Release v0.17.1
This release supports running the book with SageMaker Studio Lab for free and introduces several fixes:
- Fix data synchronization for multi-GPU training in PyTorch (https://github.com/d2l-ai/d2l-en/pull/1978)
- Fix token sampling in BERT datasets (https://github.com/d2l-ai/d2l-en/pull/1979/)
- Fix semantic segmentation normalization in PyTorch (https://github.com/d2l-ai/d2l-en/pull/1980/)
- Fix mean square loss calculation in PyTorch and TensorFlow (https://github.com/d2l-ai/d2l-en/pull/1984)
- Fix broken paragraphs (https://github.com/d2l-ai/d2l-en/commit/8e0fe4ba54b6e2a0aa0f15f58a1e81f7fef1cdd7)