num_points)
# Apply activation function
y_vals = []
for x in x_vals:
input_tensor = Tensor([[x]])
output = activation_fn(input_tensor)
y_vals.append(output.data.item())
# Create plot
plt.figure(figsize=(10, 6))
plt.plot(x_vals, y_vals, 'b-', linewidth=2, label=f'{name} Activation')
plt.grid(True, alpha=0.3)
plt.xlabel('Input (x)')
plt.ylabel(f'{name}(x)')
plt.title(f'{name} Activation Function')
plt.legend()
plt.show()
except ImportError:
print(" 📊 Matplotlib not available - skipping visualization")
except Exception as e:
print(f" ⚠️ Visualization error: {e}")
def visualize_activation_on_data(activation_fn, name: str, data: Tensor):
"""Show activation function applied to sample data"""
if not _should_show_plots():
return
try:
output = activation_fn(data)
print(f" 📊 {name} Example:")
print(f" Input: {data.data.flatten()}")
print(f" Output: {output.data.flatten()}")
print(f" Range: [{output.data.min():.3f}, {output.data.max():.3f}]")
except Exception as e:
print(f" ⚠️ Data visualization error: {e}")
# %% ../../modules/02_activations/activations_dev.ipynb 7
class ReLU: class ReLU:
""" """
ReLU Activation: f(x) = max(0, x) ReLU Activation Function: f(x) = max(0, x)
The most popular activation function in deep learning. The most popular activation function in deep learning.
Simple, effective, and computationally efficient. Simple, fast, and effective for most applications.
TODO: Implement ReLU activation function.
""" """
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
""" """
Apply ReLU: f(x) = max(0, x) Apply ReLU activation: f(x) = max(0, x)
Args: TODO: Implement ReLU activation
x: Input tensor
APPROACH:
Returns: 1. For each element in the input tensor, apply max(0, element)
Output tensor with ReLU applied element-wise 2. Return a new Tensor with the results
TODO: Implement element-wise max(0, x) operation EXAMPLE:
Hint: Use np.maximum(0, x.data) Input: Tensor([[-1, 0, 1, 2, -3]])
Expected: Tensor([[0, 0, 1, 2, 0]])
HINTS:
- Use np.maximum(0, x.data) for element-wise max
- Remember to return a new Tensor object
- The shape should remain the same as input
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
"""Make activation callable: relu(x) same as relu.forward(x)""" """Allow calling the activation like a function: relu(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/activations/activations_dev.ipynb 6 # %% ../../modules/02_activations/activations_dev.ipynb 8
class ReLU: class ReLU:
"""ReLU Activation: f(x) = max(0, x)""" """ReLU Activation: f(x) = max(0, x)"""
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
"""Apply ReLU: f(x) = max(0, x)""" result = np.maximum(0, x.data)
return Tensor(np.maximum(0, x.data)) return Tensor(result)
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
return self.forward(x) return self.forward(x)
# %% ../../modules/activations/activations_dev.ipynb 12 # %% ../../modules/02_activations/activations_dev.ipynb 13
class Sigmoid: class Sigmoid:
""" """
Sigmoid Activation: f(x) = 1 / (1 + e^(-x)) Sigmoid Activation Function: f(x) = 1 / (1 + e^(-x))
Squashes input to range (0, 1). Often used for binary classification. Squashes inputs to the range (0, 1), useful for binary classification
and probability interpretation.
TODO: Implement Sigmoid activation function.
""" """
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
""" """
Apply Sigmoid: f(x) = 1 / (1 + e^(-x)) Apply Sigmoid activation: f(x) = 1 / (1 + e^(-x))
Args: TODO: Implement Sigmoid activation
x: Input tensor
Returns:
Output tensor with Sigmoid applied element-wise
TODO: Implement sigmoid function (be careful with numerical stability!)
Hint: For numerical stability, use: APPROACH:
- For x >= 0: sigmoid(x) = 1 / (1 + exp(-x)) 1. For numerical stability, clip x to reasonable range (e.g., -500 to 500)
- For x < 0: sigmoid(x) = exp(x) / (1 + exp(x)) 2. Compute 1 / (1 + exp(-x)) for each element
3. Return a new Tensor with the results
EXAMPLE:
Input: Tensor([[-2, -1, 0, 1, 2]])
Expected: Tensor([[0.119, 0.269, 0.5, 0.731, 0.881]]) (approximately)
HINTS:
- Use np.clip(x.data, -500, 500) for numerical stability
- Use np.exp(-clipped_x) for the exponential
- Formula: 1 / (1 + np.exp(-clipped_x))
- Remember to return a new Tensor object
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
"""Allow calling the activation like a function: sigmoid(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/activations/activations_dev.ipynb 13 # %% ../../modules/02_activations/activations_dev.ipynb 14
class Sigmoid: class Sigmoid:
"""Sigmoid Activation: f(x) = 1 / (1 + e^(-x))""" """Sigmoid Activation: f(x) = 1 / (1 + e^(-x))"""
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
"""Apply Sigmoid with numerical stability""" # Clip for numerical stability
# Use the numerically stable version to avoid overflow clipped = np.clip(x.data, -500, 500)
# For x >= 0: sigmoid(x) = 1 / (1 + exp(-x)) result = 1 / (1 + np.exp(-clipped))
# For x < 0: sigmoid(x) = exp(x) / (1 + exp(x))
x_data = x.data
result = np.zeros_like(x_data)
# Stable computation
positive_mask = x_data >= 0
result[positive_mask] = 1.0 / (1.0 + np.exp(-x_data[positive_mask]))
result[~positive_mask] = np.exp(x_data[~positive_mask]) / (1.0 + np.exp(x_data[~positive_mask]))
return Tensor(result) return Tensor(result)
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
return self.forward(x) return self.forward(x)
# %% ../../modules/activations/activations_dev.ipynb 19 # %% ../../modules/02_activations/activations_dev.ipynb 18
class Tanh: class Tanh:
""" """
Tanh Activation: f(x) = tanh(x) Tanh Activation Function: f(x) = (e^x - e^(-x)) / (e^x + e^(-x))
Squashes input to range (-1, 1). Zero-centered output. Zero-centered activation function with range (-1, 1).
Often preferred over Sigmoid for hidden layers.
TODO: Implement Tanh activation function.
""" """
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
""" """
Apply Tanh: f(x) = tanh(x) Apply Tanh activation: f(x) = (e^x - e^(-x)) / (e^x + e^(-x))
Args: TODO: Implement Tanh activation
x: Input tensor
APPROACH:
Returns: 1. Use numpy's built-in tanh function: np.tanh(x.data)
Output tensor with Tanh applied element-wise 2. Return a new Tensor with the results
TODO: Implement tanh function ALTERNATIVE APPROACH:
Hint: Use np.tanh(x.data) 1. Compute e^x and e^(-x)
2. Use formula: (e^x - e^(-x)) / (e^x + e^(-x))
EXAMPLE:
Input: Tensor([[-2, -1, 0, 1, 2]])
Expected: Tensor([[-0.964, -0.762, 0.0, 0.762, 0.964]]) (approximately)
HINTS:
- np.tanh() is the simplest approach
- Output range is (-1, 1)
- tanh(0) = 0 (zero-centered)
- Remember to return a new Tensor object
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
"""Allow calling the activation like a function: tanh(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/activations/activations_dev.ipynb 20 # %% ../../modules/02_activations/activations_dev.ipynb 19
class Tanh: class Tanh:
"""Tanh Activation: f(x) = tanh(x)""" """Tanh Activation: f(x) = (e^x - e^(-x)) / (e^x + e^(-x))"""
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
"""Apply Tanh""" result = np.tanh(x.data)
return Tensor(np.tanh(x.data)) return Tensor(result)
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
return self.forward(x) return self.forward(x)
# %% ../../modules/02_activations/activations_dev.ipynb 23
class Softmax: class Softmax:
"""Softmax Activation: f(x) = exp(x) / sum(exp(x))""" """
Softmax Activation Function: f(x_i) = e^(x_i) / Σ(e^(x_j))
Converts a vector of real numbers into a probability distribution.
Essential for multi-class classification.
"""
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
"""Apply Softmax with numerical stability""" """
# Subtract max for numerical stability Apply Softmax activation: f(x_i) = e^(x_i) / Σ(e^(x_j))
x_stable = x.data - np.max(x.data, axis=-1, keepdims=True)
# Compute exponentials TODO: Implement Softmax activation
exp_vals = np.exp(x_stable)
# Normalize to get probabilities APPROACH:
result = exp_vals / np.sum(exp_vals, axis=-1, keepdims=True) 1. For numerical stability, subtract the maximum value from each row
2. Compute exponentials of the shifted values
3. Divide each exponential by the sum of exponentials in its row
4. Return a new Tensor with the results
return Tensor(result) EXAMPLE:
Input: Tensor([[1, 2, 3]])
Expected: Tensor([[0.090, 0.245, 0.665]]) (approximately)
Sum should be 1.0
HINTS:
- Use np.max(x.data, axis=1, keepdims=True) to find row maximums
- Subtract max from x.data for numerical stability
- Use np.exp() for exponentials
- Use np.sum(exp_vals, axis=1, keepdims=True) for row sums
- Remember to return a new Tensor object
"""
raise NotImplementedError("Student implementation required")
def __call__(self, x: Tensor) -> Tensor:
"""Allow calling the activation like a function: softmax(x)"""
return self.forward(x)
# %% ../../modules/02_activations/activations_dev.ipynb 24
class Softmax:
"""Softmax Activation: f(x_i) = e^(x_i) / Σ(e^(x_j))"""
def forward(self, x: Tensor) -> Tensor:
# Subtract max for numerical stability
shifted = x.data - np.max(x.data, axis=1, keepdims=True)
exp_vals = np.exp(shifted)
result = exp_vals / np.sum(exp_vals, axis=1, keepdims=True)
return Tensor(result)
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
return self.forward(x) return self.forward(x)

157
tinytorch/core/cnn.py
View File

@@ -1,22 +1,61 @@
# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/cnn/cnn_dev.ipynb. # AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/05_cnn/cnn_dev.ipynb.
# %% auto 0 # %% auto 0
__all__ = ['conv2d_naive', 'Conv2D', 'flatten'] __all__ = ['conv2d_naive', 'Conv2D', 'flatten']
# %% ../../modules/cnn/cnn_dev.ipynb 4 # %% ../../modules/05_cnn/cnn_dev.ipynb 3
import numpy as np
from typing import List, Tuple, Optional
from .tensor import Tensor
# Setup and imports (for development)
import matplotlib.pyplot as plt
from .layers import Dense
from .activations import ReLU
# %% ../../modules/05_cnn/cnn_dev.ipynb 5
def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray: def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:
""" """
Naive 2D convolution (single channel, no stride, no padding). Naive 2D convolution (single channel, no stride, no padding).
Args: Args:
input: 2D input array (H, W) input: 2D input array (H, W)
kernel: 2D filter (kH, kW) kernel: 2D filter (kH, kW)
Returns: Returns:
2D output array (H-kH+1, W-kW+1) 2D output array (H-kH+1, W-kW+1)
TODO: Implement the sliding window convolution using for-loops. TODO: Implement the sliding window convolution using for-loops.
APPROACH:
1. Get input dimensions: H, W = input.shape
2. Get kernel dimensions: kH, kW = kernel.shape
3. Calculate output dimensions: out_H = H - kH + 1, out_W = W - kW + 1
4. Create output array: np.zeros((out_H, out_W))
5. Use nested loops to slide the kernel:
- i loop: output rows (0 to out_H-1)
- j loop: output columns (0 to out_W-1)
- di loop: kernel rows (0 to kH-1)
- dj loop: kernel columns (0 to kW-1)
6. For each (i,j), compute: output[i,j] += input[i+di, j+dj] * kernel[di, dj]
EXAMPLE:
Input: [[1, 2, 3], Kernel: [[1, 0],
[4, 5, 6], [0, -1]]
[7, 8, 9]]
Output[0,0] = 1*1 + 2*0 + 4*0 + 5*(-1) = 1 - 5 = -4
Output[0,1] = 2*1 + 3*0 + 5*0 + 6*(-1) = 2 - 6 = -4
Output[1,0] = 4*1 + 5*0 + 7*0 + 8*(-1) = 4 - 8 = -4
Output[1,1] = 5*1 + 6*0 + 8*0 + 9*(-1) = 5 - 9 = -4
HINTS:
- Start with output = np.zeros((out_H, out_W))
- Use four nested loops: for i in range(out_H): for j in range(out_W): for di in range(kH): for dj in range(kW):
- Accumulate the sum: output[i,j] += input[i+di, j+dj] * kernel[di, dj]
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
# %% ../../modules/cnn/cnn_dev.ipynb 5 # %% ../../modules/05_cnn/cnn_dev.ipynb 6
def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray: def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:
H, W = input.shape H, W = input.shape
kH, kW = kernel.shape kH, kW = kernel.shape
@@ -24,34 +63,134 @@ def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:
output = np.zeros((out_H, out_W), dtype=input.dtype) output = np.zeros((out_H, out_W), dtype=input.dtype)
for i in range(out_H): for i in range(out_H):
for j in range(out_W): for j in range(out_W):
output[i, j] = np.sum(input[i:i+kH, j:j+kW] * kernel) for di in range(kH):
for dj in range(kW):
output[i, j] += input[i + di, j + dj] * kernel[di, dj]
return output return output
# %% ../../modules/cnn/cnn_dev.ipynb 9 # %% ../../modules/05_cnn/cnn_dev.ipynb 12
class Conv2D: class Conv2D:
""" """
2D Convolutional Layer (single channel, single filter, no stride/pad). 2D Convolutional Layer (single channel, single filter, no stride/pad).
Args: Args:
kernel_size: (kH, kW) kernel_size: (kH, kW) - size of the convolution kernel
TODO: Initialize a random kernel and implement the forward pass using conv2d_naive. TODO: Initialize a random kernel and implement the forward pass using conv2d_naive.
APPROACH:
1. Store kernel_size as instance variable
2. Initialize random kernel with small values
3. Implement forward pass using conv2d_naive function
4. Return Tensor wrapped around the result
EXAMPLE:
layer = Conv2D(kernel_size=(2, 2))
x = Tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) # shape (3, 3)
y = layer(x) # shape (2, 2)
HINTS:
- Store kernel_size as (kH, kW)
- Initialize kernel with np.random.randn(kH, kW) * 0.1 (small values)
- Use conv2d_naive(x.data, self.kernel) in forward pass
- Return Tensor(result) to wrap the result
""" """
def __init__(self, kernel_size: Tuple[int, int]): def __init__(self, kernel_size: Tuple[int, int]):
"""
Initialize Conv2D layer with random kernel.
Args:
kernel_size: (kH, kW) - size of the convolution kernel
TODO:
1. Store kernel_size as instance variable
2. Initialize random kernel with small values
3. Scale kernel values to prevent large outputs
STEP-BY-STEP:
1. Store kernel_size as self.kernel_size
2. Unpack kernel_size into kH, kW
3. Initialize kernel: np.random.randn(kH, kW) * 0.1
4. Convert to float32 for consistency
EXAMPLE:
Conv2D((2, 2)) creates:
- kernel: shape (2, 2) with small random values
"""
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
"""
Forward pass: apply convolution to input.
Args:
x: Input tensor of shape (H, W)
Returns:
Output tensor of shape (H-kH+1, W-kW+1)
TODO: Implement convolution using conv2d_naive function.
STEP-BY-STEP:
1. Use conv2d_naive(x.data, self.kernel)
2. Return Tensor(result)
EXAMPLE:
Input x: Tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) # shape (3, 3)
Kernel: shape (2, 2)
Output: Tensor([[val1, val2], [val3, val4]]) # shape (2, 2)
HINTS:
- x.data gives you the numpy array
- self.kernel is your learned kernel
- Use conv2d_naive(x.data, self.kernel)
- Return Tensor(result) to wrap the result
"""
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
"""Make layer callable: layer(x) same as layer.forward(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/cnn/cnn_dev.ipynb 10 # %% ../../modules/05_cnn/cnn_dev.ipynb 13
class Conv2D: class Conv2D:
def __init__(self, kernel_size: Tuple[int, int]): def __init__(self, kernel_size: Tuple[int, int]):
self.kernel = np.random.randn(*kernel_size).astype(np.float32) self.kernel_size = kernel_size
kH, kW = kernel_size
# Initialize with small random values
self.kernel = np.random.randn(kH, kW).astype(np.float32) * 0.1
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
return Tensor(conv2d_naive(x.data, self.kernel)) return Tensor(conv2d_naive(x.data, self.kernel))
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
return self.forward(x) return self.forward(x)
# %% ../../modules/cnn/cnn_dev.ipynb 12 # %% ../../modules/05_cnn/cnn_dev.ipynb 17
def flatten(x: Tensor) -> Tensor:
"""
Flatten a 2D tensor to 1D (for connecting to Dense).
TODO: Implement flattening operation.
APPROACH:
1. Get the numpy array from the tensor
2. Use .flatten() to convert to 1D
3. Add batch dimension with [None, :]
4. Return Tensor wrapped around the result
EXAMPLE:
Input: Tensor([[1, 2], [3, 4]]) # shape (2, 2)
Output: Tensor([[1, 2, 3, 4]]) # shape (1, 4)
HINTS:
- Use x.data.flatten() to get 1D array
- Add batch dimension: result[None, :]
- Return Tensor(result)
"""
raise NotImplementedError("Student implementation required")
# %% ../../modules/05_cnn/cnn_dev.ipynb 18
def flatten(x: Tensor) -> Tensor: def flatten(x: Tensor) -> Tensor:
"""Flatten a 2D tensor to 1D (for connecting to Dense).""" """Flatten a 2D tensor to 1D (for connecting to Dense)."""
return Tensor(x.data.flatten()[None, :]) return Tensor(x.data.flatten()[None, :])

146
tinytorch/core/layers.py
View File

@@ -1,28 +1,24 @@
# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/layers/layers_dev.ipynb. # AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/03_layers/layers_dev.ipynb.
