Question

我得到VGG改变的网络的输出（这里是3个浮点数的向量）每个东西都可以，但是当我只想得到其他层的输出（例如最后的卷积层conv5_4）而不是最后一个层，输出向量全为零。这是获取输出的python代码：

import sys
import cv2
import numpy as np
sys.path.insert(0, '/home/deep/rahim/caffe-master/python')
import caffe
input_image_file = sys.argv[1]
output_file = sys.argv[2]
model_file = '/home/deep/rahim/PGM/Final/feature/deep/snapshot_iter_355000.caffemodel'
deploy_prototxt = '/home/deep/rahim/PGM/Final/feature/deep/deploy.prototxt'
net = caffe.Net(deploy_prototxt, model_file, caffe.TEST)
layer = 'conv5_4'
transformer = caffe.io.Transformer({'data':       net.blobs['data'].data.shape})
transformer.set_transpose('data', (2,0,1))
transformer.set_raw_scale('data', 255.0)
net.blobs['data'].reshape(1,3,40,40)
img = caffe.io.load_image(input_image_file)
net.blobs['data'].data[...] = transformer.preprocess('data', img)
output = net.forward()
print '%s' %(net.blobs[layer].data[0])

请帮帮我

Answer 1

我将模型从VGG更改为LENET。问题解决了。似乎改变为vgg会导致上述问题。

caffe layer zero output-python

1 个答案: