【Python】【Caffe】五、参数、特征图可视化《python调用caffe模块》

GitHub代码地址：https://github.com/HandsomeHans/Use-Python-to-call-Caffe-module

一、参数可视化

#!/usr/bin/env python2# -*- coding: utf-8 -*-"""Created on Sun Jul 30 22:15:05 2017@author: hans"""import caffeimport numpy as npimport matplotlib.pyplot as pltdef show(data, padsize=1, padval=0):    data = (data - data.min()) / (data.max() - data.min())        n = int(np.ceil(np.sqrt(data.shape[0])))    padding = ((0, n ** 2 - data.shape[0]), (0, padsize), (0, padsize)) + ((0, 0),) * (data.ndim - 3)    data = np.pad(data, padding, mode='constant', constant_values=(padval, padval))        data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])    plt.imshow(data)    plt.axis('off')    plt.show()prototxt='doc/deploy.prototxt'caffe_model='animal_iter_120000.caffemodel'net = caffe.Net(prototxt,caffe_model,caffe.TEST)for name, param_blob in net.params.items():#查看各层参数规模    print name + '\t' + str(param_blob[0].data.shape), str(param_blob[1].data.shape)conv1_param=net.params['conv1'][0].data  #提取参数w, 参数维度为(n, k, h, w)show(conv1_param.transpose(0, 2, 3, 1)) # 对于第一层卷积层，转换参数维度为(n, h, w, k)#show(conv1_param.reshape(k*n, h, w) # 对于其他层，要用这句代码。

二、特征图可视化

#!/usr/bin/env python2# -*- coding: utf-8 -*-"""Created on Sun Jul 30 22:15:05 2017@author: hans"""import caffeimport numpy as npimport matplotlib.pyplot as pltdef show(data, padsize=1, padval=0): # padsize为特征图间距    data -= data.min()    data /= data.max()        n = int(np.ceil(np.sqrt(data.shape[0])))    padding = ((0, n ** 2 - data.shape[0]), (0, padsize), (0, padsize)) + ((0, 0),) * (data.ndim - 3)    data = np.pad(data, padding, mode='constant', constant_values=(padval, padval))        data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])    plt.imshow(data)    plt.axis('off')prototxt='doc/deploy_lenet.prototxt'caffe_model='models/lenet_iter_10000.caffemodel'mean_file='doc/mnist_mean.npy'im = caffe.io.load_image('doc/3.jpg')im = caffe.io.resize_image(im,(28,28,1))caffe.set_mode_gpu()net = caffe.Net(prototxt,caffe_model,caffe.TEST)transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape}) #data blob 结构（n, k, h, w)transformer.set_transpose('data', (2, 0, 1)) #改变图片维度顺序，(h, w, k) -> (k, h, w)transformer.set_mean('data', np.load(mean_file).mean(1).mean(1))transformer.set_raw_scale('data', 255)# transformer.set_channel_swap('data', (2, 1, 0)) # RGB -> BGRnet.blobs['data'].data[...] = transformer.preprocess('data', im)net.forward()for name,feature in net.blobs.items(): #查看各层特征规模    print name + '\t' + str(feature.data.shape)conv1_data = net.blobs['conv1'].data[0] #提取特征show(conv1_data)prob_data = net.blobs['prob'].data[0] #各类概率分布prob_data.shape = (len(prob_data),)plt.figure()plt.plot(prob_data)

以上内容部分参考自：http://www.cnblogs.com/denny402/p/5105911.html