Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

Some cleaning and changing default argument from boxlist_nms #429

Merged
merged 7 commits into from
Feb 14, 2019

Conversation

LeviViana
Copy link
Contributor

No description provided.

@facebook-github-bot facebook-github-bot added the CLA Signed Do not delete this pull request or issue due to inactivity. label Feb 13, 2019
Copy link
Contributor

@fmassa fmassa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi,

Thanks for the PR!

I'm ok with the Python changes, I think though that the cuda changes could be improved a bit.
Or, why not just leaving the CUDA file as is for now?


int n_rois = nthreads / channels / pooled_width / pooled_height;
AT_ASSERT(roi_cols == 5)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

given that we only support roi_cols == 5, is there really a point in exposing it to the user?

Copy link
Contributor

@fmassa fmassa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks a lot!

@fmassa fmassa merged commit 327bc29 into facebookresearch:master Feb 14, 2019
Lyears pushed a commit to Lyears/maskrcnn-benchmark that referenced this pull request Jun 28, 2020
…ookresearch#429)

* Adding support to Caffe2 ResNeXt-152-32x8d-FPN-IN5k backbone for Mask R-CNN

* Clean up

* Fixing path_catalogs.py

* Back to old ROIAlign_cpu.cpp file
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
CLA Signed Do not delete this pull request or issue due to inactivity.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants