Fastai

New Features

- Small DICOM segmentation dataset ([3034](https://github.com/fastai/fastai/pull/3034)), thanks to [moritzschwyzer](https://github.com/moritzschwyzer)

Bugs Squashed

- `NoneType object has no attribute append` in fastbook chapter 6 BIWI example ([3091](https://github.com/fastai/fastai/issues/3091))

New Features

- Refactor MixUp and CutMix into MixHandler ([3037](https://github.com/fastai/fastai/pull/3037)), thanks to [muellerzr](https://github.com/muellerzr)
- Refactors into a general MixHandler class, with MixUp and CutMix simply implementing a `before_batch` to perform the data augmentation. See `fastai.callback.mixup`

Bugs Squashed

- Gradient Accumulation + Mixed Precision shows artificially high training loss ([3048](https://github.com/fastai/fastai/issues/3048))

New Features

Bugs Squashed

- Update for fastcore `negate_func`->`not_`
- LR too high for gradient accumulation ([3040](https://github.com/fastai/fastai/pull/3040)), thanks to [marii-moe](https://github.com/marii-moe)
- Torchscript transforms incompatibility with nn.Sequential ([2920](https://github.com/fastai/fastai/issues/2920))

New Features

- Pytorch 1.7 subclassing support ([2769](https://github.com/fastai/fastai/issues/2769))

Bugs Squashed

- unsupported operand type(s) for +=: 'TensorCategory' and 'TensorText' when using AWD_LSTM for text classification ([3027](https://github.com/fastai/fastai/issues/3027))
- UserWarning when using SaveModelCallback() on after_epoch ([3025](https://github.com/fastai/fastai/issues/3025))
- Segmentation error: no implementation found for 'torch.nn.functional.cross_entropy' on types that implement torch_function ([3022](https://github.com/fastai/fastai/issues/3022))
- `TextDataLoaders.from_df()` returns `TypeError: 'float' object is not iterable` ([2978](https://github.com/fastai/fastai/issues/2978))
- Internal assert error in awd_qrnn ([2967](https://github.com/fastai/fastai/issues/2967))

New Features

- Option to preserve filenames in `download_images` ([2983](https://github.com/fastai/fastai/pull/2983)), thanks to [mess-lelouch](https://github.com/mess-lelouch)
- Deprecate `config` in `create_cnn` and instead pass kwargs directly ([2966](https://github.com/fastai/fastai/pull/2966)), thanks to [borisdayma](https://github.com/borisdayma)

Bugs Squashed

- Progress and Recorder callbacks serialize their data, resulting in large Learner export file sizes ([2981](https://github.com/fastai/fastai/issues/2981))
- `TextDataLoaders.from_df()` returns `TypeError: 'float' object is not iterable` ([2978](https://github.com/fastai/fastai/issues/2978))
- "only one element tensors can be converted to Python scalars" exception in Siamese Tutorial ([2973](https://github.com/fastai/fastai/issues/2973))
- Learn.load and LRFinder not functioning properly for the optimizer states ([2892](https://github.com/fastai/fastai/issues/2892))

Breaking Changes

- remove `log_args` ([2954](https://github.com/fastai/fastai/issues/2954))

New Features

- Improve performance of `RandomSplitter` (h/t muellerzr) ([2957](https://github.com/fastai/fastai/issues/2957))

Bugs Squashed

- Exporting TabularLearner via learn.export() leads to huge file size ([2945](https://github.com/fastai/fastai/issues/2945))
- `TensorPoint` object has no attribute `img_size` ([2950](https://github.com/fastai/fastai/issues/2950))