# %% auto 0 # %% auto 0
__all__ = ['matmul_naive', 'Dense'] __all__ = ['matmul_naive', 'Dense']
# %% ../../modules/layers/layers_dev.ipynb 3 # %% ../../modules/03_layers/layers_dev.ipynb 3
import numpy as np import numpy as np
import math import math
import sys import sys
from typing import Union, Optional, Callable from typing import Union, Optional, Callable
# Import from the main package (rock solid foundation)
from .tensor import Tensor from .tensor import Tensor
# Import activation functions from the activations module
from .activations import ReLU, Sigmoid, Tanh from .activations import ReLU, Sigmoid, Tanh
# Import our Tensor class
# sys.path.append('../../')
# from modules.tensor.tensor_dev import Tensor
# print("🔥 TinyTorch Layers Module") # print("🔥 TinyTorch Layers Module")
# print(f"NumPy version: {np.__version__}") # print(f"NumPy version: {np.__version__}")
# print(f"Python version: {sys.version_info.major}.{sys.version_info.minor}") # print(f"Python version: {sys.version_info.major}.{sys.version_info.minor}")
# print("Ready to build neural network layers!") # print("Ready to build neural network layers!")
# %% ../../modules/layers/layers_dev.ipynb 5 # %% ../../modules/03_layers/layers_dev.ipynb 6
def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray: def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray:
""" """
Naive matrix multiplication using explicit for-loops. Naive matrix multiplication using explicit for-loops.
@@ -37,10 +33,34 @@ def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray:
Matrix of shape (m, p) where C[i,j] = sum(A[i,k] * B[k,j] for k in range(n)) Matrix of shape (m, p) where C[i,j] = sum(A[i,k] * B[k,j] for k in range(n))
TODO: Implement matrix multiplication using three nested for-loops. TODO: Implement matrix multiplication using three nested for-loops.
APPROACH:
1. Get the dimensions: m, n from A and n2, p from B
2. Check that n == n2 (matrices must be compatible)
3. Create output matrix C of shape (m, p) filled with zeros
4. Use three nested loops:
- i loop: rows of A (0 to m-1)
- j loop: columns of B (0 to p-1)
- k loop: shared dimension (0 to n-1)
5. For each (i,j), compute: C[i,j] += A[i,k] * B[k,j]
EXAMPLE:
A = [[1, 2], B = [[5, 6],
[3, 4]] [7, 8]]
C[0,0] = A[0,0]*B[0,0] + A[0,1]*B[1,0] = 1*5 + 2*7 = 19
C[0,1] = A[0,0]*B[0,1] + A[0,1]*B[1,1] = 1*6 + 2*8 = 22
C[1,0] = A[1,0]*B[0,0] + A[1,1]*B[1,0] = 3*5 + 4*7 = 43
C[1,1] = A[1,0]*B[0,1] + A[1,1]*B[1,1] = 3*6 + 4*8 = 50
HINTS:
- Start with C = np.zeros((m, p))
- Use three nested for loops: for i in range(m): for j in range(p): for k in range(n):
- Accumulate the sum: C[i,j] += A[i,k] * B[k,j]
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
# %% ../../modules/layers/layers_dev.ipynb 6 # %% ../../modules/03_layers/layers_dev.ipynb 7
def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray: def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray:
""" """
Naive matrix multiplication using explicit for-loops. Naive matrix multiplication using explicit for-loops.
@@ -58,7 +78,7 @@ def matmul_naive(A: np.ndarray, B: np.ndarray) -> np.ndarray:
C[i, j] += A[i, k] * B[k, j] C[i, j] += A[i, k] * B[k, j]
return C return C
# %% ../../modules/layers/layers_dev.ipynb 7 # %% ../../modules/03_layers/layers_dev.ipynb 11
class Dense: class Dense:
""" """
Dense (Linear) Layer: y = Wx + b Dense (Linear) Layer: y = Wx + b
@@ -73,6 +93,23 @@ class Dense:
use_naive_matmul: Whether to use naive matrix multiplication (for learning) use_naive_matmul: Whether to use naive matrix multiplication (for learning)
TODO: Implement the Dense layer with weight initialization and forward pass. TODO: Implement the Dense layer with weight initialization and forward pass.
APPROACH:
1. Store layer parameters (input_size, output_size, use_bias, use_naive_matmul)
2. Initialize weights with small random values (Xavier/Glorot initialization)
3. Initialize bias to zeros (if use_bias=True)
4. Implement forward pass using matrix multiplication and bias addition
EXAMPLE:
layer = Dense(input_size=3, output_size=2)
x = Tensor([[1, 2, 3]]) # batch_size=1, input_size=3
y = layer(x) # shape: (1, 2)
HINTS:
- Use np.random.randn() for random initialization
- Scale weights by sqrt(2/(input_size + output_size)) for Xavier init
- Store weights and bias as numpy arrays
- Use matmul_naive or @ operator based on use_naive_matmul flag
""" """
def __init__(self, input_size: int, output_size: int, use_bias: bool = True, def __init__(self, input_size: int, output_size: int, use_bias: bool = True,
@@ -90,6 +127,18 @@ class Dense:
1. Store layer parameters (input_size, output_size, use_bias, use_naive_matmul) 1. Store layer parameters (input_size, output_size, use_bias, use_naive_matmul)
2. Initialize weights with small random values 2. Initialize weights with small random values
3. Initialize bias to zeros (if use_bias=True) 3. Initialize bias to zeros (if use_bias=True)
STEP-BY-STEP:
1. Store the parameters as instance variables
2. Calculate scale factor for Xavier initialization: sqrt(2/(input_size + output_size))
3. Initialize weights: np.random.randn(input_size, output_size) * scale
4. If use_bias=True, initialize bias: np.zeros(output_size)
5. If use_bias=False, set bias to None
EXAMPLE:
Dense(3, 2) creates:
- weights: shape (3, 2) with small random values
- bias: shape (2,) with zeros
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
@@ -105,8 +154,27 @@ class Dense:
TODO: Implement matrix multiplication and bias addition TODO: Implement matrix multiplication and bias addition
- Use self.use_naive_matmul to choose between NumPy and naive implementation - Use self.use_naive_matmul to choose between NumPy and naive implementation
- If use_naive_matmul=True, use matmul_naive(x.data, self.weights.data) - If use_naive_matmul=True, use matmul_naive(x.data, self.weights)
- If use_naive_matmul=False, use x.data @ self.weights.data - If use_naive_matmul=False, use x.data @ self.weights
- Add bias if self.use_bias=True
STEP-BY-STEP:
1. Perform matrix multiplication: Wx
- If use_naive_matmul: result = matmul_naive(x.data, self.weights)
- Else: result = x.data @ self.weights
2. Add bias if use_bias: result += self.bias
3. Return Tensor(result)
EXAMPLE:
Input x: Tensor([[1, 2, 3]]) # shape (1, 3)
Weights: shape (3, 2)
Output: Tensor([[val1, val2]]) # shape (1, 2)
HINTS:
- x.data gives you the numpy array
- self.weights is your weight matrix
- Use broadcasting for bias addition: result + self.bias
- Return Tensor(result) to wrap the result
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
@@ -114,7 +182,7 @@ class Dense:
"""Make layer callable: layer(x) same as layer.forward(x)""" """Make layer callable: layer(x) same as layer.forward(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/layers/layers_dev.ipynb 8 # %% ../../modules/03_layers/layers_dev.ipynb 12
class Dense: class Dense:
""" """
Dense (Linear) Layer: y = Wx + b Dense (Linear) Layer: y = Wx + b
@@ -125,40 +193,52 @@ class Dense:
def __init__(self, input_size: int, output_size: int, use_bias: bool = True, def __init__(self, input_size: int, output_size: int, use_bias: bool = True,
use_naive_matmul: bool = False): use_naive_matmul: bool = False):
"""Initialize Dense layer with random weights.""" """
Initialize Dense layer with random weights.
Args:
input_size: Number of input features
output_size: Number of output features
use_bias: Whether to include bias term
use_naive_matmul: Use naive matrix multiplication (for learning)
"""
# Store parameters
self.input_size = input_size self.input_size = input_size
self.output_size = output_size self.output_size = output_size
self.use_bias = use_bias self.use_bias = use_bias
self.use_naive_matmul = use_naive_matmul self.use_naive_matmul = use_naive_matmul
# Initialize weights with Xavier/Glorot initialization # Xavier/Glorot initialization
# This helps with gradient flow during training scale = np.sqrt(2.0 / (input_size + output_size))
limit = math.sqrt(6.0 / (input_size + output_size)) self.weights = np.random.randn(input_size, output_size).astype(np.float32) * scale
self.weights = Tensor(
np.random.uniform(-limit, limit, (input_size, output_size)).astype(np.float32)
)
# Initialize bias to zeros # Initialize bias
if use_bias: if use_bias:
self.bias = Tensor(np.zeros(output_size, dtype=np.float32)) self.bias = np.zeros(output_size, dtype=np.float32)
else: else:
self.bias = None self.bias = None
def forward(self, x: Tensor) -> Tensor: def forward(self, x: Tensor) -> Tensor:
"""Forward pass: y = Wx + b""" """
# Choose matrix multiplication implementation Forward pass: y = Wx + b
Args:
x: Input tensor of shape (batch_size, input_size)
Returns:
Output tensor of shape (batch_size, output_size)
"""
# Matrix multiplication
if self.use_naive_matmul: if self.use_naive_matmul:
# Use naive implementation (for learning) result = matmul_naive(x.data, self.weights)
output = Tensor(matmul_naive(x.data, self.weights.data))
else: else:
# Use NumPy's optimized implementation (for speed) result = x.data @ self.weights
output = Tensor(x.data @ self.weights.data)
# Add bias if present # Add bias
if self.bias is not None: if self.use_bias:
output = Tensor(output.data + self.bias.data) result += self.bias
return output return Tensor(result)
def __call__(self, x: Tensor) -> Tensor: def __call__(self, x: Tensor) -> Tensor:
"""Make layer callable: layer(x) same as layer.forward(x)""" """Make layer callable: layer(x) same as layer.forward(x)"""

815
tinytorch/core/networks.py
View File

@@ -1,10 +1,10 @@
# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/networks/networks_dev.ipynb. # AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/04_networks/networks_dev.ipynb.
