pytorch_convNd icon indicating copy to clipboard operation
pytorch_convNd copied to clipboard

Published 20 hours ago • verified publisher icon pvjosue
→

Metadata

Functional N-dimensional convolution in Pytorch, recursively calling convNd until reaching conv3d.

Results 2 pytorch_convNd issues
Sort by recently updated
recently updated
newest added

Getting NaNs... manual initialization required?

5 comment

@pvjosue I tried swapping this in for conv2D and conv3D in a Unet. I am getting the correct shape but all NaNs as output. Do kernel_initializer and bias_initializer need to...

kevinjohncutler avatar kevinjohncutler

Why is transposed convolution faster ?

This is the result of 2D convolution ``` ConvNd time: 6209.3720703125 ConvGT time: 13.088768005371094 convND error: 3.196690840923111e-07 % ConvTransposeNd time: 32.824127197265625 ConvTransposeGT time: 21.486591339111328 convTransposeND error: 4.2337585881568884e-08 % ``` and...

EvergreenTree avatar EvergreenTree

← Metadata

70
Stars
9
Forks
Watchers

Owner

verified publisher icon pvjosue

Metadata

Functional N-dimensional convolution in Pytorch, recursively calling convNd until reaching conv3d.

Back