内涵：caffe踩过的一些坑

1、caffe.io.load_image()与cv2.imread()的区别与联系

from __future__ import division
a=caffe.io.load_image("1.jpg")
b=cv2.imread("1.jpg")

则a=b/255

2、

transformed_image = self.transformer.preprocess('data', image)
self.net.blobs['data'].data[...] = transformed_image

用datetime.datetime.now()测了一下caffe中这两句话的耗时，我的天，20几个毫秒，抵得上前向耗费的时间了。

3、之前一直都是一次前向，一副图片，今天看到了一次前向，一个batch的图片的代码，记录下

bs = len(fnames)  # batch size
in_shape = net.blobs['data'].data.shape
in_shape[0] = bs # set new batch size
net.blobs['data'].reshape(*in_shape)
net.reshape()
for i, f in enumerate(fnames):
    img = Image.open(f)
    # scale all images to 256x256
    img = img.resize((256,256), PIL.Image.ANTIALIAS)
    img = numpy.array(img).astype(numpy.float32)

    transformed_image = transformer.preprocess('data', img)
    #print transformed_image.shape

    # put the image into i-th place in batch
    net.blobs['data'].data[i,:,:,:] = transformed_image   

# after reading all images into batch, forward once:
net.forward()