PyTorch

From your first tensor to autograd, models, and training loops. Go through each lesson in order: read, run the examples yourself, then work the exercises at the bottom. Prefer a dense lookup instead? Jump to the quick reference.

Beginner

1. Tensors Basics

Creating tensors and reading their shape, dtype, and device.

2. Shape Ops & Indexing

reshape, squeeze/unsqueeze, permute, and indexing: same spirit as NumPy.

Intermediate

How PyTorch computes gradients automatically via the chain rule.

4. Building Models with nn.Module

Layers, forward passes, and what nn.Linear does under the hood.

Advanced

5. Loss Functions & Training Loop

Measuring how wrong a model is, and the update loop that fixes it.

6. Classification Metrics & Putting It Together

Accuracy, precision/recall, and reading model output correctly.