Need help with ThiNet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.
Roll920

Description

caffe model of ICCV'17 paper - ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression https://arxiv.org/abs/1707.06342

132 Stars 34 Forks 5 Commits 6 Opened issues

Services available

Need anything else?

ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

Pretrained caffe model of ICCV'17 paper:

"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression"

For more details, please see our project page: [ThiNet Project Page]

Code

Caffe Implementation of ThiNet

Models

224x224 center crop validation accuracy on ImageNet, tested on one M40 GPU with batch_size=32.

| Model | Top-1 | Top-5 | #Param. | #FLOPs | f./b. (ms) | | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | | ThiNet-GAP | 67.34% | 87.92% | 8.32M | 9.34B | 71.73/145.51 | | ThiNet-Tiny | 59.34% | 81.97% | 1.32M | 2.01B | 29.51/55.83 |

Note: These two models are trained with different image cropping method, see

trainval.prototxt
for more details.

Citation

If you find this work useful for your research, please cite:

@CONFERENCE{ThiNet_ICCV17,
  author={Jian-Hao Luo, Jianxin Wu, and Weiyao Lin},
  title={ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression},
  booktitle={ICCV},
  year = {2017},
  pages={5058-5066},
}

Contact

Feel free to contact me if you have any question (Jian-Hao Luo [email protected] or [email protected]).

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.