diff --git a/book/chapters/01-setup.md b/book/chapters/01-setup.md index e1c25b1e..5d3d71cd 100644 --- a/book/chapters/01-setup.md +++ b/book/chapters/01-setup.md @@ -24,11 +24,7 @@ learning_objectives: ['Understand the nbdev notebook-to-Python workflow', 'Write Welcome to TinyTorch! This is your first module in the Machine Learning Systems course. -## Overview - -The setup module teaches you the complete TinyTorch development workflow while introducing fundamental programming concepts. You'll learn to write code with NBDev directives, implement classes and functions, and understand the module-to-package export system. - -## Learning Goals +## 🎯 Learning Objectives - Understand the nbdev notebook-to-Python workflow - Write your first TinyTorch code with `#| export` directives @@ -36,15 +32,11 @@ The setup module teaches you the complete TinyTorch development workflow while i - Run tests and use the CLI tools - Get comfortable with the development rhythm -## Files +## 🧠 Overview -- `setup_dev.py` - Main development file (Jupytext format with full educational content) -- `setup_dev.ipynb` - Jupyter notebook version (auto-generated and executed) -- `tinytorch_flame.txt` - ASCII art file containing the TinyTorch flame design -- `tests/test_setup.py` - Comprehensive pytest test suite -- `README.md` - This file +The setup module teaches you the complete TinyTorch development workflow while introducing fundamental programming concepts. You'll learn to write code with NBDev directives, implement classes and functions, and understand the module-to-package export system. -## What You'll Implement +## 📚 What You'll Build ### 1. Basic Functions - `hello_tinytorch()` - Display ASCII art and welcome message diff --git a/book/chapters/06-cnn.md b/book/chapters/06-cnn.md index 7f90c958..a0d50db3 100644 --- a/book/chapters/06-cnn.md +++ b/book/chapters/06-cnn.md @@ -5,7 +5,7 @@ difficulty: "Intermediate" time_estimate: "2-4 hours" prerequisites: [] next_steps: [] -learning_objectives: [] +learning_objectives: ['Understand the convolution operation (sliding window, local connectivity, weight sharing)', 'Implement Conv2D with explicit for-loops (single channel, single filter, no stride/pad)', 'Visualize how convolution builds feature maps', 'Compose Conv2D with other layers to build a simple ConvNet', '(Stretch) Explore stride, padding, pooling, and multi-channel input'] --- # Module: CNN @@ -16,24 +16,20 @@ learning_objectives: [] -```{admonition} 📊 Module Info -:class: note +## 📊 Module Info - **Difficulty**: ⭐⭐⭐ Advanced - **Time Estimate**: 6-8 hours - **Prerequisites**: Tensor, Activations, Layers, Networks modules - **Next Steps**: Training, Computer Vision modules **Implement the core building block of modern computer vision: the convolutional layer.** -``` -```{admonition} 🎯 Learning Objectives -:class: tip +## 🎯 Learning Objectives - Understand the convolution operation (sliding window, local connectivity, weight sharing) - Implement Conv2D with explicit for-loops (single channel, single filter, no stride/pad) - Visualize how convolution builds feature maps - Compose Conv2D with other layers to build a simple ConvNet - (Stretch) Explore stride, padding, pooling, and multi-channel input -``` ## 🧠 Build → Use → Understand 1. **Build**: Implement Conv2D from scratch (for-loop) diff --git a/book/chapters/11-compression.md b/book/chapters/11-compression.md index af8d71f9..dc1d35bd 100644 --- a/book/chapters/11-compression.md +++ b/book/chapters/11-compression.md @@ -16,10 +16,13 @@ learning_objectives: ['Understand model size and deployment constraints in real -## Overview -This module teaches students to make neural networks smaller, faster, and more efficient for real-world deployment. Students implement four core compression techniques and learn to balance accuracy with efficiency. +## 📊 Module Info +- **Difficulty**: ⭐⭐⭐⭐⭐ Expert +- **Time Estimate**: 8-10 hours +- **Prerequisites**: Networks, Training modules +- **Next Steps**: Kernels, MLOps modules -## Learning Goals +## 🎯 Learning Objectives - Understand model size and deployment constraints in real systems - Implement magnitude-based pruning to remove unimportant weights - Master quantization for 75% memory reduction (FP32 → INT8) @@ -27,6 +30,9 @@ This module teaches students to make neural networks smaller, faster, and more e - Create structured pruning to optimize network architectures - Compare compression techniques and their