Torchdistill

New method
- Add knowledge review method (PRs 141, 145, 146)

The experimental result shown in [README.md](https://github.com/yoshitomo-matsubara/torchdistill) can be reproduced with [this yaml file](https://github.com/yoshitomo-matsubara/torchdistill/blob/main/configs/sample/ilsvrc2012/single_stage/kr/resnet18_from_resnet34.yaml).
The log and checkpoint file (including student model weights) are provided as part of **Assets** below.

New features
- Make nn.ModuleList hookable (PR 139)
- Support negative index in module path (PR 144)

Minor updates
- Update version (PRs 137, 148)
- Update README (PRs 138, 147)
- Fix a typo (PR 142)

Minor updates
- Update version (PRs 128, 136)
- Fix a typo (PR 130)
- Make pin_memory configurable (PR 134)

Bug fix
- Clear io_dict in pre-process (Issue 132, PR 135)

Bug fixes
- `DistributedDataParallel` is no longer allowed for wrapping models with no updatable parameters (Issue 122 PRs 124, 125)
- Fix a bug in detecting collate function type (Issue 123 PR 126)

Misc
- Update version (PR 127)

Examples
- Improve log format (PR 111)
- Tune hyperparameters for GLUE tasks (PRs 112, 113)
- Add sample KD configs for GLUE tasks (PR 114)

Misc
- Update notebooks (PR 115)
- Update README (PR 116)
- Update version (PRs 118, 120)
- Support PyTorch v1.9.0 (PR 119)

Examples
- Update GLUE example (PRs 97, 98, 99, 104, 106, 108)
- Enable test prediction to make a submission for GLUE leaderboard (PR 102)
- Add notebook (PRs 105, 109)

Bug fixes
- Provide kwargs (PR 94)
- Enable teacher to run in fp16 mode (PR 110)

Minor updates
- Update README (PRs 93, 101, 102, 103 107, 108)
- Refactor / Fix typos (PRs 95, 96, 100, 101, 104)

New features and example
- Introduce Hugging Face's Accelerate to better collaborate with their Transformers package (PR 91)
- Introduce example of text classification (GLUE tasks) with Hugging Face's Transformers and datasets (PR 92)

Minor updates
- Update README (PR 93)
- Allow non-function collator and make filtering optimizer's params optional (PR 89)