#uncoding:utf-8 # set up Python environment: numpy for numerical routines, and matplotlib for plotting import numpy as np import matplotlib.pyplot as plt # display plots in this notebook #%matplotlib inline # set display defaults plt.rcParams['figure.figsize'] = (10, 10) # large images plt.rcParams['image.interpolation'] = 'nearest' # don't interpolate: show square pixels plt.rcParams['image.cmap'] = 'gray' # use # The caffe module needs to be on the Python path; # we'll add it here explicitly. import sys caffe_root = '/home/sea/caffe/' # this file should be run from {caffe_root}/examples (otherwise change this line) sys.path.insert(0, caffe_root + 'python') import caffe # If you get "No module named _caffe", either you have no import os if os.path.isfile(caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'): print 'CaffeNet found.' else: print 'Downloading pre-trained CaffeNet model...' #!../scripts/download_model_binary.py ../models/bvlc_reference_caffenet caffe.set_mode_cpu() model_def = caffe_root + 'models/bvlc_reference_caffenet/deploy.prototxt' model_weights = caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel' print "定义网络结构：" net = caffe.Net(model_def, # defines the structure of the model model_weights, # contains the trained weights caffe.TEST) # use test mode (e.g., don't perform dropout) print "加载平均图：" # load the mean ImageNet image (as distributed with Caffe) for subtraction mu = np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy') mu = mu.mean(1).mean(1) # average over pixels to obtain the mean (BGR) pixel values print 'mean-subtracted values:', zip('BGR', mu) print "初始化转换输入数据格式转换器：" # create transformer for the input called 'data' transformer = caffe.io.Transformer({ 'data': net.blobs['data'].data.shape}) print "设置输入数据格式转换器参数：" transformer.set_transpose('data', (2,0,1)) # move image channels to outermost dimension transformer.set_mean('data', mu) # subtract the dataset-mean value in each channel transformer.set_raw_scale('data', 255) # rescale from [0, 1] to [0, 255] transformer.set_channel_swap('data', (2,1,0)) # swap channels from RGB to BGR print "设置输入数据格式：" # set the size of the input (we can skip this if we're happy # with the default; we can also change it later, e.g., for different batch sizes) net.blobs['data'].reshape(50, # batch size 3, # 3-channel (BGR) images 227, 227) # image size is 227x227 print "加载猫：" image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg') transformed_image = transformer.preprocess('data', image) plt.imshow(image) plt.show() print "将猫加载到内存：" # copy the image data into the memory allocated for the net net.blobs['data'].data[...] = transformed_image ### perform classification output = net.forward() output_prob = output['prob'][0] # the output probability vector for the first image in the batch print 'predicted class is:', output_prob.argmax() print "加载图像集合标签：" # load ImageNet labels labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt' if not os.path.exists(labels_file): print "/data/ilsvrc12/get......sh" #!../data/ilsvrc12/get_ilsvrc_aux.sh labels = np.loadtxt(labels_file, str, delimiter=' ') print 'output label:', labels[output_prob.argmax()] # sort top five predictions from softmax output top_inds = output_prob.argsort()[::-1][:5] # reverse sort and take five largest items print "打印分类结果：概率和标签：" print 'probabilities and labels:' zip(output_prob[top_inds], labels[top_inds]) #%timeit net.forward() print "切换到gpu模式：" caffe.set_device(0) # if we have multiple GPUs, pick the first one caffe.set_mode_gpu() net.forward() # run once before timing to set up memory #%timeit net.forward() # for each layer, show the output shape for layer_name, blob in net.blobs.iteritems(): print layer_name + ' ' + str(blob.data.shape) for layer_name, param in net.params.iteritems(): print layer_name + ' ' + str(param[0].data.shape), str(param[1].data.shape) print "定义可视化直方图的函数：" def vis_square(data): """Take an array of shape (n, height, width) or (n, height, width, 3) and visualize each (height, width) thing in a grid of size approx. sqrt(n) by sqrt(n)""" # normalize data for display data = (data - data.min()) / (data.max() - data.min()) # 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, 1), (0, 1)) # add some space between filters + ((0, 0),) * (data.ndim - 3)) # don't pad the last dimension (if there is one) data = np.pad(data, padding, mode='constant', constant_values=1) # pad with ones (white) # 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.imshow(data); plt.axis('off') # plt.show() print "显示：直方图--conv1" # the parameters are a list of [weights, biases] filters = net.params['conv1'][0].data vis_square(filters.transpose(0, 2, 3, 1)) # plt.show() print "显示：直方图：conv5" feat = net.blobs['conv1'].data[0, :36] vis_square(feat) # plt.show() print "显示：直方图, pool5" feat = net.blobs['pool5'].data[0] vis_square(feat) # plt.show() print "显示：hist -fc6 " feat = net.blobs['fc6'].data[0] plt.subplot(2, 1, 1) plt.plot(feat.flat) plt.subplot(2, 1, 2) _ = plt.hist(feat.flat[feat.flat > 0], bins=100) # plt.show() print "显示：t--prob" t = net.blobs['prob'].data[0] plt.figure(figsize=(15, 3)) # plt.plot(feat.flat) # plt.show() # download an image #my_image_url = "..." # paste your URL here # for example: # my_image_url = "https://upload.wikimedia.org/wikipedia/commons/b/be/Orang_Utan%2C_Semenggok_Forest_Reserve%2C_Sarawak%2C_Borneo%2C_Malaysia.JPG" #!wget -O image.jpg $my_image_url print "加载图像" # transform it and copy it into the net #image = caffe.io.load_image('/home/sea/shareVm/images/monkey/2.jpg') image=caffe.io.load_image('/home/sea/Downloads/555eae4532988a6dc175031eed969fc0.jpg') net.blobs['data'].data[...] = transformer.preprocess('data', image) # perform classification net.forward() # obtain the output probabilities output_prob = net.blobs['prob'].data[0] # print "output_prob = ", output_prob # sort top five predictions from softmax output top_inds = output_prob.argsort()[::-1][:5] print "top_inds = ", top_inds print "显示：图像" plt.imshow(image) plt.show() print "打印分类结果：" print 'probabilities and labels:' zd = zip(output_prob[top_inds], labels[top_inds]) print "结果： ", zd for e in zd: print e #copy------------------------------------------------------------------------------- output_prob = output['prob'][0] # the output probability vector for the first image in the batch print 'predicted class is:', output_prob.argmax() indd = output_prob.argmax() top_inds = indd print "加载图像集合标签：" print (output_prob[top_inds], labels[top_inds])