# %% auto 0 # %% auto 0
__all__ = ['Sequential', 'visualize_network_architecture', 'visualize_data_flow', 'compare_networks', 'create_mlp', __all__ = ['Sequential', 'create_mlp', 'visualize_network_architecture', 'visualize_data_flow', 'compare_networks',
'analyze_network_behavior', 'create_classification_network', 'create_regression_network'] 'create_classification_network', 'create_regression_network', 'analyze_network_behavior']
# %% ../../modules/networks/networks_dev.ipynb 3 # %% ../../modules/04_networks/networks_dev.ipynb 3
import numpy as np import numpy as np
import sys import sys
from typing import List, Union, Optional, Callable from typing import List, Union, Optional, Callable
@@ -18,12 +18,12 @@ from .tensor import Tensor
from .layers import Dense from .layers import Dense
from .activations import ReLU, Sigmoid, Tanh from .activations import ReLU, Sigmoid, Tanh
# %% ../../modules/networks/networks_dev.ipynb 4 # %% ../../modules/04_networks/networks_dev.ipynb 4
def _should_show_plots(): def _should_show_plots():
"""Check if we should show plots (disable during testing)""" """Check if we should show plots (disable during testing)"""
return 'pytest' not in sys.modules and 'test' not in sys.argv return 'pytest' not in sys.modules and 'test' not in sys.argv
# %% ../../modules/networks/networks_dev.ipynb 6 # %% ../../modules/04_networks/networks_dev.ipynb 6
class Sequential: class Sequential:
""" """
Sequential Network: Composes layers in sequence Sequential Network: Composes layers in sequence
@@ -35,6 +35,27 @@ class Sequential:
layers: List of layers to compose layers: List of layers to compose
TODO: Implement the Sequential network with forward pass. TODO: Implement the Sequential network with forward pass.
APPROACH:
1. Store the list of layers as an instance variable
2. Implement forward pass that applies each layer in sequence
3. Make the network callable for easy use
EXAMPLE:
network = Sequential([
Dense(3, 4),
ReLU(),
Dense(4, 2),
Sigmoid()
])
x = Tensor([[1, 2, 3]])
y = network(x) # Forward pass through all layers
HINTS:
- Store layers in self.layers
- Use a for loop to apply each layer in order
- Each layer's output becomes the next layer's input
- Return the final output
""" """
def __init__(self, layers: List): def __init__(self, layers: List):
@@ -45,6 +66,14 @@ class Sequential:
layers: List of layers to compose in order layers: List of layers to compose in order
TODO: Store the layers and implement forward pass TODO: Store the layers and implement forward pass
STEP-BY-STEP:
1. Store the layers list as self.layers
2. This creates the network architecture
EXAMPLE:
Sequential([Dense(3,4), ReLU(), Dense(4,2)])
creates a 3-layer network: Dense → ReLU → Dense
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
@@ -59,6 +88,25 @@ class Sequential:
Output tensor after passing through all layers Output tensor after passing through all layers
TODO: Implement sequential forward pass through all layers TODO: Implement sequential forward pass through all layers
STEP-BY-STEP:
1. Start with the input tensor: current = x
2. Loop through each layer in self.layers
3. Apply each layer: current = layer(current)
4. Return the final output
EXAMPLE:
Input: Tensor([[1, 2, 3]])
Layer1 (Dense): Tensor([[1.4, 2.8]])
Layer2 (ReLU): Tensor([[1.4, 2.8]])
Layer3 (Dense): Tensor([[0.7]])
Output: Tensor([[0.7]])
HINTS:
- Use a for loop: for layer in self.layers:
- Apply each layer: current = layer(current)
- The output of one layer becomes input to the next
- Return the final result
""" """
raise NotImplementedError("Student implementation required") raise NotImplementedError("Student implementation required")
@@ -66,7 +114,7 @@ class Sequential:
"""Make network callable: network(x) same as network.forward(x)""" """Make network callable: network(x) same as network.forward(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/networks/networks_dev.ipynb 7 # %% ../../modules/04_networks/networks_dev.ipynb 7
class Sequential: class Sequential:
""" """
Sequential Network: Composes layers in sequence Sequential Network: Composes layers in sequence
@@ -90,245 +138,7 @@ class Sequential:
"""Make network callable: network(x) same as network.forward(x)""" """Make network callable: network(x) same as network.forward(x)"""
return self.forward(x) return self.forward(x)
# %% ../../modules/networks/networks_dev.ipynb 11 # %% ../../modules/04_networks/networks_dev.ipynb 11
def visualize_network_architecture(network: Sequential, title: str = "Network Architecture"):
"""
Create a visual representation of network architecture.
Args:
network: Sequential network to visualize
title: Title for the plot
"""
if not _should_show_plots():
print("📊 Plots disabled during testing - this is normal!")
return
fig, ax = plt.subplots(1, 1, figsize=(12, 8))
# Network parameters
layer_count = len(network.layers)
layer_height = 0.8
layer_spacing = 1.2
# Colors for different layer types
colors = {
'Dense': '#4CAF50', # Green
'ReLU': '#2196F3', # Blue
'Sigmoid': '#FF9800', # Orange
'Tanh': '#9C27B0', # Purple
'default': '#757575' # Gray
}
# Draw layers
for i, layer in enumerate(network.layers):
# Determine layer type and color
layer_type = type(layer).__name__
color = colors.get(layer_type, colors['default'])
# Layer position
x = i * layer_spacing
y = 0
# Create layer box
layer_box = FancyBboxPatch(
(x - 0.3, y - layer_height/2),
0.6, layer_height,
boxstyle="round,pad=0.1",
facecolor=color,
edgecolor='black',
linewidth=2,
alpha=0.8
)
ax.add_patch(layer_box)
# Add layer label
ax.text(x, y, layer_type, ha='center', va='center',
fontsize=10, fontweight='bold', color='white')
# Add layer details
if hasattr(layer, 'input_size') and hasattr(layer, 'output_size'):
details = f"{layer.input_size}→{layer.output_size}"
ax.text(x, y - 0.3, details, ha='center', va='center',
fontsize=8, color='white')
# Draw connections to next layer
if i < layer_count - 1:
next_x = (i + 1) * layer_spacing
connection = ConnectionPatch(
(x + 0.3, y), (next_x - 0.3, y),
"data", "data",
arrowstyle="->", shrinkA=5, shrinkB=5,
mutation_scale=20, fc="black", lw=2
)
ax.add_patch(connection)
# Formatting
ax.set_xlim(-0.5, (layer_count - 1) * layer_spacing + 0.5)
ax.set_ylim(-1, 1)
ax.set_aspect('equal')
ax.axis('off')
# Add title
plt.title(title, fontsize=16, fontweight='bold', pad=20)
# Add legend
legend_elements = []
for layer_type, color in colors.items():
if layer_type != 'default':
legend_elements.append(patches.Patch(color=color, label=layer_type))
ax.legend(handles=legend_elements, loc='upper right', bbox_to_anchor=(1, 1))
plt.tight_layout()
plt.show()
# %% ../../modules/networks/networks_dev.ipynb 12
def visualize_data_flow(network: Sequential, input_data: Tensor, title: str = "Data Flow Through Network"):
"""
Visualize how data flows through the network.
