Open CmdQ opened 5 years ago
Is the Tensor type suited to implement an im2col operation? I tried and only succeeded with nested loops—which of course is bad for CUDA.
Tensor
im2col
In the end, I want to arrive at an efficient convolution. Would that be possible with the current API surface?
Is the
Tensortype suited to implement anim2coloperation? I tried and only succeeded with nested loops—which of course is bad for CUDA.In the end, I want to arrive at an efficient convolution. Would that be possible with the current API surface?