Changelog¶

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[0.3.4] - 2021-06-17¶

[0.3.4] - Changed¶

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

[0.3.4] - 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)

[0.3.3] - 2021-04-17¶

[0.3.3] - Changed¶

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

[0.3.3] - Fixed¶

Add missing dataclass requirements (#618)

[0.3.2] - 2021-03-20¶

[0.3.2] - Changed¶

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

[0.3.1] - 2021-03-09¶

[0.3.1] - Added¶

Added Pix2Pix model (#533)

[0.3.1] - Changed¶

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

[0.3.1] - 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)

[0.3.0] - 2021-01-20¶

[0.3.0] - 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 pption 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)

[0.3.0] - 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)

[0.3.0] - 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)

[0.2.5] - 2020-10-12¶

Enabled PyTorch Lightning 1.0 compatibility

[0.2.4] - 2020-10-12¶

Enabled manual returns (#267)

[0.2.3] - 2020-10-12¶

[0.2.3] - Added¶

Enabled PyTorch Lightning 0.10 compatibility (#264)
Added dummy datasets (#266)
Added KittiDataModule (#248)
Added UNet (#247)
Added reinforcement learning models, losses and datamodules (#257)

[0.2.2] - 2020-09-14¶

Fixed confused logit (#222)

[0.2.1] - 2020-09-13¶

[0.2.1] - Added¶

Added pretrained VAE with resnet encoders and decoders
Added pretrained AE with resnet encoders and decoders
Added CPC pretrained on CIFAR10 and STL10
Verified BYOL implementation

[0.2.1] - Changed¶

Dropped all dependencies except PyTorch Lightning and PyTorch
Decoupled datamodules from GAN (#206)
Modularize AE & VAE (#196)

[0.2.1] - Fixed¶

Fixed gym (#221)
Fix L1/L2 regularization (#216)
Fix max_depth recursion crash in AsynchronousLoader (#191)

[0.2.0] - 2020-09-10¶

[0.2.0] - Added¶

Enabled Apache License, Version 2.0

[0.2.0] - Changed¶

Moved unnecessary dependencies to __main__ section in BYOL (#176)

[0.2.0] - Fixed¶

Fixed CPC STL10 finetune (#173)

[0.1.1] - 2020-08-23¶

[0.1.1] - Added¶

Added Faster RCNN + Pscal VOC DataModule (#157)
Added a better lars scheduling LARSWrapper (#162)
Added CPC finetuner (#158)
Added BinaryMNISTDataModule (#153)
Added learning rate scheduler to BYOL (#148)
Added Cityscapes DataModule (#136)
Added learning rate scheduler LinearWarmupCosineAnnealingLR (#138)
Added BYOL (#144)
Added ConfusedLogitCallback (#118)
Added an asynchronous single GPU dataloader. (#1521)

[0.1.1] - Fixed¶

Fixed simclr finetuner (#165)
Fixed STL10 finetuner (#164)
Fixed Image GPT (#108)
Fixed unused MNIST transforms in tran/val/test (#109)

[0.1.1] - Changed¶

Enhanced train batch function (#107)

[0.1.0] - 2020-07-02¶

[0.1.0] - Added¶

Added setup and repo structure
Added requirements
Added docs
Added Manifest
Added coverage
Added MNIST template
Added VAE template
Added GAN + AE + MNIST
Added Linear Regression
Added Moco2g
Added simclr
Added RL module
Added Loggers
Added Transforms
Added Tiny Datasets
Added regularization to linear + logistic models
Added Linear and Logistic Regression tests
Added Image GPT
Added Recommenders module

[0.1.0] - Changed¶

Device is no longer set in the DQN model init
Moved RL loss function to the losses module
Moved rl.common.experience to datamodules
train_batch function to VPG model to generate batch of data at each step (POC)
Experience source no longer gets initialized with a device, instead the device is passed at each step()
Refactored ExperienceSource classes to be handle multiple environments.

[0.1.0] - Removed¶

Removed N-Step DQN as the latest version of the DQN supports N-Step by setting the n_step arg to n
Deprecated common.experience

[0.1.0] - Fixed¶

Documentation
Doct tests
CI pipeline
Imports and pkg
CPC fixes