Improved YOLO models

[0.7.0] - 2022-06-30

Added

• Improved YOLO model includes YOLOv4, YOLOv5, and YOLOX networks and training algorithms (#817)

Changed

• Move SSL transforms to pl_bolts/transforms (#905)
• Reviewed models.detection.yolo (#851)
• Reviewed LogisticRegression (#950)
• Bumped support of min python version to py3.8+ (#1021)
• Update numpy compatibility to <1.25.0 (#959)
• Update torchmetrics compatibility to <0.12.0 (#1016)
• Update pytorch-lightning compatibility to >1.7.0,<2.0.0 (#965, #973, #1006)

Fixed

• Dropped reference to torch._six (#993)

New Contributors

• @AdeelH made their first contribution in #939
• @AndresAlgaba made their first contribution in #967
• @Delaunay made their first contribution in #982
• @cdeepali made their first contribution in #993
• @NeoKish made their first contribution in #944
• @julien-blanchon made their first contribution in #973
• @qxcv made their first contribution in #964
• @vishnu-dev made their first contribution in #965
• @eggry made their first contribution in #960
• @heimish-kyma made their first contribution in #851

Full Changelog: 0.6.0...0.7.0

Minor patch release

What's Changed

• resolve require collisions by @Borda in #938
• Metrics by @BaruchG in #892

Full Changelog: 0.6.0...0.6.0.post1

Revisions and compatibility

[0.6.0] - 2022-11-03

Added

• Updated SparseML callback for latest PyTorch Lightning (#822)

• Updated torch version to v1.10.X (#815)

• Dataset specific args method to CIFAR10, ImageNet, MNIST, and STL10 (#890)

• Migrate to use lightning-utilities (#907)

• Support PyTorch Lightning v1.8 (#910)

• Major revision of Bolts

  • under_review flag (#835, #837)
  • Reviewing GAN basics, VisionDataModule, MNISTDataModule, CIFAR10DataModule (#843)
  • Added tests, updated doc-strings for Dummy Datasets (#865)
  • Binary MNIST/EMNIST Datasets and Datamodules (#866)
  • FashionMNIST/EMNIST Datamodules (#871)
  • Revision ArrayDataset (#872)
  • BYOL weight update callback (#867)
  • Revision models.vision.unet, models.vision.segmentation (#880)
  • Revision of SimCLR transforms (#857)
  • Revision Metrics (#878, #887)
  • Revision of BYOL module and tests (#874)
  • Revision of MNIST module (#873)
  • Revision of dataset normalizations (#898)
  • Revision of SimSiam module and tests (#891)
  • Revision datasets.kitti_dataset.KittiDataset (#896)
  • SWAV improvements (#903)
  • minor dcgan-import fix (#921)

Fixed

• Removing extra flatten (#809)
• support number of channels!=3 in YOLOConfiguration (#806)
• CVE-2007-4559 Patch (#894)

Contributors

@ArnolFokam, @Atharva-Phatak, @BaruchG, @Benjamin-Etheredge, @Borda, @Ce11an, @clementpoiret, @kfirgedal, @lijm1358, @matsumotosan, @nishantb06, @otaj, @rohitgr7, @shivammehta25, @TrellixVulnTeam

If we forgot someone due to not matching commit email with GitHub account, let us know :]

More object detection models and backbones

[0.5.0] - 2021-12-20

Added

• Added YOLO model (#552)
• Added SRGAN, SRImageLoggerCallback, TVTDataModule, SRCelebA, SRMNIST, SRSTL10 (#466)
• Added nn.Module support for FasterRCNN backbone (#661)
• Added RetinaNet with torchvision backbones (#529)
• Added Python 3.9 support (#786)

Changed

• VAE now uses deterministic KL divergence during training, previously estimated KL divergence by random sampling (#760)

Removed

• Removed PyTorch 1.6 support (#786)
• Removed Python 3.6 support (#785)

Fixed

• Fixed doctest fails with ImportError: cannot import name 'Env' from 'gym' (#751)
• Fixed MoCo v2 missing Cosine Annealing learning scheduler (#757)

Contributors

@abhayraw1 @akihironitta @chris-clem @hoangtnm @nmichlo @oke-aditya @Programmer-RD-AI @senarvi

If we forgot someone due to not matching commit email with GitHub account, let us know :]

More RL and callbacks

[0.4.0] - 2021-09-09

Added

• Added Soft Actor Critic (SAC) Model (#627)
• Added EMNISTDataModule, BinaryEMNISTDataModule, and BinaryEMNIST dataset (#676)
• Added Advantage Actor-Critic (A2C) Model (#598)
• Added Torch ORT Callback (#720)
• Added SparseML Callback (#724)

Changed

• Changed the default values pin_memory=False, shuffle=False and num_workers=16 to pin_memory=True, shuffle=True and num_workers=0 of datamodules (#701)
• Supporting deprecated attribute usage (#699)

Fixed

• Fixed ImageNet val loader to use val transform instead of train transform (#713)
• Fixed the MNIST download giving HTTP 404 with torchvision>=0.9.1 (#674)
• Removed momentum updating from val step and add separate val queue (#631)
• Fixed moving the queue to GPU when resuming checkpoint for SwAV model (#684)
• Fixed FP16 support with vision GPT model (#694)
• Removing bias from linear model regularisation (#669)
• Fixed CPC module issue (#680)

less softmax

[0.3.4] - 2021-06-17

Changed

• Replaced load_boston with load_diabetes in the docs and tests (#629)
• Added base encoder and MLP dimension arguments to BYOL constructor (#637)

