Deep Learning with PyTorch, Eli Stevens, Luca Antiga, and Thomas Viehmann, 2020 (Manning Publications) - A practical and detailed guide to PyTorch, covering model development and common issues, including debugging strategies.
Designing Machine Learning Systems, Chip Huyen, 2022 (O'Reilly Media) - Offers a broad perspective on building and debugging robust machine learning systems, providing insights applicable to PyTorch model development.
On the difficulty of training recurrent neural networks, Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio, 2013Proceedings of the 30th International Conference on Machine Learning (ICML), Vol. 28 (PMLR (Proceedings of Machine Learning Research))DOI: 10.5555/3042817.3042823 - A foundational paper discussing challenges in training deep networks, particularly vanishing and exploding gradients, and methods to address them like gradient clipping.
pytorchviz GitHub Repository, Sergey Zagoruyko, 2024 - Provides a tool for visualizing PyTorch computation graphs, which aids in understanding tensor flow and identifying detached components during debugging.