Oxford pets PyTorch pipeline — 7 Steps

Fine-grained visual categorization of 37 cat and dog breeds in PyTorch: RGB data augmentation with torchvision transforms, pretrained ResNet-18 transfer learning, and Top-1/Top-3 accuracy audit.

1. 01 Data ingestion & EDA
2. 02 Preprocessing without leakage
3. 03 TensorDataset & DataLoader
4. 04 nn.Module architecture
5. 05 Loss function & optimizer
6. 06 Training loop & backprop
7. 07 Eval, metrics & checkpoint