Why we only support kernel (1,1) for TF conv2d_transpose SAME?

It seems the current conv2d_transpose is not implemented this way. The SAME padding is achieved by

  1. dilatied the input with zeros
  2. padding inputs according to the expected output shape
  3. transpose and convolution. Please refer to the implementation. I guess it is following this, but I am not quiet sure since I haven’t joined this project long time enought.