This class implements a layer that concatenates the input blobs along the Depth
dimension.
This layer has no settings.
This layer has no trainable parameters.
The layer accepts an arbitrary number of inputs, each containing a blob with data:
BatchLength
,BatchWidth
,ListSize
,Height
,Width
, andChannels
dimensions must be the same for all inputs.- The
Depth
dimension may vary.
The layer has one output which contains a blob with the result of concatenation. The dimensions of the blob are:
BatchLength
,BatchWidth
,ListSize
,Height
,Width
, andChannels
are equal to the corresponding inputs' dimensions.Depth
is equal to the sum ofDepth
over all the inputs.