Download Latest Version MetaModules, TasksetSampler, Adapters _ LoRA, more examples and tutorials + removed dependency. source code.tar.gz (6.2 MB)
Email in envelope

Get an email when there's a new version of learn2learn

Home / v0.2.0
Name Modified Size InfoDownloads / Week
Parent folder
MetaModules, TasksetSampler, Adapters _ LoRA, more examples and tutorials source code.tar.gz 2023-06-03 6.2 MB
0
MetaModules, TasksetSampler, Adapters _ LoRA, more examples and tutorials source code.zip 2023-06-03 6.4 MB
0
README.md 2023-06-03 1.0 kB
0
Totals: 3 Items   12.6 MB 0

Added

  • New vision example: MAML++. (@Theo Morales)
  • Add tutorial: "Demystifying Task Transforms", (Varad Pimpalkhute)
  • Add l2l.nn.MetaModule and l2l.nn.ParameterTransform for parameter-efficient finetuning.
  • Add l2l.nn.freezeand 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)
  • Example for detach_module. (Nimish Sanghi)
  • 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.
Source: README.md, updated 2023-06-03