Learn2learn

Added

* New vision example: MAML++. ([Theo Morales](https://github.com/DubiousCactus))
* Add tutorial: "Demystifying Task Transforms", ([Varad Pimpalkhute](https://github.com/nightlessbaron/))
* Add `l2l.nn.MetaModule` and `l2l.nn.ParameterTransform` for parameter-efficient finetuning.
* Add `l2l.nn.freeze`and `l2l.nn.unfreeze`.
* Add Adapters and LoRA examples.
* Add TasksetSampler, compatible with PyTorch's Dataloaders.

Changed

* Documentation: uses `mkdocstrings` instead of `pydoc-markdown`.
* Remove `text/news_topic_classification.py` example.
* Rename TaskDataset to Taskset.

Fixed

* MAML Toy example. ([Theo Morales](https://github.com/DubiousCactus))
* Example for `detach_module`. ([Nimish Sanghi](https://github.com/nsanghi))
* Loading duplicate FGVC Aircraft images.
* Move vision datasets to Zenodo. (mini-ImageNet, tiered-ImageNet, FC100, CIFAR-FS, CUB200)
* mini-ImageNet targets are now ints (not np.float64).
* Swap family for variants in FGVCAircraft, as in MetaDataset.

Added

* Bounding box cropping for Aircraft and CUB200.
* Pretrained weights for vision models with: `l2l.vision.models.get_pretrained_backbone()`.
* Add `keep_requires_grad` flag to `detach_module`. ([Zhaofeng Wu](https://github.com/ZhaofengWu))

Changed

Fixed

* Fix arguments when instantiating `l2l.nn.Scale`.
* Fix `train_loss` logging in `LightningModule` implementations with PyTorch-Lightning 1.5.
* Fix `RandomClassRotation` ([283](https://github.com/learnables/learn2learn/pull/283)) to incorporate multi-channelled inputs. ([Varad Pimpalkhute](https://github.com/nightlessbaron/))
* Fix memory leak in `maml.py` and `meta-sgd.py` and add tests to `maml_test.py` and `metasgd_test.py` to check for possible future memory leaks. ([284](https://github.com/learnables/learn2learn/issues/284)) ([Kevin Zhang](https://github.com/kzhang2))

Added

* PyTorch Lightning interface to MAML, ANIL, ProtoNet, MetaOptNet.
* Automatic batcher for Lightning: `l2l.data.EpisodicBatcher`.
* `l2l.nn.PrototypicalClassifier` and `l2l.nn.SVMClassifier`.
* Add `l2l.vision.models.WRN28`.
* Separate modules for `CNN4Backbone`, `ResNet12Backbone`, `WRN28Backbones` w/ pretrained weights.
* Add `l2l.data.OnDeviceDataset` and implement `device` parameter for benchmarks.
* (Beta) Add `l2l.data.partition_task` and `l2l.data.InfiniteIterator`.

Changed

* Renamed and clarify dropout parameters for `ResNet12`.

Fixed

* Improved support for 1D inputs in `l2l.nn.KroneckerLinear`. (timweiland)

Fixed

* Fix setup.py for windows installs.

Added

* `FilteredMetaDatasest` filter the classes used to sample tasks.
* `UnionMetaDatasest` to get the union of multiple MetaDatasets.
* Alias `MiniImageNetCNN` to `CNN4` and add `embedding_size` argument.
* Optional data augmentation schemes for vision benchmarks.
* `l2l.vision.models.ResNet12`
* `l2l.vision.datasets.DescribableTextures`
* `l2l.vision.datasets.Quickdraw`
* `l2l.vision.datasets.FGVCFungi`
* Add `labels_to_indices` and `indices_to_labels` as optional arguments to `l2l.data.MetaDataset`.

Changed

* Updated reference for citations.

Added

* `l2l.vision.datasets.CUBirds200`.

Changed

* Optimization transforms can be accessed directly through `l2l.optim`, e.g. `l2l.optim.KroneckerTransform`.
* All vision models adhere to the `.features` and `.classifier` interface.

Fixed

* Fix `clone_module` for Modules whose submodules share parameters.