How to reshape a blob in Caffe?

Question

How to reshape a blob of the shape N x C x H x W to N x 1 x (C*H) x W in Caffe?

I want to make a convolution layer the weights of which are identical between channels.

One way I come up with is to reshape the bottom blob of the shape N x C x H x W to N x 1 x (C*H) x W and place a convolution layer upon it. But I just don't know how to reshape a blob.

Please help me out, thank you.

Answer 1

As pointed by whjxnyzh, you can use "Reshape" layer. Caffe is quite flexible in the way it allows you to define the output shape.
See the declaration of reshap_param in caffe.proto`:

// Specify the output dimensions. If some of the dimensions are set to 0,
// the corresponding dimension from the bottom layer is used (unchanged).
// Exactly one dimension may be set to -1, in which case its value is
// inferred from the count of the bottom blob and the remaining dimensions.

In your case I guess you'll have a layer like this:

layer {
  name: "my_reshape"
  type: "Reshape"
  bottom: "in"
  top: "reshaped_in"
  reshape_param { shape: {dim: 0 dim: 1 dim: -1 dim: 0 } }
}

See also on caffe.help.

Answer 2

Caffe now has a reshapeLayer for you. http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ReshapeLayer.html

Answer 3

If I understand your final objective right, Caffe's convolution layer already can do multiple input-output convolution with common/shared filters like:

layer {
  name:   "conv"
  type:   "Convolution"
  bottom: "in1"
  bottom: "in2"
  bottom: "in3"
  top:    "out1"
  top:    "out2"
  top:    "out3"
  convolution_param {
    num_output : 10  #the same 10 filters for all 3 inputs
    kernel_size: 3        
  }
}

Assuming you have all streams split (slice layer can do that), and finally you may merge them if desired with a concat or eltwise layer.

That avoid the needs of reshaping blob, convolved, and then reshaping it back, which might introduce cross-channel interference near the margins.