deep-learning - Got confused after I extracted weights from Trained caffenet

Question

So basically this are the dimensions of the weights from trained caffenet:

conv1: (96,3,11,11) conv2: (256,48,5,5) conv3:(384,256,3,3) conv4: (384,192,3,3) conv5:(256, 192, 3 , 3)

I am confused that although conv1 gives 96 channels as output why does conv2 only considers 48 while convolution? Am I missing something?

Answer 1

是的，您错过了参数“组”。conv2层中定义的convolution_param如下所示。你可以发现参数组设置为2，因为对卷积层进行分组可以节省gpu内存。

 convolution_param {
 num_output: 256
 pad: 2
 kernel_size: 5
 group: 2
 weight_filler {
  type: "gaussian"
  std: 0.01
 }
 bias_filler {
  type: "constant"
  value: 1
 }