Fixed

• Fixed the MNIST download giving HTTP 503 (#633)
• Fixed type annotation of ExperienceSource.__iter__ (#645)
• Fixed pretrained_urls on Windows (#652)
• Fixed logistic regression (#655, #664)
• Fixed double softmax in SSLEvaluator (#663)

updated LARS

[0.3.3] - 2021-04-17

Changed

• Suppressed missing package warnings, conditioned by WARN_MISSING_PACKAGE="1" (#617)
• Updated all scripts to LARS (#613)

Fixed

• Add missing dataclass requirements (#618)

typing friendly

[0.3.2] - 2021-03-20

Changed

• Renamed SSL modules: CPCV2 >> CPC_v2 and MocoV2 >> Moco_v2 (#585)
• Refactored setup.py to be typing friendly (#601)

compatibility PyTorch 1.8

[0.3.1] - 2021-03-09

Added

• Added Pix2Pix model (#533)

Changed

• Moved vision models (GPT2, ImageGPT, SemSegment, UNet) to pl_bolts.models.vision (#561)

Fixed

• Fixed BYOL moving average update (#574)
• Fixed custom gamma in rl (#550)
• Fixed PyTorch 1.8 compatibility issue (#580, #579)
• Fixed handling batchnorms in BatchGradientVerification [#569)
• Corrected num_rows calculation in LatentDimInterpolator callback (#573)

Contributors

@akihironitta, @aniketmaurya, @BartekRoszak, @FlorianMF, @indigoviolet, @kaushikb11, @mxksowie, @wjn0

If we forgot someone due to not matching commit email with GitHub account, let us know :]

major fixes & refactoring

Detail chnages

Added

• Added input_channels argument to UNet (#297)
• Added SwAV (#239, #348, #323)
• Added data monitor callbacks ModuleDataMonitor and TrainingDataMonitor (#285)
• Added DCGAN module (#403)
• Added VisionDataModule as parent class for BinaryMNISTDataModule, CIFAR10DataModule, FashionMNISTDataModule,
  and MNISTDataModule (#400)
• Added GIoU loss (#347)
• Added IoU loss (#469)
• Added semantic segmentation model SemSegment with UNet backend (#259)
• Added option to normalize latent interpolation images (#438)
• Added flags to datamodules (#388)
• Added metric GIoU (#347)
• Added Intersection over Union Metric/Loss (#469)
• Added SimSiam model (#407)
• Added gradient verification callback (#465)
• Added Backbones to FRCNN (#475)

Changed

• Decoupled datamodules from models (#332, #270)
• Set PyTorch Lightning 1.0 as the minimum requirement (#274)
• Moved pl_bolts.callbacks.self_supervised.BYOLMAWeightUpdate to pl_bolts.callbacks.byol_updates.BYOLMAWeightUpdate (#288)
• Moved pl_bolts.callbacks.self_supervised.SSLOnlineEvaluator to pl_bolts.callbacks.ssl_online.SSLOnlineEvaluator (#288)
• Moved pl_bolts.datamodules.*_dataset to pl_bolts.datasets.*_dataset (#275)
• Ensured sync across val/test step when using DDP (#371)
• Refactored CLI arguments of models (#394)
• Upgraded DQN to use .log (#404)
• Decoupled DataModules from models - CPCV2 (#386)
• Refactored datamodules/datasets (#338)
• Refactored Vision DataModules (#400)
• Refactored pl_bolts.callbacks (#477)
• Refactored the rest of pl_bolts.models.self_supervised (#481, #479)
• Update [torchvision.utils.make_grid(https://pytorch.org/docs/stable/torchvision/utils.html#torchvision.utils.make_grid)] kwargs to TensorboardGenerativeModelImageSampler (#494)

Fixed

• Fixed duplicate warnings when optional packages are unavailable (#341)
• Fixed ModuleNotFoundError when importing datamoules (#303)
• Fixed cyclic imports in pl_bolts.utils.self_suprvised (#350)
• Fixed VAE loss to use KL term of ELBO (#330)
• Fixed dataloders of MNISTDataModule to use self.batch_size (#331)
• Fixed missing outputs in SSL hooks for PyTorch Lightning 1.0 (#277)
• Fixed stl10 datamodule (#369)
• Fixes SimCLR transforms (#329)
• Fixed binary MNIST datamodule (#377)
• Fixed the end of batch size mismatch (#389)
• Fixed batch_size parameter for DataModules remaining (#344)
• Fixed CIFAR num_samples (#432)
• Fixed DQN run_n_episodes using the wrong environment variable (#525)

Contributors

@akihironitta, @ananyahjha93, @annikabrundyn, @awaelchli, @Borda, @briankosw, @chris-clem, @deng-cy, @hecoding, @miccio-dk, @oke-aditya, @SeanNaren, @sid-sundrani, @teddykoker, @zlapp

If we forgot someone due to not matching commit email with GitHub account, let us know :]