关于特征提取时用cv2.imread()和caffe.io.load_image()读图像的差别

如果用cv2。imread()接口读图像，读进来直接是BGR 格式and 0~255

所以不需要再缩放到【0,255】和通道变换【2,1,0】，不需要transformer.set_raw_scale('data',255)和transformer.set_channel_swap('data',(2,1,0)

###################分割线##########################

若是caffe.io.load_image()读进来是RGB格式和0~1(float）

所以在进行特征提取之前要在transformer中设置transformer.set_raw_scale('data',255)(缩放至0~255）

以及transformer.set_channel_swap('data',(2,1,0)(将RGB变换到BGR）

完毕！

调用caffe model进行特征提取 分类

要注意区分image用何种方法读进来，下面的是用cv2读取的

还可以用caffe.io.loadimage方法

#new model
self.model_def = self.QSPath + '/SRC/model/NewModel/deploy.prototxt'
self.model_weights = self.QSPath + '/SRC/model/NewModel/_iter_115000.caffemodel'
self.mean_file= self.QSPath + '/SRC/model/NewModel/mean.npy'
# net
net = caffe.Net(self.model_def,self.model_weights,caffe.TEST)

#transformer
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2,0,1))
transformer.set_mean('data', np.load(self.mean_file).mean(1).mean(1)) # mean ixel
# transformer.set_raw_scale('data', 255)# from [0,1] to [0,255]
# transformer.set_channel_swap('data', (2,1,0))
net.blobs['data'].reshape(1,3,size,size)

return net, transformer

def caffe_predict(self, img, net, transformer):
try:
# transform it and copy it into the net
net.blobs['data'].data[...] = transformer.preprocess('data', img)
# perform classification
net.forward()
feat_vec = net.blobs['loss3/feature1'].data[0]

output = net.forward()
out_prob = output['prob'][0]# prob vector

label = out_prob.argmax()#输出最大概率的那一类
prob = out_prob[label]# the prob value correspoding to the predict catogory
return feat_vec, label

except Exception as e:
print e
return 0