Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
焦文静 585a1e9165 | 1 year ago | |
---|---|---|
models | 1 year ago | |
README.md | 1 year ago | |
check_model.py | 1 year ago | |
datasets.py | 1 year ago | |
dist_train.sh | 1 year ago | |
engine.py | 1 year ago | |
generate_tensorboard.py | 1 year ago | |
losses.py | 1 year ago | |
lr_scheduler.py | 1 year ago | |
main.py | 1 year ago | |
requirements.txt | 1 year ago | |
samplers.py | 1 year ago | |
utils.py | 1 year ago |
Official PyTorch implementation of IEEE Transaction on Multimedia 2023 paper “DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition” .
[paper]
[Project Page]
We currenent release the pytorch version code for:
Our repository is built base on the DeiT repository, but we add some useful features:
Install PyTorch 1.7.0+ and torchvision 0.8.1+
conda install -c pytorch pytorch torchvision
Install other packages
pip install timm
pip install fvcore
Simply run the training scripts as followed, and take dilateformer_tiny as example:
bash dist_train.sh dilateformer_tiny [other prams]
If the training was interrupted abnormally, you can simply rerun the script for auto-resuming. Sometimes the checkpoint may not be saved properly, you should set the resumed model via --reusme ${work_path}/ckpt/backup.pth
.
You can generate the training curves as followed:
python3 generate_tensoboard.py
Note that you should install tensorboardX
.
You can calculate the FLOPs and parameters via:
python3 check_model.py
This repository is built using the timm library and the DeiT repository.
If you use this code for a paper, please cite:
DilateFormer
@article{jiao2023dilateformer,
title = {DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition},
author = {Jiao, Jiayu and Tang, Yu-Ming and Lin, Kun-Yu and Gao, Yipeng and Ma, Jinhua and Wang, Yaowei and Zheng, Wei-Shi},
journal = {{IEEE} Transaction on Multimedia},
year = {2023}
}
No Description
Python Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》