Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
GuoSong c5dd06bb7a | 2 years ago | |
---|---|---|
configs | 2 years ago | |
debug | 2 years ago | |
doc/paper_reading | 2 years ago | |
quantization | 2 years ago | |
tools | 2 years ago | |
xcom | 2 years ago | |
.gitignore | 2 years ago | |
0309env.yaml | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
requirements.txt | 2 years ago | |
setup.py | 2 years ago |
An easy use Neural Network Compression framework.
Python
Pytorch
yacs
chmod 744 -R ./
pip install -r requirements.txt
python setup.py develop --user
We use YAML format to get configuration. All configs are listed in xcom/core/configs.py. Config files are listed in configs/
Type | Name | Paper |
---|---|---|
Sparsity | Level | |
Channels/Sparsity | L1Norm | PRUNING FILTERS FOR EFFICIENT CONVNETS |
Channels | FPGM | Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration |
Channels | Slim | Learning Efficient Convolutional Networks through Network Slimming |
Channels | APoZ | Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures |
Channels | Taylor | Importance Estimation for Neural Network Pruning |
This project is based on microsoft/nni and facebookresearch/pycls
The entire codebase is under MIT license
神经网络模型压缩框架
Python Jupyter Notebook Cuda C++ Markdown 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》