#加載必要的庫
import numpy as np import matplotlib.pyplot as plt %matplotlib inline import sys,os,caffe 

#設置當前目錄，判斷模型是否訓練好
caffe_root = '/home/bnu/caffe/' sys.path.insert(0, caffe_root + 'python') os.chdir(caffe_root) if not os.path.isfile(caffe_root + 'examples/cifar10/cifar10_quick_iter_4000.caffemodel'): print("caffemodel is not exist...") 

#利用提前訓練好的模型，設置測試網絡
caffe.set_mode_gpu() net = caffe.Net(caffe_root + 'examples/cifar10/cifar10_quick.prototxt', caffe_root + 'examples/cifar10/cifar10_quick_iter_4000.caffemodel', caffe.TEST) 

net.blobs['data'].data.shape 

(1, 3, 32, 32)

#加載測試圖片，並顯示
im = caffe.io.load_image('examples/images/32.jpg') print im.shape plt.imshow(im) plt.axis('off') 

(32, 32, 3)

(-0.5, 31.5, 31.5, -0.5)

#　編寫一個函數，將二進制的均值轉換為python的均值
def convert_mean(binMean,npyMean): blob = caffe.proto.caffe_pb2.BlobProto() bin_mean = open(binMean, 'rb' ).read() blob.ParseFromString(bin_mean) arr = np.array( caffe.io.blobproto_to_array(blob) ) npy_mean = arr[0] np.save(npyMean, npy_mean ) binMean=caffe_root+'examples/cifar10/mean.binaryproto' npyMean=caffe_root+'examples/cifar10/mean.npy' convert_mean(binMean,npyMean) 

#將圖片載入blob中,並減去均值
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape}) transformer.set_transpose('data', (2,0,1)) transformer.set_mean('data', np.load(npyMean).mean(1).mean(1)) # 減去均值 transformer.set_raw_scale('data', 255) transformer.set_channel_swap('data', (2,1,0)) net.blobs['data'].data[...] = transformer.preprocess('data',im) inputData=net.blobs['data'].data 

#顯示減去均值前后的數據
plt.figure() plt.subplot(1,2,1),plt.title("origin") plt.imshow(im) plt.axis('off') plt.subplot(1,2,2),plt.title("subtract mean") plt.imshow(transformer.deprocess('data', inputData[0])) plt.axis('off') 

(-0.5, 31.5, 31.5, -0.5)

#運行測試模型，並顯示各層數據信息
net.forward() [(k, v.data.shape) for k, v in net.blobs.items()] 

[('data', (1, 3, 32, 32)),
 ('conv1', (1, 32, 32, 32)),
 ('pool1', (1, 32, 16, 16)),
 ('conv2', (1, 32, 16, 16)),
 ('pool2', (1, 32, 8, 8)),
 ('conv3', (1, 64, 8, 8)),
 ('pool3', (1, 64, 4, 4)),
 ('ip1', (1, 64)),
 ('ip2', (1, 10)),
 ('prob', (1, 10))]

#顯示各層的參數信息
[(k, v[0].data.shape) for k, v in net.params.items()] 

[('conv1', (32, 3, 5, 5)),
 ('conv2', (32, 32, 5, 5)),
 ('conv3', (64, 32, 5, 5)),
 ('ip1', (64, 1024)),
 ('ip2', (10, 64))]

#　編寫一個函數，用於顯示各層數據
def show_data(data, padsize=1, padval=0): data -= data.min() data /= data.max() # force the number of filters to be square 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)) # tile the filters into an image 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.figure() plt.imshow(data,cmap='gray') plt.axis('off') plt.rcParams['figure.figsize'] = (8, 8) plt.rcParams['image.interpolation'] = 'nearest' plt.rcParams['image.cmap'] = 'gray' 

#顯示第一個卷積層的輸出數據和權值（filter）
show_data(net.blobs['conv1'].data[0]) print net.blobs['conv1'].data.shape show_data(net.params['conv1'][0].data.reshape(32*3,5,5)) print net.params['conv1'][0].data.shape 

(1, 32, 32, 32)
(32, 3, 5, 5)

#顯示第一次pooling后的輸出數據
show_data(net.blobs['pool1'].data[0]) net.blobs['pool1'].data.shape 

(1, 32, 16, 16)

#顯示第二次卷積后的輸出數據以及相應的權值（filter）
show_data(net.blobs['conv2'].data[0],padval=0.5) print net.blobs['conv2'].data.shape show_data(net.params['conv2'][0].data.reshape(32**2,5,5)) print net.params['conv2'][0].data.shape 

(1, 32, 16, 16)
(32, 32, 5, 5)

#顯示第三次卷積后的輸出數據以及相應的權值（filter）,取前１024個進行顯示
show_data(net.blobs['conv3'].data[0],padval=0.5) print net.blobs['conv3'].data.shape show_data(net.params['conv3'][0].data.reshape(64*32,5,5)[:1024]) print net.params['conv3'][0].data.shape 

(1, 64, 8, 8)
(64, 32, 5, 5)

#顯示第三次池化后的輸出數據
show_data(net.blobs['pool3'].data[0],padval=0.2) print net.blobs['pool3'].data.shape 

(1, 64, 4, 4)

# 最后一層輸入屬於某個類的概率
feat = net.blobs['prob'].data[0] print feat plt.plot(feat.flat) 

[  5.21440245e-03   1.58397834e-05   3.71246301e-02   2.28459597e-01
   1.08315737e-03   7.17785358e-01   1.91939052e-03   7.67927198e-03
   6.13298907e-04   1.05107691e-04]

[<matplotlib.lines.Line2D at 0x7f3d882b00d0>]

從輸入的結果和圖示來看，最大的概率是7.17785358e-01，屬於第５類（標號從０開始）。與cifar10中的10種類型名稱進行對比：

airplane、automobile、bird、cat、deer、dog、frog、horse、ship、truck

根據測試結果，判斷為dog。 測試無誤！

 

原文見：http://www.cnblogs.com/denny402/p/5105911.html