Skip to content
This repository has been archived by the owner on Jul 1, 2024. It is now read-only.

Releases: facebookresearch/ClassyVision

v0.7.0

21 Mar 05:24
Compare
Choose a tag to compare

Final Classy Vision stable release. Tested with Pytorch 2.0 and Python 3.9.

v0.6.0

19 Jul 20:08
Compare
Choose a tag to compare

New Features

  • Added compatibility with pytorch version 1.9.0 (#753)
  • Added RegNetZ model implementation (#713)
  • Redefined RegNetY 64GF to better performing model (#748
  • Added support for Pytorch AMP + ShardedDDP (#667)
  • Added support for cutmix in MixupTransform
  • Added support for a 1x1 convolution in the fully connected head (#712
  • Add support to normalize inputs in the heads (#664
  • Added support for SiLU activation in RegNets (#711
  • Added support for FP16 gradient communication in DDP (#709
  • Added reduction mode none in soft_target_cross_entropy_loss (#714
  • Added FLOPs computation to ViT (#746)
  • Upstreamed parameter schedulers to fvcore

v0.5.0

20 Nov 16:42
Compare
Choose a tag to compare

New Features

  • Release Vision Transformers model implementation, with recipes(#646)
  • Implemented gradient clipping (#643)
  • Implemented gradient accumulation (#644)
  • Added support for AdamW (#636)
  • Added Precise batch norm hook (#592)
  • Added support for adaptive pooling in fully_convolutional_linear_head (#602)
  • Added support for sync batch norm group size (#534)
  • Added a CSV Hook to manually inspect model predictions
  • Added a ClassyModel tutorial (#485)
  • Migrated to Hydra 1.0 (#536)
  • Migrated off of tensorboardX (#488)

Breaking Changes

  • ClassyOptimizer API improvements
    • added OptionsView to retrieve options from the optimizer param_group
  • Removed ClassyModel.evaluation_mode (#521)
  • Removed ImageNetDataset, now a subset of ImagePathDataset (#494)
  • Renamed is_master to is_primary in distributed_util (#576)

v0.4.0

29 Apr 23:00
Compare
Choose a tag to compare

New Features

  • Release EfficientNet model implementation (#475)
  • Add support to convert any PyTorch model to a ClassyModel with the ability to attach heads to it (#461)
    • Added a corresponding tutorial on ClassyModel and ClassyHeads (#485)
  • Squeeze and Excitation support for ResNe(X)t and DenseNet models (#426, #427)
  • Made ClassyHooks registrable (#401) and configurable (#402)
  • Migrated to TorchElastic v0.2.0 (#464)
  • Add SyncBatchNorm support (#423)
  • Implement mixup train augmentation (#469)
  • Support LARC for SGD optimizer (#408)
  • Added convenience wrappers for Iterable datasets (#455)
  • Tensorboard improvements
    • Plot histograms of model weights to Tensorboard (#432)
    • Reduce data logged to tensorboard (#436)
  • Invalid (NaN / Inf) loss detection
  • Revamped logging (#478)
  • Add bn_weight_decay configuration option for ResNe(X)t models
  • Support specifying update_interval to Parameter Schedulers (#418)

Breaking changes

  • ClassificationTask API improvement and train_step, eval_step simplification
    • Removed local_variables from ClassificationTask (#411, #412, #413, #414, #416, #421)
    • Move use_gpu from ClassyTrainer to ClassificationTask (#468)
    • Move num_dataloader_workers out of ClassyTrainer (#477)
  • Rename lr to value in parameter schedulers (#417)

v0.3.0

06 Mar 21:01
Compare
Choose a tag to compare

V0.30 release notes:

  • checkpoint_folder renamed to checkpoint_load_path: #379
  • head support on DenseNet: #383
  • Cleaner abstraction in ClassyTask/ClassyTrainer: eval_step, on_start, on_end, …
  • Speed metrics in TB: #385
  • test_phase_period in ClassificationTask #395
  • support for losses with trainable parameters #394
  • Added presets for some typical resNe(X)t configurations: #405

v0.2.0

24 Jan 21:00
Compare
Choose a tag to compare

Classy Vision v0.2 release notes

New features:

  • Adam optimizer (#301)
  • R(2+1)d units (#322)
  • Mixed precision training (#338)
  • One-hot targets in meters (#349)

This release has been tested on the latest PyTorch (1.4) and torchvision (0.5) releases. It also includes bug fixes and other smaller features.

v0.1.0

05 Dec 23:59
Compare
Choose a tag to compare

Initial release