These are chat archives for dmlc/mxnet

24th
Jul 2018
Bob Poekert
@bobpoekert
Jul 24 2018 18:05
calling keras.backend.conv2d with the mxnet backend in a loss function gives me "MXNet Backend: Cannot automatically infer shape for convolution operator.Please provide input shape. Given input shape"
is there some way to manually specify the input shape?