Newmu/dcgan_code

What does "GpuDnnConvGradI" do in deconv?

jazzsaxmafia opened this issue · 0 comments

Hello, thank you very much for making public this great project.
I was going through your code, and ran into a point that was not quiet clear to me.
in "deconv" functino in lib/ops.py, line 92 and 95, you put the part that calculates gradient wrt input. I checked the counterpart of Torch version, and it was implemented using regular convolution layer there.

Why is this GpuDnnConvGradI used?
Thank you again for this great source code.

-Taeksoo