Args:
network: Sequential network
input_data: Input tensor
title: Title for the plot
"""
if not _should_show_plots():
print("📊 Plots disabled during testing - this is normal!")
return
# Get intermediate outputs
intermediate_outputs = []
x = input_data
for i, layer in enumerate(network.layers):
x = layer(x)
intermediate_outputs.append({
'layer': network.layers[i],
'output': x,
'layer_index': i
})
# Create visualization
fig, axes = plt.subplots(2, len(network.layers), figsize=(4*len(network.layers), 8))
if len(network.layers) == 1:
axes = axes.reshape(1, -1)
for i, (layer, output) in enumerate(zip(network.layers, intermediate_outputs)):
# Top row: Layer information
ax_top = axes[0, i] if len(network.layers) > 1 else axes[0]
# Layer type and details
layer_type = type(layer).__name__
ax_top.text(0.5, 0.8, layer_type, ha='center', va='center',
fontsize=12, fontweight='bold')
if hasattr(layer, 'input_size') and hasattr(layer, 'output_size'):
ax_top.text(0.5, 0.6, f"{layer.input_size} → {layer.output_size}",
ha='center', va='center', fontsize=10)
# Output shape
ax_top.text(0.5, 0.4, f"Shape: {output['output'].shape}",
ha='center', va='center', fontsize=9)
# Output statistics
output_data = output['output'].data
ax_top.text(0.5, 0.2, f"Mean: {np.mean(output_data):.3f}",
ha='center', va='center', fontsize=9)
ax_top.text(0.5, 0.1, f"Std: {np.std(output_data):.3f}",
ha='center', va='center', fontsize=9)
ax_top.set_xlim(0, 1)
ax_top.set_ylim(0, 1)
ax_top.axis('off')
# Bottom row: Output visualization
ax_bottom = axes[1, i] if len(network.layers) > 1 else axes[1]
# Show output as heatmap or histogram
output_data = output['output'].data.flatten()
if len(output_data) <= 20: # Small output - show as bars
ax_bottom.bar(range(len(output_data)), output_data, alpha=0.7)
ax_bottom.set_title(f"Layer {i+1} Output")
ax_bottom.set_xlabel("Output Index")
ax_bottom.set_ylabel("Value")
else: # Large output - show histogram
ax_bottom.hist(output_data, bins=20, alpha=0.7, edgecolor='black')
ax_bottom.set_title(f"Layer {i+1} Output Distribution")
ax_bottom.set_xlabel("Value")
ax_bottom.set_ylabel("Frequency")
ax_bottom.grid(True, alpha=0.3)
plt.suptitle(title, fontsize=14, fontweight='bold')
plt.tight_layout()
plt.show()
# %% ../../modules/networks/networks_dev.ipynb 13
def compare_networks(networks: List[Sequential], network_names: List[str],
input_data: Tensor, title: str = "Network Comparison"):
"""
Compare different network architectures side-by-side.
Args:
networks: List of networks to compare
network_names: Names for each network
input_data: Input tensor to test with
title: Title for the plot
"""
if not _should_show_plots():
print("📊 Plots disabled during testing - this is normal!")
return
fig, axes = plt.subplots(2, len(networks), figsize=(6*len(networks), 10))
if len(networks) == 1:
axes = axes.reshape(2, -1)
for i, (network, name) in enumerate(zip(networks, network_names)):
# Get network output
output = network(input_data)
# Top row: Architecture visualization
ax_top = axes[0, i] if len(networks) > 1 else axes[0]
# Count layer types
layer_types = {}
for layer in network.layers:
layer_type = type(layer).__name__
layer_types[layer_type] = layer_types.get(layer_type, 0) + 1
# Create pie chart of layer types
if layer_types:
labels = list(layer_types.keys())
sizes = list(layer_types.values())
colors = plt.cm.Set3(np.linspace(0, 1, len(labels)))
ax_top.pie(sizes, labels=labels, autopct='%1.1f%%', colors=colors)
ax_top.set_title(f"{name}\nLayer Distribution")
# Bottom row: Output comparison
ax_bottom = axes[1, i] if len(networks) > 1 else axes[1]
output_data = output.data.flatten()
# Show output statistics
ax_bottom.hist(output_data, bins=20, alpha=0.7, edgecolor='black')
ax_bottom.axvline(np.mean(output_data), color='red', linestyle='--',
label=f'Mean: {np.mean(output_data):.3f}')
ax_bottom.axvline(np.median(output_data), color='green', linestyle='--',
label=f'Median: {np.median(output_data):.3f}')
ax_bottom.set_title(f"{name} Output Distribution")
ax_bottom.set_xlabel("Output Value")
ax_bottom.set_ylabel("Frequency")
ax_bottom.legend()
ax_bottom.grid(True, alpha=0.3)
plt.suptitle(title, fontsize=16, fontweight='bold')
plt.tight_layout()
plt.show()
# %% ../../modules/networks/networks_dev.ipynb 15
def create_mlp(input_size: int, hidden_sizes: List[int], output_size: int, def create_mlp(input_size: int, hidden_sizes: List[int], output_size: int,
activation=ReLU, output_activation=Sigmoid) -> Sequential: activation=ReLU, output_activation=Sigmoid) -> Sequential:
""" """
@@ -338,193 +148,432 @@ def create_mlp(input_size: int, hidden_sizes: List[int], output_size: int,
input_size: Number of input features input_size: Number of input features
hidden_sizes: List of hidden layer sizes hidden_sizes: List of hidden layer sizes
output_size: Number of output features output_size: Number of output features
activation: Activation function for hidden layers activation: Activation function for hidden layers (default: ReLU)
output_activation: Activation function for output layer output_activation: Activation function for output layer (default: Sigmoid)
Returns: Returns:
Sequential network Sequential network with MLP architecture
TODO: Implement MLP creation with alternating Dense and activation layers.
APPROACH:
1. Start with an empty list of layers
2. Add the first Dense layer: input_size → first hidden size
3. For each hidden layer:
- Add activation function
- Add Dense layer connecting to next hidden size
4. Add final activation function
5. Add final Dense layer: last hidden size → output_size
6. Add output activation function
7. Return Sequential(layers)
EXAMPLE:
create_mlp(3, [4, 2], 1) creates:
Dense(3→4) → ReLU → Dense(4→2) → ReLU → Dense(2→1) → Sigmoid
HINTS:
- Start with layers = []
- Add Dense layers with appropriate input/output sizes
- Add activation functions between Dense layers
- Don't forget the final output activation
""" """
raise NotImplementedError("Student implementation required")
# %% ../../modules/04_networks/networks_dev.ipynb 12
def create_mlp(input_size: int, hidden_sizes: List[int], output_size: int,
activation=ReLU, output_activation=Sigmoid) -> Sequential:
"""Create a Multi-Layer Perceptron (MLP) network."""
layers = [] layers = []
# Input layer # Add first layer
if hidden_sizes: current_size = input_size
layers.append(Dense(input_size, hidden_sizes[0])) for hidden_size in hidden_sizes:
layers.append(Dense(input_size=current_size, output_size=hidden_size))
layers.append(activation()) layers.append(activation())
current_size = hidden_size
# Hidden layers
for i in range(len(hidden_sizes) - 1):
layers.append(Dense(hidden_sizes[i], hidden_sizes[i + 1]))
layers.append(activation())
# Output layer
layers.append(Dense(hidden_sizes[-1], output_size))
else:
# Direct input to output
layers.append(Dense(input_size, output_size))
# Add output layer
layers.append(Dense(input_size=current_size, output_size=output_size))
layers.append(output_activation()) layers.append(output_activation())
return Sequential(layers) return Sequential(layers)
# %% ../../modules/networks/networks_dev.ipynb 18 # %% ../../modules/04_networks/networks_dev.ipynb 16
def analyze_network_behavior(network: Sequential, input_data: Tensor, def visualize_network_architecture(network: Sequential, title: str = "Network Architecture"):
title: str = "Network Behavior Analysis"):
""" """
Analyze how a network behaves with different types of input. Visualize the architecture of a Sequential network.
Args: Args:
network: Network to analyze network: Sequential network to visualize
input_data: Input tensor
title: Title for the plot title: Title for the plot
TODO: Create a visualization showing the network structure.
APPROACH:
1. Create a matplotlib figure
2. For each layer, draw a box showing its type and size
3. Connect the boxes with arrows showing data flow
4. Add labels and formatting
EXAMPLE:
Input → Dense(3→4) → ReLU → Dense(4→2) → Sigmoid → Output
HINTS:
- Use plt.subplots() to create the figure
- Use plt.text() to add layer labels
- Use plt.arrow() to show connections
- Add proper spacing and formatting
""" """
raise NotImplementedError("Student implementation required")
# %% ../../modules/04_networks/networks_dev.ipynb 17
def visualize_network_architecture(network: Sequential, title: str = "Network Architecture"):
"""Visualize the architecture of a Sequential network."""
