原文地址：http://blog.csdn.NET/u014510375/article/details/51704447
最近读到一篇paper非常有意思，他们把caffe里训练好的模型的参数导出来了，然后…弄到了torch里。所以，今天就来看看怎么导出参数吧。 为了简单，这次我选的是LeNet
import numpy as np import scipy.io as sio import caffe def load(): # Load the net caffe.set_mode_cpu() # You may need to train this caffemodel first # There should be script to help you do the training net = caffe.Net(root + 'lenet.prototxt', root + 'lenet_iter_10000.caffemodel',\ caffe.TEST) conv1_w = net.params['conv1'][0].data conv1_b = net.params['conv1'][1].data conv2_w = net.params['conv2'][0].data conv2_b = net.params['conv2'][1].data ip1_w = net.params['ip1'][0].data ip1_b = net.params['ip1'][1].data ip2_w = net.params['ip2'][0].data ip2_b = net.params['ip2'][1].data sio.savemat('conv1_w', {'conv1_w':conv1_w}) sio.savemat('conv1_b', {'conv1_b':conv1_b}) sio.savemat('conv2_w', {'conv2_w':conv2_w}) sio.savemat('conv2_b', {'conv2_b':conv2_b}) sio.savemat('ip1_w', {'ip1_w':ip1_w}) sio.savemat('ip1_b', {'ip1_b':ip1_b}) sio.savemat('ip2_w', {'ip2_w':ip2_w}) sio.savemat('ip2_b', {'ip2_b':ip2_b}) if __name__ == "__main__": # You will need to change this path root = '/Users/yuliangzou/caffe-rc3/examples/mnist/' load() print 'Caffemodel loaded and written to .mat files successfully!' 12345678910111213141516171819202122232425262728293031323334 12345678910111213141516171819202122232425262728293031323334从代码里可以看得很清楚啦，首先导入模型，然后利用net.params就可以获取参数了，另外你也可以利用net.data导出数据进行可视化。当然，在导出参数之前…你必须要跑过一遍，不然你没有这个caffemodel… 最后…要说一下我最近无聊的时候在github上开了个Naive-CNN的项目，就是….把Caffe里的模型参数导出来，用Matlab或者Python写一遍。目前只做了LeNet。欢迎大家也来玩: https://github.com/Yuliang-Zou/Naive-CNN
