code refactor for OpenSTL V0.2.0

.coveragerc

@@ -0,0 +1,5 @@
+[report]
+exclude_lines =
+    @abstractmethod
+    @abc.abstractmethod
+    raise NotImplementedError

README.md

@@ -1,15 +1,15 @@
-# SimVP: Towards Simple yet Powerful Spatiotemporal Predictive learning
+# OpenSTL: Open-source Toolbox for SpatioTemporal Predictive Learning
 
 <p align="left">
 <a href="https://arxiv.org/abs/2211.12509" alt="arXiv">
     <img src="https://img.shields.io/badge/arXiv-2211.12509-b31b1b.svg?style=flat" /></a>
-<a href="https://github.com/Westlake-AI/MogaNet/blob/main/LICENSE" alt="license">
+<a href="https://github.com/chengtan9907/OpenSTL/blob/master/LICENSE" alt="license">
     <img src="https://img.shields.io/badge/license-Apache--2.0-%23002FA7" /></a>
 <a href="https://simvpv2.readthedocs.io/en/latest/" alt="docs">
     <img src="https://readthedocs.org/projects/simvpv2/badge/?version=latest" /></a>
-<a href="https://simvpv2.readthedocs.io/en/latest/" alt="docs">
+<a href="https://github.com/chengtan9907/OpenSTL/issues" alt="docs">
     <img src="https://img.shields.io/github/issues-raw/chengtan9907/SimVPv2?color=%23FF9600" /></a>
-<a href="https://github.com/chengtan9907/SimVPv2/issues" alt="resolution">
+<a href="https://github.com/chengtan9907/OpenSTL/issues" alt="resolution">
     <img src="https://img.shields.io/badge/issue%20resolution-1%20d-%23B7A800" /></a>
 </p>
 
@@ -25,47 +25,35 @@ This repository is an open-source project for video prediction benchmarks, which
 
 ## Introduction
 
-This is the journal version of our previous conference work ([SimVP: Simpler yet Better Video Prediction](https://arxiv.org/abs/2206.05099), In CVPR 2022).
-
-It is worth noticing that the hidden Translator $h$ in SimVP can be replaced by any [MetaFormer](https://arxiv.org/abs/2111.11418) block (satisfying the macro design of `token mixing` and `channel mixing`).
+This is the journal version of our previous conference work ([SimVP: Simpler yet Better Video Prediction](https://arxiv.org/abs/2206.05099), In CVPR 2022). It is worth noticing that the hidden Translator $h$ in SimVP can be replaced by any [MetaFormer](https://arxiv.org/abs/2111.11418) block (satisfying the macro design of `token mixing` and `channel mixing`).
 <p align="center">
     <img width="75%" src="https://user-images.githubusercontent.com/44519745/219116763-bb4ab408-7f25-47d3-b93e-79834c7b065e.png"> <br>
 </p>
 
-The performance of SimVPs on the Moving MNIST dataset. For the training time, the less the better. For the inference efficiency (frames per second), the more the better.
-<p align="center">
-    <img width="70%" src="https://user-images.githubusercontent.com/44519745/219116933-a34f5133-b38f-4657-bea4-c49361696fd2.png"> <br>
-</p>
-
-Quantitative results of different methods on the Moving MNIST dataset ($10 \rightarrow 10$ frames).
-<p align="center">
-    <img width="75%" src="https://user-images.githubusercontent.com/44519745/219117248-90825af9-28e8-42c6-8fec-858ef7f6dd92.png"> <br>
-</p>
-
 <p align="right">(<a href="#top">back to top</a>)</p>
 
 ## Overview
 
-* `simvp/api` contains an experiment runner.
-* `simvp/core` contains core training plugins and metrics.
-* `simvp/datasets` contains datasets and dataloaders.
-* `simvp/methods/` contains training methods for various video prediction methods.
-* `simvp/models/` contains the main network architectures of various video prediction methods.
-* `simvp/modules/` contains network modules and layers.
-* `tools/non_dist_train.py` is the executable python file with possible arguments for training, validating, and testing pipelines.
+* `openstl/api` contains an experiment runner.
+* `openstl/core` contains core training plugins and metrics.
+* `openstl/datasets` contains datasets and dataloaders.
+* `openstl/methods/` contains training methods for various video prediction methods.
+* `openstl/models/` contains the main network architectures of various video prediction methods.
+* `openstl/modules/` contains network modules and layers.
+* `tools/train.py` and `tools/train.py` are the executable python file with possible arguments for training, validating, and testing pipelines.
 
