fix conv1d/deconv1d bug with stride more than 1 by lanluo-nvidia · Pull Request #3737 · pytorch/TensorRT

Description

in conv1d/deconv1d,
input_tensor is (N,C,H) ---> (N, C, H, 1)
if stride is 2, once we moved to 2d, it should be (2, 1) not (2, 2)

This bug is only appear when we have a conv1d/deconv1d with stride more than 1

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist:

  • My code follows the style guidelines of this project (You can use the linters)
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas and hacks
  • I have made corresponding changes to the documentation
  • I have added tests to verify my fix or my feature
  • New and existing unit tests pass locally with my changes
  • I have added the relevant labels to my PR in so that relevant reviewers are notified