This repository is an open-source project for video prediction benchmarks, which contains the implementation code for paper:
SimVP: Towards Simple yet Powerful Spatiotemporal Predictive learning
Cheng Tan, Zhangyang Gao, Stan Z. Li.
This is the journal version of our previous conference work (SimVP: Simpler yet Better Video Prediction, In CVPR 2022).
It is worth noticing that the hidden Translator token mixing
and channel mixing
).
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.
Quantitative results of different methods on the Moving MNIST dataset (
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.
[2023-02-18] SimVP
v0.1.0 is released.
This project has provided an environment setting file of conda, users can easily reproduce the environment by the following commands:
git clone https://github.com/chengtan9907/SimVPv2
cd SimVPv2
conda env create -f environment.yml
conda activate SimVP
python setup.py develop
Dependencies
- argparse
- numpy
- hickle
- scikit-image=0.16.2
- torch
- timm
- tqdm
An example of single GPU training SimVP+gSTA on Moving MNIST dataset.
bash tools/prepare_data/download_mmnist.sh
python tools/non_dist_train.py -d mmnist -m SimVP --model_type gsta --lr 1e-3 --ex_name mmnist_simvp_gsta
We support various video prediction methods and will provide benchmarks on various video prediction datasets. We are working on add new methods and collecting experiment results.
-
Video Prediction Methods.
Currently supported methods
Currently supported MetaFormer models for SimVP
- ViT (ICLR'2021)
- Swin-Transformer (ICCV'2021)
- MLP-Mixer (NIPS'2021)
- ConvMixer (Openreview'2021)
- UniFormer (ICLR'2022)
- PoolFormer (CVPR'2022)
- ConvNeXt (CVPR'2022)
- VAN (ArXiv'2022)
- IncepU (SimVP.V1) (CVPR'2022)
- gSTA (SimVP.V2) (ArXiv'2022)
- HorNet (NIPS'2022)
- MogaNet (ArXiv'2022)
-
Video Prediction Benchmarks.
Currently supported datasets
- KTH Action (ICPR'2004) [download]
- KittiCaltech Pedestrian (IJRR'2013) [download]
- Moving MNIST (ICML'2015) [download]
- TaxiBJ (AAAI'2017) [download]
If you are interested in our repository and 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},
journal={arXiv preprint arXiv:2211.12509},
year={2022}
}
If you have any questions, feel free to contact us through email. Enjoy!
- Cheng Tan (tancheng@westlake.edu.cn), Westlake University & Zhejiang University
- Siyuan Li (lisiyuan@westlake.edu.cn), Westlake University & Zhejiang University
- Zhangyang Gao (gaozhangyang@westlake.edu.cn), Westlake University & Zhejiang University