Skip to content

Latest commit

 

History

History

seg_light_ham

README.md

Light-Ham

This is a PyTorch implementation of Light-Ham combined with the VAN backbone. The code is based on MMSegmentation. More details can be found in Visual Attention Network.

Citation

@inproceedings{
    ham,
    title={Is Attention Better Than Matrix Decomposition?},
    author={Zhengyang Geng and Meng-Hao Guo and Hongxu Chen and Xia Li and Ke Wei and Zhouchen Lin},
    booktitle={International Conference on Learning Representations},
    year={2021},
}

@article{guo2022visual,
  title={Visual Attention Network},
  author={Guo, Meng-Hao and Lu, Cheng-Ze and Liu, Zheng-Ning and Cheng, Ming-Ming and Hu, Shi-Min},
  journal={arXiv preprint arXiv:2202.09741},
  year={2022}
}

Results

Notes: Pre-trained models can be found in Visual Attention Network for Classification.

VAN + Light-Ham / HamNet

Method Backbone Iters mIoU Params FLOPs Config Download
Light-Ham-D256 VAN-Tiny 160K 40.9 4.2M 6.5G config Google Drive
Light-Ham VAN-Tiny 160K 42.3 4.9M 11.3G config Google Drive
Light-Ham-D256 VAN-Small 160K 45.2 13.8M 15.8G config Google Drive
Light-Ham VAN-Small 160K 45.7 14.7M 21.4G config Google Drive
Light-Ham VAN-Base 160K 49.6 27.4M 34.4G config Google Drive
Light-Ham VAN-Large 160K 51.0 45.6M 55.0G config Google Drive
Light-Ham VAN-Huge 160K 51.5 61.1M 71.8G config Google Drive
- - - - - - - -
Segformer VAN-Base 160K 48.4 29.3M 68.6G - -
Segformer VAN-Large 160K 50.3 47.5M 89.2G - -
- - - - - - - -
HamNet VAN-Tiny-OS8 160K 41.5 11.9M 50.8G config Google Drive
HamNet VAN-Small-OS8 160K 45.1 24.2M 100.6G config Google Drive
HamNet VAN-Base-OS8 160K 48.7 36.9M 153.6G config Google Drive
HamNet VAN-Large-OS8 160K 50.2 55.1M 227.7G config Google Drive

Notes: In this scheme, we use multi-scale validation following Swin-Transformer. FLOPs are tested under the input size of 512 x 512 using torchprofile (recommended, highly accurate and automatic MACs/FLOPs statistics).

Preparation

Install MMSegmentation and download ADE20K according to the guidelines in MMSegmentation.

Training

We use 8 GPUs for training by default. Run:

bash dist_train.sh /path/to/config 8

Evaluation

To evaluate the model, run:

bash dist_test.sh /path/to/config /path/to/checkpoint_file 8 --out results.pkl --eval mIoU --aug-test

FLOPs

Install torchprofile using

pip install torchprofile

To calculate FLOPs for a model, run:

bash tools/flops.sh /path/to/checkpoint_file --shape 512 512