 ## News and Updates
 
-[2023-02-18] `SimVP` v0.1.0 is released. Benchmark results and config files are updated for MMNIST, TaxiBJ, and WeatherBench datasets.
+[2023-04-19] `OpenSTL` v0.2.0 is released.
 
 ## Installation
 
 This project has provided an environment setting file of conda, users can easily reproduce the environment by the following commands:
 ```shell
-git clone https://github.com/chengtan9907/SimVPv2
-cd SimVPv2
+git clone https://github.com/chengtan9907/OpenSTL
+cd OpenSTL
 conda env create -f environment.yml
-conda activate SimVP
+conda activate OpenSTL
 python setup.py develop
 ```
 
@@ -76,21 +64,22 @@ python setup.py develop
 * fvcore
 * numpy
 * hickle
-* scikit-image=0.16.2
+* scikit-image
 * scikit-learn
 * torch
 * timm
 * tqdm
+* xarray
 </details>
 
 Please refer to [install.md](docs/en/install.md) for more detailed instructions.
 
 ## Getting Started
 
-Please see [get_started.md](docs/en/get_started.md) for the basic usage. Here is an example of single GPU training SimVP+gSTA on Moving MNIST dataset.
+Please see [get_started.md](docs/en/get_started.md) for the basic usage. Here is an example of single GPU non-dist training SimVP+gSTA on Moving MNIST dataset.
 ```shell
 bash tools/prepare_data/download_mmnist.sh
-python tools/non_dist_train.py -d mmnist --lr 1e-3 -c ./configs/mmnist/simvp/SimVP_gSTA.py --ex_name mmnist_simvp_gsta
+python tools/train.py -d mmnist --lr 1e-3 -c ./configs/mmnist/simvp/SimVP_gSTA.py --ex_name mmnist_simvp_gsta
 ```
 
 <p align="right">(<a href="#top">back to top</a>)</p>
@@ -140,11 +129,11 @@ We support various video prediction methods and will provide benchmarks on vario
     <details open>
     <summary>Currently supported datasets</summary>
 
-    - [x] [KTH Action](https://ieeexplore.ieee.org/document/1334462) (ICPR'2004)  [[download](https://www.csc.kth.se/cvap/actions/)] [[config](https://github.com/chengtan9907/SimVPv2/configs/kth)]
-    - [x] [KittiCaltech Pedestrian](https://dl.acm.org/doi/10.1177/0278364913491297) (IJRR'2013) [[download](https://figshare.com/articles/dataset/KITTI_hkl_files/7985684)] [[config](https://github.com/chengtan9907/SimVPv2/configs/kitticaltech)]
-    - [x] [Moving MNIST](http://arxiv.org/abs/1502.04681) (ICML'2015) [[download](http://www.cs.toronto.edu/~nitish/unsupervised_video/)] [[config](https://github.com/chengtan9907/SimVPv2/configs/mmnist)]
-    - [x] [TaxiBJ](https://arxiv.org/abs/1610.00081) (AAAI'2017) [[download](https://github.com/TolicWang/DeepST/tree/master/data/TaxiBJ)] [[config](https://github.com/chengtan9907/SimVPv2/configs/taxibj)]
-    - [x] [WeatherBench](https://arxiv.org/abs/2002.00469) (ArXiv'2020) [[download](https://github.com/pangeo-data/WeatherBench)] [[config](https://github.com/chengtan9907/SimVPv2/configs/weather)]
+    - [x] [KTH Action](https://ieeexplore.ieee.org/document/1334462) (ICPR'2004)  [[download](https://www.csc.kth.se/cvap/actions/)] [[config](configs/kth)]
+    - [x] [KittiCaltech Pedestrian](https://dl.acm.org/doi/10.1177/0278364913491297) (IJRR'2013) [[download](https://figshare.com/articles/dataset/KITTI_hkl_files/7985684)] [[config](configs/kitticaltech)]
+    - [x] [Moving MNIST](http://arxiv.org/abs/1502.04681) (ICML'2015) [[download](http://www.cs.toronto.edu/~nitish/unsupervised_video/)] [[config](configs/mmnist)]
+    - [x] [TaxiBJ](https://arxiv.org/abs/1610.00081) (AAAI'2017) [[download](https://github.com/TolicWang/DeepST/tree/master/data/TaxiBJ)] [[config](configs/taxibj)]
+    - [x] [WeatherBench](https://arxiv.org/abs/2002.00469) (ArXiv'2020) [[download](https://github.com/pangeo-data/WeatherBench)] [[config](configs/weather)]
 
