5 Commits

Author	SHA1	Message	Date
Vijay Janapa Reddi	b6bf37ac3c	feat: Add Milestone 04 (CNN Revolution 1998) + Clean spatial imports ... Milestone 04 - CNN Revolution: ✅ Complete 5-Act narrative structure (Challenge → Reflection) ✅ SimpleCNN architecture: Conv2d → ReLU → MaxPool → Linear ✅ Trains on 8x8 digits dataset (1,437 train, 360 test) ✅ Achieves 84.2% accuracy with only 810 parameters ✅ Demonstrates spatial operations preserve structure ✅ Beautiful visual output with progress tracking Key Features: - Conv2d (1→8 channels, 3×3 kernel) detects local patterns - MaxPool2d (2×2) provides translation invariance - 100× fewer parameters than equivalent MLP - Training completes in ~105 seconds (50 epochs) - Sample predictions table shows 9/10 correct Module 09 Spatial Improvements: - Removed ugly try/except import pattern - Clean imports: 'from tinytorch.core.tensor import Tensor' - Matches PyTorch style (simple and professional) - No fallback logic needed All 4 milestones now follow consistent 5-Act structure!	2025-09-30 17:04:41 -04:00
Vijay Janapa Reddi	9aa200767b	fix: Update Module 09 spatial for standalone classes ... Changes: - Removed broken _SimplifiedTensor and internal Module helper classes - Updated imports to use tinytorch.core instead of dev modules - Removed Module inheritance from Conv2d, MaxPool2d, AvgPool2d, SimpleCNN - All spatial classes now standalone like Linear in layers module This allows spatial module to export cleanly and import correctly: from tinytorch.core.spatial import Conv2d, MaxPool2d, AvgPool2d Smoke test: Conv2d(1,3,8,8) → (1,16,6,6) ✓	2025-09-30 16:54:21 -04:00
Vijay Janapa Reddi	ee9f559b8c	Fix nbdev export system across all 20 modules ... PROBLEM: - nbdev requires #| export directive on EACH cell to export when using # %% markers - Cell markers inside class definitions split classes across multiple cells - Only partial classes were being exported to tinytorch package - Missing matmul, arithmetic operations, and activation classes in exports SOLUTION: 1. Removed # %% cell markers INSIDE class definitions (kept classes as single units) 2. Added #| export to imports cell at top of each module 3. Added #| export before each exportable class definition in all 20 modules 4. Added __call__ method to Sigmoid for functional usage 5. Fixed numpy import (moved to module level from __init__) MODULES FIXED: - 01_tensor: Tensor class with all operations (matmul, arithmetic, shape ops) - 02_activations: Sigmoid, ReLU, Tanh, GELU, Softmax classes - 03_layers: Linear, Dropout classes - 04_losses: MSELoss, CrossEntropyLoss, BinaryCrossEntropyLoss classes - 05_autograd: Function, AddBackward, MulBackward, MatmulBackward, SumBackward - 06_optimizers: Optimizer, SGD, Adam, AdamW classes - 07_training: CosineSchedule, Trainer classes - 08_dataloader: Dataset, TensorDataset, DataLoader classes - 09_spatial: Conv2d, MaxPool2d, AvgPool2d, SimpleCNN classes - 10-20: All exportable classes in remaining modules TESTING: - Test functions use 'if __name__ == "__main__"' guards - Tests run in notebooks but NOT on import - Rosenblatt Perceptron milestone working perfectly RESULT: ✅ All 20 modules export correctly ✅ Perceptron (1957) milestone functional ✅ Clean separation: development (modules/source) vs package (tinytorch)	2025-09-30 11:21:04 -04:00
Vijay Janapa Reddi	ea2d0809d6	feat: update advanced modules (09-20) with latest improvements ... - Update spatial, tokenization, embeddings, attention modules - Update transformers, kv-caching, profiling modules - Update acceleration, quantization, compression modules - Update benchmarking and capstone modules - Align with current TinyTorch standards and patterns	2025-09-30 09:45:00 -04:00
Vijay Janapa Reddi	acb772dd92	Clean up module imports: convert tinytorch.core to sys.path style ... - Remove circular imports where modules imported from themselves - Convert tinytorch.core imports to sys.path relative imports - Only import dependencies that are actually used in each module - Preserve documentation imports in markdown cells - Use consistent relative path pattern across all modules - Remove hardcoded absolute paths in favor of relative imports Affected modules: 02_activations, 03_layers, 04_losses, 06_optimizers, 07_training, 09_spatial, 12_attention, 17_quantization	2025-09-30 08:58:58 -04:00