一.设置
首先设置Python, numpy, and matplotlib
# 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 grayscale output rather than a (potentially misleading) color heatmap
然后加载caffe
# The caffe module needs to be on the Python path;
# we'll add it here explicitly.
import sys
caffe_root = '../' # 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 not built pycaffe or you have the wrong path.
下载caffeNet(之所以使用caffeNet是为了方便演示)
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
CaffeNet found.
二.加载网络并设置图像预处理
加载网络并设置caffe为cpu模式
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'
net = caffe.Net(model_def, model_weights, caffe.TEST)
# 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)
# create transformer for the input called 'data'
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
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))
三.分类
net.blobs['data'].reshape(50, # batch size
3, # 3-channel (BGR) images
227, 227) # image size is 227x227
虽然仅仅对一张图片进行分类,但仍设置batch size为50
image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg')
transformed_image = transformer.preprocess('data', image)
plt.imshow(image)
此时如果一切正常会显示出以下情景
现在对这张图片进行分类
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()
现在对分类的图片进行检测,看看分类是否正确
# load ImageNet labels
labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt'
if not os.path.exists(labels_file):
!../data/ilsvrc12/get_ilsvrc_aux.sh
labels = np.loadtxt(labels_file, str, delimiter='\t')
print 'output label:', labels[output_prob.argmax()]