/channel-pruning

Channel Pruning for Accelerating Very Deep Neural Networks

Primary LanguagePython

[配置的时候，如果是ubuntu14,里面会有python3.4。这里的caffe必须用python3来make && make py. 在makefile.config里面需要设置python3.4的路径：]

PYTHON_LIBRARIES := boost_python3 python3.4m PYTHON_INCLUDE := /usr/include/python3.4m
/usr/lib/python3/dist-packages/numpy/core/include

[在配置caffe环境前面，应该吧所有的protobuf都省略，在最开始自己安装最新的protobuf，如果不是最新的protoc，后面便宜的pycaffe始终运行不起，具体安装方式就是clone github上的protobuf，按上面的命令来安装这个库]

[但是可能发现没有相关哦路径，这个时候，sudo apt-get install python3-pip 就会生成相关的路径，接下来，安装哦一切包都用pip3来装]

用pip3之前也应该pip3 install --upgrade pip来升级pip3命令 用pip3的时候，可以在命令后面加  -i https:// 的国内源，来加快下载速度.(注意，现在国内源都是https！)

有可能会提示没有tkinter的东西 ： 安装 ： sudo apt-get install python3-tk

pip/pip3国内源： 新版ubuntu要求使用https源，要注意。 清华：https://pypi.tuna.tsinghua.edu.cn/simple 阿里云：http://mirrors.aliyun.com/pypi/simple/ **科技大学 https://pypi.mirrors.ustc.edu.cn/simple/ 华中理工大学：http://pypi.hustunique.com/ 山东理工大学：http://pypi.sdutlinux.org/ 豆瓣：http://pypi.douban.com/simple/ 临时使用： 可以在使用pip的时候加参数-i https://pypi.tuna.tsinghua.edu.cn/simple

Channel Pruning for Accelerating Very Deep Neural Networks

ICCV 2017, by Yihui He, Xiangyu Zhang and Jian Sun

In this repository, we released code for the following models:

model Speed-up Accuracy
VGG-16 channel pruning 5x 88.1 (Top-5), 67.8 (Top-1)
VGG-16 3C1 4x 89.9 (Top-5), 70.6 (Top-1)
ResNet-50 2x 90.8 (Top-5), 72.3 (Top-1)
faster RCNN 2x 36.7 (AP@.50:.05:.95)
faster RCNN 4x 35.1 (AP@.50:.05:.95)
1 3C method combined spatial decomposition (Speeding up Convolutional Neural Networks with Low Rank Expansions) and channel decomposition (Accelerating Very Deep Convolutional Networks for Classification and Detection) (mentioned in 4.1.2)
i2 i1
Structured simplification methods Channel pruning (d)

Citation

If you find the code useful in your research, please consider citing:

@InProceedings{He_2017_ICCV,
author = {He, Yihui and Zhang, Xiangyu and Sun, Jian},
title = {Channel Pruning for Accelerating Very Deep Neural Networks},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}

Contents

  1. Requirements
  2. Installation
  3. Channel Pruning and finetuning
  4. Pruned models for download
  5. Pruning faster RCNN
  6. FAQ

requirements

  1. Python3 packages you might not have: scipy, sklearn, easydict, use sudo pip3 install to install.
  2. For finetuning with 128 batch size, 4 GPUs (~11G of memory)

Installation (sufficient for the demo)

  1. Clone the repository

    # Make sure to clone with --recursive
git clone --recursive https://github.com/yihui-he/channel-pruning.git

  2. Build my Caffe fork (which support bicubic interpolation and resizing image shorter side to 256 then crop to 224x224)

    cd caffe

# If you're experienced with Caffe and have all of the requirements installed, then simply do:
make all -j8 && make pycaffe
# Or follow the Caffe installation instructions here:
# http://caffe.berkeleyvision.org/installation.html

# you might need to add pycaffe to PYTHONPATH, if you've already had a caffe before

  3. Download ImageNet classification dataset http://www.image-net.org/download-images

  4. Specify imagenet source path in temp/vgg.prototxt (line 12 and 36)

Channel Pruning

For fast testing, you can directly download pruned model. See next section

  1. Download the original VGG-16 model http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel
    move it to temp/vgg.caffemodel (or create a softlink instead)

  2. Start Channel Pruning

    python3 train.py -action c3 -caffe [GPU0]
# or log it with ./run.sh python3 train.py -action c3 -caffe [GPU0]
# replace [GPU0] with actual GPU device like 0,1 or 2

  3. Combine some factorized layers for further compression, and calculate the acceleration ratio. Replace the ImageData layer of temp/cb_3c_3C4x_mem_bn_vgg.prototxt with temp/vgg.prototxt's

    ./combine.sh | xargs ./calflop.sh

  4. Finetuning

    caffe train -solver temp/solver.prototxt -weights temp/cb_3c_vgg.caffemodel -gpu [GPU0,GPU1,GPU2,GPU3]
# replace [GPU0,GPU1,GPU2,GPU3] with actual GPU device like 0,1,2,3

  5. Testing

    Though testing is done while finetuning, you can test anytime with:

    caffe test -model path/to/prototxt -weights path/to/caffemodel -iterations 5000 -gpu [GPU0]
# replace [GPU0] with actual GPU device like 0,1 or 2

Pruned models (for download)

For fast testing, you can directly download pruned model from release: VGG-16 3C 4X, VGG-16 5X, ResNet-50 2X. Or follow Baidu Yun Download link

Test with:

caffe test -model channel_pruning_VGG-16_3C4x.prototxt -weights channel_pruning_VGG-16_3C4x.caffemodel -iterations 5000 -gpu [GPU0]
# replace [GPU0] with actual GPU device like 0,1 or 2

Pruning faster RCNN

For fast testing, you can directly download pruned model from release
Or you can:

  1. clone my py-faster-rcnn repo: https://github.com/yihui-he/py-faster-rcnn
  2. use the pruned models from this repo to train faster RCNN 2X, 4X, solver prototxts are in https://github.com/yihui-he/py-faster-rcnn/tree/master/models/pascal_voc

FAQ

You can find answers of some commonly asked questions in our Github wiki, or just create a new issue