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.
[0.7.0] - 2022-06-30¶
[0.7.0] - Added¶
Improved YOLO model includes YOLOv4, YOLOv5, and YOLOX networks and training algorithms (#817)
[0.7.0] - 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 )
[0.7.0] - Fixed¶
Dropped reference to
torch._six
(#993)
[0.6.0] - 2022-11-02¶
[0.6.0] - 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
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 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)
[0.6.0] - Fixed¶
[0.5.0] - 2021-12-20¶
[0.5.0] - Added¶
[0.5.0] - Changed¶
VAE now uses deterministic KL divergence during training, previously estimated KL divergence by random sampling (#760)
[0.5.0] - Removed¶
[0.5.0] - Fixed¶
[0.4.0] - 2021-09-09¶
[0.4.0] - Added¶
[0.4.0] - Changed¶
[0.4.0] - 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)
[0.3.4] - 2021-06-17¶
[0.3.4] - Changed¶
[0.3.4] - Fixed¶
[0.3.3] - 2021-04-17¶
[0.3.3] - Changed¶
[0.3.3] - Fixed¶
Add missing
dataclass
requirements (#618)
[0.3.2] - 2021-03-20¶
[0.3.2] - Changed¶
[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
) topl_bolts.models.vision
(#561)
[0.3.1] - Fixed¶
[0.3.0] - 2021-01-20¶
[0.3.0] - Added¶
Added
input_channels
argument to UNet (#297)Added data monitor callbacks
ModuleDataMonitor
andTrainingDataMonitor
(#285)Added DCGAN module (#403)
Added
VisionDataModule
as parent class forBinaryMNISTDataModule
,CIFAR10DataModule
,FashionMNISTDataModule
, andMNISTDataModule
(#400)Added GIoU loss (#347)
Added IoU loss (#469)
Added semantic segmentation model
SemSegment
withUNet
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¶
Set PyTorch Lightning 1.0 as the minimum requirement (#274)
Moved
pl_bolts.callbacks.self_supervised.BYOLMAWeightUpdate
topl_bolts.callbacks.byol_updates.BYOLMAWeightUpdate
(#288)Moved
pl_bolts.callbacks.self_supervised.SSLOnlineEvaluator
topl_bolts.callbacks.ssl_online.SSLOnlineEvaluator
(#288)Moved
pl_bolts.datamodules.*_dataset
topl_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, #479Update [
torchvision.utils.make_grid
(https://pytorch.org/docs/stable/torchvision/utils.html#torchvision.utils.make_grid)] kwargs toTensorboardGenerativeModelImageSampler
(#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 useself.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¶
[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¶
[0.2.1] - Fixed¶
[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¶
[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 nDeprecated common.experience
[0.1.0] - Fixed¶
Documentation
Doct tests
CI pipeline
Imports and pkg
CPC fixes