if not _should_show_plots(): if not _should_show_plots():
print("📊 Plots disabled during testing - this is normal!") print("📊 Visualization disabled during testing")
return return
fig, axes = plt.subplots(2, 3, figsize=(15, 10)) fig, ax = plt.subplots(1, 1, figsize=(12, 6))
# 1. Input vs Output relationship # Calculate positions
ax1 = axes[0, 0] num_layers = len(network.layers)
input_flat = input_data.data.flatten() x_positions = np.linspace(0, 10, num_layers + 2)
output = network(input_data)
output_flat = output.data.flatten()
ax1.scatter(input_flat, output_flat, alpha=0.6) # Draw input
ax1.plot([input_flat.min(), input_flat.max()], ax.text(x_positions[0], 0, 'Input', ha='center', va='center',
[input_flat.min(), input_flat.max()], 'r--', alpha=0.5, label='y=x') bbox=dict(boxstyle='round,pad=0.3', facecolor='lightblue'))
ax1.set_xlabel('Input Values')
ax1.set_ylabel('Output Values')
ax1.set_title('Input vs Output')
ax1.legend()
ax1.grid(True, alpha=0.3)
# 2. Output distribution # Draw layers
ax2 = axes[0, 1] for i, layer in enumerate(network.layers):
ax2.hist(output_flat, bins=20, alpha=0.7, edgecolor='black') layer_name = type(layer).__name__
ax2.axvline(np.mean(output_flat), color='red', linestyle='--', ax.text(x_positions[i+1], 0, layer_name, ha='center', va='center',
label=f'Mean: {np.mean(output_flat):.3f}') bbox=dict(boxstyle='round,pad=0.3', facecolor='lightgreen'))
ax2.set_xlabel('Output Values')
ax2.set_ylabel('Frequency') # Draw arrow
ax2.set_title('Output Distribution') ax.arrow(x_positions[i], 0, 0.8, 0, head_width=0.1, head_length=0.1,
ax2.legend() fc='black', ec='black')
ax2.grid(True, alpha=0.3)
# 3. Layer-by-layer activation patterns # Draw output
ax3 = axes[0, 2] ax.text(x_positions[-1], 0, 'Output', ha='center', va='center',
activations = [] bbox=dict(boxstyle='round,pad=0.3', facecolor='lightcoral'))
x = input_data
for layer in network.layers: ax.set_xlim(-0.5, 10.5)
x = layer(x) ax.set_ylim(-0.5, 0.5)
if hasattr(layer, 'input_size'): # Dense layer ax.set_title(title)
activations.append(np.mean(x.data)) ax.axis('off')
else: # Activation layer plt.show()
activations.append(np.mean(x.data))
# %% ../../modules/04_networks/networks_dev.ipynb 21
ax3.plot(range(len(activations)), activations, 'bo-', linewidth=2, markersize=8) def visualize_data_flow(network: Sequential, input_data: Tensor, title: str = "Data Flow Through Network"):
ax3.set_xlabel('Layer Index')
ax3.set_ylabel('Mean Activation')
ax3.set_title('Layer-by-Layer Activations')
ax3.grid(True, alpha=0.3)
# 4. Network depth analysis
ax4 = axes[1, 0]
layer_types = [type(layer).__name__ for layer in network.layers]
layer_counts = {}
for layer_type in layer_types:
layer_counts[layer_type] = layer_counts.get(layer_type, 0) + 1
if layer_counts:
ax4.bar(layer_counts.keys(), layer_counts.values(), alpha=0.7)
ax4.set_xlabel('Layer Type')
ax4.set_ylabel('Count')
ax4.set_title('Layer Type Distribution')
ax4.grid(True, alpha=0.3)
# 5. Shape transformation
ax5 = axes[1, 1]
shapes = [input_data.shape]
x = input_data
for layer in network.layers:
x = layer(x)
shapes.append(x.shape)
layer_indices = range(len(shapes))
shape_sizes = [np.prod(shape) for shape in shapes]
ax5.plot(layer_indices, shape_sizes, 'go-', linewidth=2, markersize=8)
ax5.set_xlabel('Layer Index')
ax5.set_ylabel('Tensor Size')
ax5.set_title('Shape Transformation')
ax5.grid(True, alpha=0.3)
# 6. Network summary
ax6 = axes[1, 2]
ax6.axis('off')
summary_text = f"""
Network Summary:
• Total Layers: {len(network.layers)}
• Input Shape: {input_data.shape}
• Output Shape: {output.shape}
• Parameters: {sum(np.prod(layer.weights.data.shape) if hasattr(layer, 'weights') else 0 for layer in network.layers)}
• Architecture: {' → '.join([type(layer).__name__ for layer in network.layers])}
""" """
Visualize how data flows through the network.
ax6.text(0.05, 0.95, summary_text, transform=ax6.transAxes, Args:
fontsize=10, verticalalignment='top', fontfamily='monospace') network: Sequential network to analyze
input_data: Input tensor to trace through the network
title: Title for the plot
TODO: Create a visualization showing how data transforms through each layer.
plt.suptitle(title, fontsize=16, fontweight='bold') APPROACH:
1. Trace the input through each layer
2. Record the output of each layer
3. Create a visualization showing the transformations
4. Add statistics (mean, std, range) for each layer
EXAMPLE:
Input: [1, 2, 3] → Layer1: [1.4, 2.8] → Layer2: [1.4, 2.8] → Output: [0.7]
HINTS:
- Use a for loop to apply each layer
- Store intermediate outputs
- Use plt.subplot() to create multiple subplots
- Show statistics for each layer output
"""
raise NotImplementedError("Student implementation required")
# %% ../../modules/04_networks/networks_dev.ipynb 22
def visualize_data_flow(network: Sequential, input_data: Tensor, title: str = "Data Flow Through Network"):
"""Visualize how data flows through the network."""
if not _should_show_plots():
print("📊 Visualization disabled during testing")
return
# Trace data through network
current_data = input_data
layer_outputs = [current_data.data.flatten()]
layer_names = ['Input']
for layer in network.layers:
current_data = layer(current_data)
layer_outputs.append(current_data.data.flatten())
layer_names.append(type(layer).__name__)
# Create visualization
fig, axes = plt.subplots(2, len(layer_outputs), figsize=(15, 8))
for i, (output, name) in enumerate(zip(layer_outputs, layer_names)):
# Histogram
axes[0, i].hist(output, bins=20, alpha=0.7)
axes[0, i].set_title(f'{name}\nShape: {output.shape}')
axes[0, i].set_xlabel('Value')
axes[0, i].set_ylabel('Frequency')
# Statistics
stats_text = f'Mean: {np.mean(output):.3f}\nStd: {np.std(output):.3f}\nRange: [{np.min(output):.3f}, {np.max(output):.3f}]'
axes[1, i].text(0.1, 0.5, stats_text, transform=axes[1, i].transAxes,
verticalalignment='center', fontsize=10)
axes[1, i].set_title(f'{name} Statistics')
axes[1, i].axis('off')
plt.suptitle(title)
plt.tight_layout() plt.tight_layout()
plt.show() plt.show()
# %% ../../modules/networks/networks_dev.ipynb 21 # %% ../../modules/04_networks/networks_dev.ipynb 26
def compare_networks(networks: List[Sequential], network_names: List[str],
input_data: Tensor, title: str = "Network Comparison"):
"""
Compare multiple networks on the same input.
Args:
networks: List of Sequential networks to compare
network_names: Names for each network
input_data: Input tensor to test all networks
title: Title for the plot
TODO: Create a comparison visualization showing how different networks process the same input.
APPROACH:
1. Run the same input through each network
2. Collect the outputs and intermediate results
3. Create a visualization comparing the results
4. Show statistics and differences
EXAMPLE:
Compare MLP vs Deep Network vs Wide Network on same input
HINTS:
- Use a for loop to test each network
- Store outputs and any relevant statistics
- Use plt.subplot() to create comparison plots
- Show both outputs and intermediate layer results
"""
raise NotImplementedError("Student implementation required")
# %% ../../modules/04_networks/networks_dev.ipynb 27
def compare_networks(networks: List[Sequential], network_names: List[str],
input_data: Tensor, title: str = "Network Comparison"):
"""Compare multiple networks on the same input."""
if not _should_show_plots():
print("📊 Visualization disabled during testing")
return
# Test all networks
outputs = []
for network in networks:
output = network(input_data)
outputs.append(output.data.flatten())
# Create comparison plot
fig, axes = plt.subplots(2, len(networks), figsize=(15, 8))
for i, (output, name) in enumerate(zip(outputs, network_names)):
# Output distribution
axes[0, i].hist(output, bins=20, alpha=0.7)
axes[0, i].set_title(f'{name}\nOutput Distribution')
axes[0, i].set_xlabel('Value')
axes[0, i].set_ylabel('Frequency')
# Statistics
stats_text = f'Mean: {np.mean(output):.3f}\nStd: {np.std(output):.3f}\nRange: [{np.min(output):.3f}, {np.max(output):.3f}]\nSize: {len(output)}'
axes[1, i].text(0.1, 0.5, stats_text, transform=axes[1, i].transAxes,
verticalalignment='center', fontsize=10)
axes[1, i].set_title(f'{name} Statistics')
axes[1, i].axis('off')
plt.suptitle(title)
plt.tight_layout()
plt.show()
# %% ../../modules/04_networks/networks_dev.ipynb 31
def create_classification_network(input_size: int, num_classes: int, def create_classification_network(input_size: int, num_classes: int,
hidden_sizes: List[int] = None) -> Sequential: hidden_sizes: List[int] = None) -> Sequential:
""" """
Create a network for classification problems. Create a network for classification tasks.
