Changelog¶

v0.2.3 (17/06/2022)¶

Support the online document of OpenMixup (built on Read the Docs).
Provide README and update configs for self-supervised and supervised methods.
Support new Masked Image Modeling (MIM) methods (A2MIM, CAE).
Support new backbone networks (ResNeSt, PoolFormer, UniFormer).
Support new Fine-tuing method (HCR).
Support new mixup augmentation methods (SmoothMix, GridMix).
Support more regression losses (Focal L1/L2 loss, Balanced L1 loss, Balanced MSE loss).
Support more regression metrics (regression errors and correlations) and the regression dataset.
Support more reweight classification losses (Gradient Harmonized loss, Varifocal Focal Loss) from MMDetection.

Refactor code structures of openmixup.models.utils and support more network layers.
Fix the bug of DropPath (using stochastic depth rule) in ResNet for RSB A1/A2.

Support more self-supervised methods (Barlow Twins and Masked Image Modeling methods).
Support popular backbones (ConvMixer, MLPMixer, VAN) based on MMClassification.
Support more regression losses (Charbonnier loss and Focal Frequency loss).

Fix bugs in self-supervised classification benchmarks (configs and implementations of VisionTransformer).
Update INSTALL.md. We suggest you install PyTorch 1.8 or higher and mmcv-full for better usage of this repo. PyTorch 1.8 has bugs in AdamW optimizer.
Fix bugs in PreciseBNHook (update all BN stats) and RepeatSampler (set sync_random_seed).

Support masked image modeling (MIM) self-supervised methods (MAE, SimMIM, MaskFeat).
Support visualization of reconstruction results in MIM methods.
Support basic regression losses and metrics.

Fix bugs in regression metrics, MIM dataset, and benchmark configs. Notice that only l1_loss is supported by FP16 training, other regression losses (e.g., MSE and Smooth_L1 losses) will cause NAN when the target and prediction are not normalized in FP16 training.
We suggest you install PyTorch 1.8 or higher (required by some self-supervised methods) and mmcv-full for better usage of this repo. You can still use PyTorch 1.6 for supervised classification methods.

Support various popular backbones (ConvNets and ViTs), various image datasets, popular mixup methods, and benchmarks for supervised learning. Config files are available.
Support popular self-supervised methods (e.g., BYOL, MoCo.V3, MAE) on both large-scale and small-scale datasets, and self-supervised benchmarks (merged from MMSelfSup). Config files are available.
Support analyzing tools for self-supervised learning (kNN/SVM/linear metrics and t-SNE/UMAP visualization).
Convenient usage of configs: fast configs generation by ‘auto_train.py’ and configs inheriting (MMCV).
Support mixed-precision training (NVIDIA Apex or MMCV Apex) for all methods.
Model Zoos and lists of Awesome Mixups have been released.

Refactor code structures for vision transformers and self-supervised methods (e.g., MoCo.V3 and MAE).
Provide online analysis of self-supervised methods (knn metric and t-SNE/UMAP visualization).
More results are provided in Model Zoos.

Fix bugs of reusing of configs, ViTs, visualization tools, etc. It requires rebuilding of OpenMixup (install mmcv-full).

Refactor code structures according to MMSelfsup to fit high version of mmcv and PyTorch.
Support self-supervised methods and optimizes config structures.

Support various popular backbones (ConvNets and ViTs).
Support various handcrafted methods and optimization-based methods (e.g., PuzzleMix, AutoMix, SAMix, etc.).
Provide supervised image classification benchmarks in model_zoo and results (on updating).

Mixed Precision Training (NVIDIA Apex).
Improvement of GaussianBlur doubles the training speed of MoCo V2, SimCLR, BYOL.
More benchmarking results, including Places, VOC, COCO, linear/semi-supevised benchmarks.
Fix bugs in moco v2 and byol, now the results are reproducible.
Provide benchmarking results and model download links.
Support updating network every several interations (accumulation).
Support LARS and LAMB optimizer with nesterov (LAMB from MMclassification).
Support excluding specific parameters from optimizer updation.