     </details>
 
@@ -160,23 +149,31 @@ SimVPv2 is an open-source project for video prediction methods created by resear
 
 ## Citation
 
-If you are interested in our repository and our paper, please cite the following paper:
+If you are interested in our repository or our paper, please cite the following paper:
 
 ```
 @article{tan2022simvp,
   title={SimVP: Towards Simple yet Powerful Spatiotemporal Predictive Learning},
-  author={Tan, Cheng and Gao, Zhangyang and Li, Stan Z},
+  author={Tan, Cheng and Gao, Zhangyang and Li, Siyuan and Li, Stan Z},
   journal={arXiv preprint arXiv:2211.12509},
   year={2022}
 }
 ```
+```
+@misc{tan2023openstl,
+  title={OpenSTL: Open-source Toolbox for SpatioTemporal Predictive Learning},
+  author={Tan, Cheng and Li, Siyuan and Gao, Zhangyang and Li, Stan Z},
+  howpublished = {\url{https://github.com/chengtan9907/OpenSTL}},
+  year={2023}
+}
+```
 
 ## Contribution and Contact
 
-For adding new features, looking for helps, or reporting bugs associated with SimVPv2, please open a [GitHub issue](https://github.com/chengtan9907/SimVPv2/issues) and [pull request](https://github.com/chengtan9907/SimVPv2/pulls) with the tag "help wanted" or "enhancement". Feel free to contact us through email if you have any questions. Enjoy!
+For adding new features, looking for helps, or reporting bugs associated with `OpenSTL`, please open a [GitHub issue](https://github.com/chengtan9907/OpenSTL/issues) and [pull request](https://github.com/chengtan9907/OpenSTL/pulls) with the tag "help wanted" or "enhancement". Feel free to contact us through email if you have any questions. Enjoy!
 
-- Cheng Tan ([email protected]), Westlake University & Zhejiang University
 - Siyuan Li ([email protected]), Westlake University & Zhejiang University
+- Cheng Tan ([email protected]), Westlake University & Zhejiang University
 - Zhangyang Gao ([email protected]), Westlake University & Zhejiang University
 
 <p align="right">(<a href="#top">back to top</a>)</p>

configs/weather/tcc_5_625/ConvLSTM.py

@@ -0,0 +1,19 @@
+method = 'ConvLSTM'
+# reverse scheduled sampling
+reverse_scheduled_sampling = 0
+r_sampling_step_1 = 25000
+r_sampling_step_2 = 50000
+r_exp_alpha = 5000
+# scheduled sampling
+scheduled_sampling = 1
+sampling_stop_iter = 50000
+sampling_start_value = 1.0
+sampling_changing_rate = 0.00002
+# model
+num_hidden = '128,128,128,128'
+filter_size = 5
+stride = 1
+patch_size = 2
+layer_norm = 0
+# training
+lr = 1e-4