trade-offs +## 🧠 Overview +This module teaches students to make neural networks smaller, faster, and more efficient for real-world deployment. Students implement four core compression techniques and learn to balance accuracy with efficiency. + ## Educational Flow ### Step 1: Understanding Model Size diff --git a/modules/source/01_setup/README.md b/modules/source/01_setup/README.md index 34b9a850..fa373cbb 100644 --- a/modules/source/01_setup/README.md +++ b/modules/source/01_setup/README.md @@ -8,11 +8,7 @@ Welcome to TinyTorch! This is your first module in the Machine Learning Systems course. -## Overview - -The setup module teaches you the complete TinyTorch development workflow while introducing fundamental programming concepts. You'll learn to write code with NBDev directives, implement classes and functions, and understand the module-to-package export system. - -## Learning Goals +## 🎯 Learning Objectives - Understand the nbdev notebook-to-Python workflow - Write your first TinyTorch code with `#| export` directives @@ -20,15 +16,11 @@ The setup module teaches you the complete TinyTorch development workflow while i - Run tests and use the CLI tools - Get comfortable with the development rhythm -## Files +## 🧠 Overview -- `setup_dev.py` - Main development file (Jupytext format with full educational content) -- `setup_dev.ipynb` - Jupyter notebook version (auto-generated and executed) -- `tinytorch_flame.txt` - ASCII art file containing the TinyTorch flame design -- `tests/test_setup.py` - Comprehensive pytest test suite -- `README.md` - This file +The setup module teaches you the complete TinyTorch development workflow while introducing fundamental programming concepts. You'll learn to write code with NBDev directives, implement classes and functions, and understand the module-to-package export system. -## What You'll Implement +## 📚 What You'll Build ### 1. Basic Functions - `hello_tinytorch()` - Display ASCII art and welcome message diff --git a/modules/source/06_cnn/README.md b/modules/source/06_cnn/README.md index 8c21aca0..47f02a79 100644 --- a/modules/source/06_cnn/README.md +++ b/modules/source/06_cnn/README.md @@ -1,23 +1,19 @@ # 🔥 Module: CNN -```{admonition} 📊 Module Info -:class: note +## 📊 Module Info - **Difficulty**: ⭐⭐⭐ Advanced - **Time Estimate**: 6-8 hours - **Prerequisites**: Tensor, Activations, Layers, Networks modules - **Next Steps**: Training, Computer Vision modules **Implement the core building block of modern computer vision: the convolutional layer.** -``` -```{admonition} 🎯 Learning Objectives -:class: tip +## 🎯 Learning Objectives - Understand the convolution operation (sliding window, local connectivity, weight sharing) - Implement Conv2D with explicit for-loops (single channel, single filter, no stride/pad) - Visualize how convolution builds feature maps - Compose Conv2D with other layers to build a simple ConvNet - (Stretch) Explore stride, padding, pooling, and multi-channel input -``` ## 🧠 Build → Use → Understand 1. **Build**: Implement Conv2D from scratch (for-loop) diff --git a/modules/source/11_compression/README.md b/modules/source/11_compression/README.md index 49c6e553..ff54df1a 100644 --- a/modules/source/11_compression/README.md +++ b/modules/source/11_compression/README.md @@ -1,9 +1,12 @@ # 🔥 Module: Compression -## Overview -This module teaches students to make neural networks smaller, faster, and more efficient for real-world deployment. Students implement four core compression techniques and learn to balance accuracy with efficiency. +## 📊 Module Info +- **Difficulty**: ⭐⭐⭐⭐⭐ Expert +- **Time Estimate**: 8-10 hours +- **Prerequisites**: Networks, Training modules +- **Next Steps**: Kernels, MLOps modules -## Learning Goals +## 🎯 Learning Objectives - Understand model size and deployment constraints in real systems - Implement magnitude-based pruning to remove unimportant weights - Master quantization for 75% memory reduction (FP32 → INT8) @@ -11,6 +14,9 @@ This module teaches students to make neural networks smaller, faster, and more e - Create structured pruning to optimize network architectures - Compare compression techniques and their trade-offs +## 🧠 Overview +This module teaches students to make neural networks smaller, faster, and more efficient for real-world deployment. Students implement four core compression techniques and learn to balance accuracy with efficiency. + ## Educational Flow ### Step 1: Understanding Model Size