Args: Args:
input_size: Number of input features input_size: Number of input features
num_classes: Number of output classes num_classes: Number of output classes
hidden_sizes: List of hidden layer sizes (default: [input_size//2]) hidden_sizes: List of hidden layer sizes (default: [input_size * 2])
Returns: Returns:
Sequential network for classification Sequential network for classification
"""
if hidden_sizes is None: TODO: Implement classification network creation.
hidden_sizes = [input_size // 2]
return create_mlp( APPROACH:
input_size=input_size, 1. Use default hidden sizes if none provided
hidden_sizes=hidden_sizes, 2. Create MLP with appropriate architecture
output_size=num_classes, 3. Use Sigmoid for binary classification (num_classes=1)
activation=ReLU, 4. Use appropriate activation for multi-class
output_activation=Sigmoid
) EXAMPLE:
create_classification_network(10, 3) creates:
Dense(10→20) → ReLU → Dense(20→3) → Sigmoid
HINTS:
- Use create_mlp() function
- Choose appropriate output activation based on num_classes
- For binary classification (num_classes=1), use Sigmoid
- For multi-class, you could use Sigmoid or no activation
"""
raise NotImplementedError("Student implementation required")
# %% ../../modules/networks/networks_dev.ipynb 22 # %% ../../modules/04_networks/networks_dev.ipynb 32
def create_classification_network(input_size: int, num_classes: int,
hidden_sizes: List[int] = None) -> Sequential:
"""Create a network for classification tasks."""
if hidden_sizes is None:
hidden_sizes = [input_size // 2] # Use input_size // 2 as default
# Choose appropriate output activation
output_activation = Sigmoid if num_classes == 1 else Softmax
return create_mlp(input_size, hidden_sizes, num_classes,
activation=ReLU, output_activation=output_activation)
# %% ../../modules/04_networks/networks_dev.ipynb 33
def create_regression_network(input_size: int, output_size: int = 1, def create_regression_network(input_size: int, output_size: int = 1,
hidden_sizes: List[int] = None) -> Sequential: hidden_sizes: List[int] = None) -> Sequential:
""" """
Create a network for regression problems. Create a network for regression tasks.
Args: Args:
input_size: Number of input features input_size: Number of input features
output_size: Number of output values (default: 1) output_size: Number of output values (default: 1)
hidden_sizes: List of hidden layer sizes (default: [input_size//2]) hidden_sizes: List of hidden layer sizes (default: [input_size * 2])
Returns: Returns:
Sequential network for regression Sequential network for regression
"""
if hidden_sizes is None: TODO: Implement regression network creation.
hidden_sizes = [input_size // 2]
return create_mlp( APPROACH:
input_size=input_size, 1. Use default hidden sizes if none provided
hidden_sizes=hidden_sizes, 2. Create MLP with appropriate architecture
output_size=output_size, 3. Use no activation on output layer (linear output)
activation=ReLU,
output_activation=Tanh # No activation for regression EXAMPLE:
) create_regression_network(5, 1) creates:
Dense(5→10) → ReLU → Dense(10→1) (no activation)
HINTS:
- Use create_mlp() but with no output activation
- For regression, we want linear outputs (no activation)
- You can pass None or identity function as output_activation
"""
raise NotImplementedError("Student implementation required")
# %% ../../modules/04_networks/networks_dev.ipynb 34
def create_regression_network(input_size: int, output_size: int = 1,
hidden_sizes: List[int] = None) -> Sequential:
"""Create a network for regression tasks."""
if hidden_sizes is None:
hidden_sizes = [input_size // 2] # Use input_size // 2 as default
# Create MLP with Tanh output activation for regression
return create_mlp(input_size, hidden_sizes, output_size,
activation=ReLU, output_activation=Tanh)
# %% ../../modules/04_networks/networks_dev.ipynb 38
def analyze_network_behavior(network: Sequential, input_data: Tensor,
title: str = "Network Behavior Analysis"):
"""
Analyze how a network behaves with different inputs.
Args:
network: Sequential network to analyze
input_data: Input tensor to test
title: Title for the plot
TODO: Create an analysis showing network behavior and capabilities.
APPROACH:
1. Test the network with the given input
2. Analyze the output characteristics
3. Test with variations of the input
4. Create visualizations showing behavior patterns
EXAMPLE:
Test network with original input and noisy versions
Show how output changes with input variations
HINTS:
- Test the original input
- Create variations (noise, scaling, etc.)
- Compare outputs across variations
- Show statistics and patterns
"""
raise NotImplementedError("Student implementation required")
# %% ../../modules/04_networks/networks_dev.ipynb 39
def analyze_network_behavior(network: Sequential, input_data: Tensor,
title: str = "Network Behavior Analysis"):
"""Analyze how a network behaves with different inputs."""
if not _should_show_plots():
print("📊 Visualization disabled during testing")
return
# Test original input
original_output = network(input_data)
# Create variations
noise_levels = [0.0, 0.1, 0.2, 0.5]
outputs = []
for noise in noise_levels:
noisy_input = Tensor(input_data.data + noise * np.random.randn(*input_data.data.shape))
output = network(noisy_input)
outputs.append(output.data.flatten())
# Create analysis plot
fig, axes = plt.subplots(2, 2, figsize=(12, 10))
# Original output
axes[0, 0].hist(outputs[0], bins=20, alpha=0.7)
axes[0, 0].set_title('Original Input Output')
axes[0, 0].set_xlabel('Value')
axes[0, 0].set_ylabel('Frequency')
# Output stability
output_means = [np.mean(out) for out in outputs]
output_stds = [np.std(out) for out in outputs]
axes[0, 1].plot(noise_levels, output_means, 'bo-', label='Mean')
axes[0, 1].fill_between(noise_levels,
[m-s for m, s in zip(output_means, output_stds)],
[m+s for m, s in zip(output_means, output_stds)],
alpha=0.3, label='±1 Std')
axes[0, 1].set_xlabel('Noise Level')
axes[0, 1].set_ylabel('Output Value')
axes[0, 1].set_title('Output Stability')
axes[0, 1].legend()
# Output distribution comparison
for i, (output, noise) in enumerate(zip(outputs, noise_levels)):
axes[1, 0].hist(output, bins=20, alpha=0.5, label=f'Noise={noise}')
axes[1, 0].set_xlabel('Output Value')
axes[1, 0].set_ylabel('Frequency')
axes[1, 0].set_title('Output Distribution Comparison')
axes[1, 0].legend()
# Statistics
stats_text = f'Original Mean: {np.mean(outputs[0]):.3f}\nOriginal Std: {np.std(outputs[0]):.3f}\nOutput Range: [{np.min(outputs[0]):.3f}, {np.max(outputs[0]):.3f}]'
axes[1, 1].text(0.1, 0.5, stats_text, transform=axes[1, 1].transAxes,
verticalalignment='center', fontsize=10)
axes[1, 1].set_title('Network Statistics')
axes[1, 1].axis('off')
plt.suptitle(title)
plt.tight_layout()
plt.show()

328
tinytorch/core/tensor.py
View File

@@ -1,67 +1,19 @@
# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/tensor/tensor_dev.ipynb. # AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/01_tensor/tensor_dev_enhanced.ipynb.
# %% auto 0 # %% auto 0
__all__ = ['Tensor'] __all__ = ['Tensor']
# %% ../../modules/tensor/tensor_dev.ipynb 3 # %% ../../modules/01_tensor/tensor_dev_enhanced.ipynb 2
import numpy as np import numpy as np
import sys from typing import Union, List, Tuple, Optional
from typing import Union, List, Tuple, Optional, Any
# %% ../../modules/tensor/tensor_dev.ipynb 4 # %% ../../modules/01_tensor/tensor_dev_enhanced.ipynb 4
class Tensor: class Tensor:
""" """
TinyTorch Tensor: N-dimensional array with ML operations. TinyTorch Tensor: N-dimensional array with ML operations.
The fundamental data structure for all TinyTorch operations. This enhanced version demonstrates dual-purpose educational content
Wraps NumPy arrays with ML-specific functionality. suitable for both self-learning and formal assessment.
TODO: Implement the core Tensor class with data handling and properties.
"""
def __init__(self, data: Union[int, float, List, np.ndarray], dtype: Optional[str] = None):
"""
Create a new tensor from data.
Args:
data: Input data (scalar, list, or numpy array)
dtype: Data type ('float32', 'int32', etc.). Defaults to auto-detect.
TODO: Implement tensor creation with proper type handling.
"""
raise NotImplementedError("Student implementation required")
@property
def data(self) -> np.ndarray:
"""Access underlying numpy array."""
raise NotImplementedError("Student implementation required")
@property
def shape(self) -> Tuple[int, ...]:
"""Get tensor shape."""
raise NotImplementedError("Student implementation required")
@property
def size(self) -> int:
"""Get total number of elements."""
raise NotImplementedError("Student implementation required")
@property
def dtype(self) -> np.dtype:
"""Get data type as numpy dtype."""
raise NotImplementedError("Student implementation required")
def __repr__(self) -> str:
"""String representation."""
raise NotImplementedError("Student implementation required")
# %% ../../modules/tensor/tensor_dev.ipynb 5
class Tensor:
"""
TinyTorch Tensor: N-dimensional array with ML operations.
The fundamental data structure for all TinyTorch operations.
Wraps NumPy arrays with ML-specific functionality.
""" """
def __init__(self, data: Union[int, float, List, np.ndarray], dtype: Optional[str] = None): def __init__(self, data: Union[int, float, List, np.ndarray], dtype: Optional[str] = None):
@@ -72,145 +24,171 @@ class Tensor:
data: Input data (scalar, list, or numpy array) data: Input data (scalar, list, or numpy array)
dtype: Data type ('float32', 'int32', etc.). Defaults to auto-detect. dtype: Data type ('float32', 'int32', etc.). Defaults to auto-detect.
