Pytorch-adapt

Features

`domains` can now be passed into `CLossHook`:

python
CLossHook(domains=["src", "target"])

Features

- Added a new base validator `SimpleLossValidator`
- Added `BNMValidator`

Features

- Added pretrained models for DomainNet126
- Added `transforms.classification.get_timm_transform`

Bug fixes

- Fixed bug where `map_location` wasn't being used in a useful way when downloading pretrained models.
- Fixed some formatting issues in the documentation.

Features

- Added `APValidator`
- Added `adapters.MultiLabelClassifier`
- Added `hooks.MultiLabelClassifierHook`
- Added `frameworks.ignite.IgniteMultiLabelClassification`
- Added `models.pretrained_scores`

Features

- Added `VOCMultiLabel` dataset
- Added `Clipart1kMultiLabel` dataset
- Added `get_voc_multilabel` dataset getter

Breaking changes

- Moved `get_mnist_transform`, `get_resnet_transform`, and `GrayscaleToRGB` to a new `transforms` module

Features

Made DomainNet126 downloadable:

python
from pytorch_adapt.datasets import get_domainnet126
datasets = get_domainnet126(["clipart"], ["real"], folder=".", download=True)