PyTorch.
Deep learning with PyTorch — tensors, autograd, nn.Module, training loops, distributed training, and TorchServe.
Beginner
Start here — no prior experience needed
PyTorch Learning Roadmap
A structured path from tensor basics to training and deploying custom neural networks at scale.
PyTorch Neural Networks with nn.Module
Build reusable neural network architectures using nn.Module, nn.Sequential, and the full PyTorch training loop.
PyTorch Projects
Projects that take you from tensor basics to training and deploying custom neural networks — covering vision, NLP, and production deployment.
Introduction to PyTorch
Learn PyTorch tensors, automatic differentiation with autograd, and build your first neural network from scratch.
Intermediate
For developers with core concepts down
PyTorch Convolutional Neural Networks
Build CNNs for image classification using PyTorch — convolutional layers, pooling, batch norm, and training on real image datasets.
RNNs and LSTMs in PyTorch
Build sequence models from scratch — RNNs, LSTMs, GRUs — and apply them to text classification and time-series forecasting.
PyTorch Custom Datasets and DataLoaders
Build efficient data pipelines — custom Dataset classes, DataLoader configuration, augmentation, and optimized loading for large-scale training.
Advanced
Production-grade patterns for experienced engineers
PyTorch Training Best Practices
Master the full production training loop — mixed precision, gradient accumulation, learning rate warmup, checkpointing, and distributed training.
PyTorch Deployment with ONNX
Export PyTorch models to ONNX, optimize for inference, serve with ONNX Runtime, and convert to TorchScript for production.
Transformers in PyTorch
Build a Transformer from scratch, understand self-attention, and fine-tune pre-trained models with HuggingFace Transformers.
PyTorch Distributed Training
Scale training to multiple GPUs with DistributedDataParallel, mixed precision, and gradient checkpointing for large models.