Changelog¶

v1.0.0 (15/12/2023)¶

Release version to OpenSTL (PyTorch Lightning) V1.0.0.

Release version to OpenSTL V0.3.0 as #25.

Support visualization tools in vis_video, config files in configs, and trained files (models, logs, and visualizations) in v0.3.0 of STL methods on various datasets (on updating).
Support the dataloader of video classification datasets Kinetics and BAIR, which has a similar setting as the Human3.6M and KTH dataloaders. Relevant video transforms in Kinetics are supported according to VideoMAE, and config files are provided. Add data preparation of TaxiBJ as issue #34.
Update STL results visualization by vis_video for video prediction, traffic prediction, weather prediction tasks in video_visualization, traffic_visualization, and weather_visualization.
Support Jupyter notebook tutorials and video examples in examples.
Support early-stop training with --early_stop_epoch as issue #36.
Support inference only with --inference in tools/test.py for issue #55, where results will be saved in ex_name/saved.

The OpenSTL paper has been accepted by NeurIPS 2023 Dataset and Benchmark Track.
Release arXiv preprint of OpenSTL, which describes the overall framework, benchmark results, and experimental settings, etc.
Update benchmark results of video prediction, traffic prediction, and weather prediction benchmarks in docs/en/model_zoos.
Add the Huggingface organization for OpenSTL🤗, where users can join it by invitation link.

Fix bugs in the dataloader (issue #26) and dataset prepration tools (issue #27 and #28).
Fix bugs of overwrite config values during training, where utils/main_utils/update_config will overwrite the config file with the default values in utils/main_utils/parser in mistake (issue #42). Using default_parser() to provide the default values and fulfill the config after updating values in the given config file (solving pull request #47).
Fix bugs of env installation (issue #62) and update environment.yml.

Release version to OpenSTL V0.2.0 as #20.

Rename the project to OpenSTL instead of SimVPv2 with module name refactoring.
Refactor the code structure thoroughly to support non-distributed and distributed (DDP) training & testing with tools/train.py and tools/test.py.
Refactor _dist_forward_collect and _non_dist_forward_collect to support collection of metrics.

Update the Weather Bench dataloader with 5.625deg, 2.8125deg, and 1.40625deg settings. Add Human3.6M dataloader (supporting augmentations) and config files. Add Moving FMNIST and MMNIST_CIFAR as two advanced variants of MMNIST datasets.
Update tools for dataset preparation of Human3.6M, Weather Bench, and Moving FMNIST.
Support PredNet, TAU, and DMVFN with configs and benchmark results. And fix bugs in these new STL methods.
Support multi-variant versions of Weather Bench with dataloader and metrics.
Support lpips metric for video prediction benchmarks.
Support STL results visualization by vis_video for video prediction, traffic prediction, weather prediction tasks.
Support visualization of STL methods on various datasets (on updating).

Update documents of video prediction, traffic prediction, and weather prediction benchmarks with benchmark results and spesific GPU settings (e.g., single GPU). Provide config files for supported STL methods.
Update docs/en documents for the basic usages and new features of V0.2.0. Adding detailed steps of installation and preparation datasets.
Clean-up STL benchmarks and update to the latest results with config files provided.

Fix bugs in training loops and validation loops to save GPU memory.
There might be some bugs in not using all parameters for calculating losses in ConvLSTM CrevNet, which should use --find_unused_parameters for DDP training.
Fig bugs of building distributed dataloaders and preparation of DDP training.
Fix bugs of some STL methods (CrevNet, DMVFN, PreDNet, and TAU).
Fix bugs in datasets: fixing Caltech dataset for evaluation (28/05/2023 updating Baidu Cloud).
Fix the bug of PSNR (changing the implementation from E3D-LSTM to the current version) and update results in the benchmarks.

Release version to V0.1.0 with code refactoring.

Refactor code structures as simvp/api, simvp/core, simvp/datasets, simvp/methods, simvp/models, simvp/modules. We support non-distributed training and evaluation by the executable python file tools/non_dist_train.py. Refactor config files for SimVP models.
Fix bugs in tools/nondist_train.py, simvp/utils, environment.yml, and .gitignore, etc.

Support Timm optimizers and schedulers.
Update popular Metaformer models as the hidden Translator \(h\) in SimVP, supporting ViT, Swin-Transformer, MLP-Mixer, ConvMixer, UniFormer, PoolFormer, ConvNeXt, VAN, HorNet, and MogaNet.
Update implementations of dataset and dataloader, supporting KTH Action, KittiCaltech Pedestrian, Moving MNIST, TaxiBJ, and WeatherBench.

Release arXiv preprint of SimVPv2. This version supports the morst experiments in SimVPv2, which is the extend version of SimVP.
Upload readthedocs documents. Summarize video prediction benchmark results on MMNIST in video_benchmarks.md.
Update benchmark results of video prediction baselines and MetaFormer architectures based on SimVP on MMNIST, TaxiBJ, and WeatherBench datasets.
Update README and add a license.