Need help with FunnelAct?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

megvii-model
167 Stars 19 Forks MIT License 20 Commits 6 Opened issues

Services available

!
?

Need anything else?

Contributors list

# 84,541
Python
17 commits

Funnel Activation for Visual Recognition

This repository provides MegEngine implementation for "Funnel Activation for Visual Recognition".

Requirement

  • MegEngine 0.5.1 (https://github.com/MegEngine/MegEngine)

Citation

If you use these models in your research, please cite:

@inproceedings{ma2020funnel, 
            title={Funnel activation for visual recognition},  
            author={Ma, Ningning and Zhang, Xiangyu and Sun, Jian},  
            booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},  
            year={2020} 
}

Usage

Train:

    python3 train.py --dataset-dir=/path/to/imagenet

Eval:

    python3 test.py --data=/path/to/imagenet --model /path/to/model --ngpus 1

Inference:

    python3 inference.py --model /path/to/model --image /path/to/image.jpg

Trained Models

  • OneDrive download: Link

Results

  • Comparison on ImageNet dataset:

| Model | Activation | Top-1 err.| | :---------------------- | :--------: | :------: | | ResNet50 | ReLU | 24.0 | | ResNet50 | PReLU | 23.7 | | ResNet50 | Swish | 23.5 | | ResNet50 | FReLU | 22.4 | | ShuffleNetV2 0.5x | ReLU | 39.6 | | ShuffleNetV2 0.5x | PReLU | 39.1 | | ShuffleNetV2 0.5x | Swish | 38.7 | | ShuffleNetV2 0.5x | FReLU | 37.1 |

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.