Is padding implemented in the layers ?

[manjunaths]

Hello,
Is padding implemented in the ConvolutionLayer and other calls ?

Is there an example that demonstrates this ?

Thanks.

[bchandle]

I just added an example here:

https://github.com/hpe-cct/cct-nn/blob/master/src/test/scala/toolkit/neuralnetwork/examples/AlexNet.scala

The border argument on ConvolutionLayer specifies how padding should be handled. The convolution sizes in this example are exactly consistent with the Caffe reference implementation:

https://github.com/BVLC/caffe/blob/master/models/bvlc_alexnet/deploy.prototxt

A BorderValid convolution produces an output with dimensions equal to the input size minus the (kernel size - 1) in each dimension. A BorderZero convolution will zero-pad such that the output has the same dimensions as the input.

If you want a different padding configuration, the ZeroPad function will let you do that. This combination of manual padding and BorderValid convolution is equivalent to BorderZero convolution:

val c1 = ConvolutionLayer(ZeroPad(data, 5), Shape(11, 11), 96, BorderValid, lr, stride = 4, impl = Space)

[manjunaths]

Thank you for this. I will try to run this and check.

[manjunaths]

What is the best way to benchmark this AlexNet network ?