""" """
#| exercise_start
#| hint: Use np.array() to convert input data to numpy array
#| solution_test: tensor.shape should match input shape
#| difficulty: easy
### BEGIN SOLUTION
# Convert input to numpy array # Convert input to numpy array
if isinstance(data, (int, float, np.number)): if isinstance(data, (int, float)):
# Handle Python and NumPy scalars self._data = np.array(data)
if dtype is None:
# Auto-detect type: int for integers, float32 for floats
if isinstance(data, int) or (isinstance(data, np.number) and np.issubdtype(type(data), np.integer)):
dtype = 'int32'
else:
dtype = 'float32'
self._data = np.array(data, dtype=dtype)
elif isinstance(data, list): elif isinstance(data, list):
# Let NumPy auto-detect type, then convert if needed self._data = np.array(data)
temp_array = np.array(data)
if dtype is None:
# Keep NumPy's auto-detected type, but prefer common ML types
if np.issubdtype(temp_array.dtype, np.integer):
dtype = 'int32'
elif np.issubdtype(temp_array.dtype, np.floating):
dtype = 'float32'
else:
dtype = temp_array.dtype
self._data = temp_array.astype(dtype)
elif isinstance(data, np.ndarray): elif isinstance(data, np.ndarray):
self._data = data.astype(dtype or data.dtype) self._data = data.copy()
else: else:
raise TypeError(f"Cannot create tensor from {type(data)}") self._data = np.array(data)
# Apply dtype conversion if specified
if dtype is not None:
self._data = self._data.astype(dtype)
### END SOLUTION
#| exercise_end
@property @property
def data(self) -> np.ndarray: def data(self) -> np.ndarray:
"""Access underlying numpy array.""" """Access underlying numpy array."""
#| exercise_start
#| hint: Return the stored numpy array (_data attribute)
#| solution_test: tensor.data should return numpy array
#| difficulty: easy
### BEGIN SOLUTION
return self._data return self._data
### END SOLUTION
#| exercise_end
@property @property
def shape(self) -> Tuple[int, ...]: def shape(self) -> Tuple[int, ...]:
"""Get tensor shape.""" """Get tensor shape."""
#| exercise_start
#| hint: Use the .shape attribute of the numpy array
#| solution_test: tensor.shape should return tuple of dimensions
#| difficulty: easy
### BEGIN SOLUTION
return self._data.shape return self._data.shape
### END SOLUTION
#| exercise_end
@property @property
def size(self) -> int: def size(self) -> int:
"""Get total number of elements.""" """Get total number of elements."""
#| exercise_start
#| hint: Use the .size attribute of the numpy array
#| solution_test: tensor.size should return total element count
#| difficulty: easy
### BEGIN SOLUTION
return self._data.size return self._data.size
### END SOLUTION
#| exercise_end
@property @property
def dtype(self) -> np.dtype: def dtype(self) -> np.dtype:
"""Get data type as numpy dtype.""" """Get data type as numpy dtype."""
#| exercise_start
#| hint: Use the .dtype attribute of the numpy array
#| solution_test: tensor.dtype should return numpy dtype
#| difficulty: easy
### BEGIN SOLUTION
return self._data.dtype return self._data.dtype
### END SOLUTION
#| exercise_end
def __repr__(self) -> str: def __repr__(self) -> str:
"""String representation.""" """String representation of the tensor."""
return f"Tensor({self._data.tolist()}, shape={self.shape}, dtype={self.dtype})" #| exercise_start
#| hint: Format as "Tensor([data], shape=shape, dtype=dtype)"
# %% ../../modules/tensor/tensor_dev.ipynb 9 #| solution_test: repr should include data, shape, and dtype
def _add_arithmetic_methods(): #| difficulty: medium
"""
Add arithmetic operations to Tensor class. ### BEGIN SOLUTION
data_str = self._data.tolist()
TODO: Implement arithmetic methods (__add__, __sub__, __mul__, __truediv__) return f"Tensor({data_str}, shape={self.shape}, dtype={self.dtype})"
and their reverse operations (__radd__, __rsub__, etc.) ### END SOLUTION
"""
#| exercise_end
def __add__(self, other: Union['Tensor', int, float]) -> 'Tensor':
"""Addition: tensor + other""" def add(self, other: 'Tensor') -> 'Tensor':
raise NotImplementedError("Student implementation required") """
Add two tensors element-wise.
def __sub__(self, other: Union['Tensor', int, float]) -> 'Tensor':
"""Subtraction: tensor - other""" Args:
raise NotImplementedError("Student implementation required") other: Another tensor to add
def __mul__(self, other: Union['Tensor', int, float]) -> 'Tensor': Returns:
"""Multiplication: tensor * other""" New tensor with element-wise sum
raise NotImplementedError("Student implementation required") """
#| exercise_start
def __truediv__(self, other: Union['Tensor', int, float]) -> 'Tensor': #| hint: Use numpy's + operator for element-wise addition
"""Division: tensor / other""" #| solution_test: result should be new Tensor with correct values
raise NotImplementedError("Student implementation required") #| difficulty: medium
# Add methods to Tensor class ### BEGIN SOLUTION
Tensor.__add__ = __add__ result_data = self._data + other._data
Tensor.__sub__ = __sub__ return Tensor(result_data)
Tensor.__mul__ = __mul__ ### END SOLUTION
Tensor.__truediv__ = __truediv__
#| exercise_end
# %% ../../modules/tensor/tensor_dev.ipynb 10
def _add_arithmetic_methods(): def multiply(self, other: 'Tensor') -> 'Tensor':
"""Add arithmetic operations to Tensor class.""" """
Multiply two tensors element-wise.
def __add__(self, other: Union['Tensor', int, float]) -> 'Tensor':
"""Addition: tensor + other""" Args:
if isinstance(other, Tensor): other: Another tensor to multiply
return Tensor(self._data + other._data)
else: # scalar Returns:
return Tensor(self._data + other) New tensor with element-wise product
"""
def __sub__(self, other: Union['Tensor', int, float]) -> 'Tensor': #| exercise_start
"""Subtraction: tensor - other""" #| hint: Use numpy's * operator for element-wise multiplication
if isinstance(other, Tensor): #| solution_test: result should be new Tensor with correct values
return Tensor(self._data - other._data) #| difficulty: medium
else: # scalar
return Tensor(self._data - other) ### BEGIN SOLUTION
result_data = self._data * other._data
def __mul__(self, other: Union['Tensor', int, float]) -> 'Tensor': return Tensor(result_data)
"""Multiplication: tensor * other""" ### END SOLUTION
if isinstance(other, Tensor):
return Tensor(self._data * other._data) #| exercise_end
else: # scalar
return Tensor(self._data * other) def matmul(self, other: 'Tensor') -> 'Tensor':
"""
def __truediv__(self, other: Union['Tensor', int, float]) -> 'Tensor': Matrix multiplication of two tensors.
"""Division: tensor / other"""
if isinstance(other, Tensor): Args:
return Tensor(self._data / other._data) other: Another tensor for matrix multiplication
else: # scalar
return Tensor(self._data / other) Returns:
New tensor with matrix product
def __radd__(self, other: Union[int, float]) -> 'Tensor':
"""Reverse addition: scalar + tensor""" Raises:
return Tensor(other + self._data) ValueError: If shapes are incompatible for matrix multiplication
"""
def __rsub__(self, other: Union[int, float]) -> 'Tensor': #| exercise_start
"""Reverse subtraction: scalar - tensor""" #| hint: Use np.dot() for matrix multiplication, check shapes first
return Tensor(other - self._data) #| solution_test: result should handle shape validation and matrix multiplication
#| difficulty: hard
def __rmul__(self, other: Union[int, float]) -> 'Tensor':
"""Reverse multiplication: scalar * tensor""" ### BEGIN SOLUTION
return Tensor(other * self._data) # Check shape compatibility
if len(self.shape) != 2 or len(other.shape) != 2:
def __rtruediv__(self, other: Union[int, float]) -> 'Tensor': raise ValueError("Matrix multiplication requires 2D tensors")
"""Reverse division: scalar / tensor"""
return Tensor(other / self._data) if self.shape[1] != other.shape[0]:
raise ValueError(f"Cannot multiply shapes {self.shape} and {other.shape}")
# Add methods to Tensor class
Tensor.__add__ = __add__ result_data = np.dot(self._data, other._data)
Tensor.__sub__ = __sub__ return Tensor(result_data)
Tensor.__mul__ = __mul__ ### END SOLUTION
Tensor.__truediv__ = __truediv__
Tensor.__radd__ = __radd__ #| exercise_end
Tensor.__rsub__ = __rsub__
Tensor.__rmul__ = __rmul__
Tensor.__rtruediv__ = __rtruediv__
# Call the function to add arithmetic methods
_add_arithmetic_methods()

25
tinytorch/core/utils.py
View File

@@ -299,3 +299,28 @@ class DeveloperProfile:
### END SOLUTION ### END SOLUTION
#| exercise_end #| exercise_end
def get_full_profile(self):
"""
Get complete profile with ASCII art.
Return full profile display including ASCII art and all details.
"""
#| exercise_start
#| hint: Format with ASCII art, then developer details with emojis
#| solution_test: Should return complete profile with ASCII art and details
#| difficulty: medium
#| points: 10
### BEGIN SOLUTION
return f"""{self.ascii_art}
👨‍💻 Developer: {self.name}
🏛️ Affiliation: {self.affiliation}
📧 Email: {self.email}
🐙 GitHub: @{self.github_username}
🔥 Ready to build ML systems from scratch!
"""
### END SOLUTION
#| exercise_end