Skip to content

Navigation Menu

Appearance settings

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

pytorch / vision Public

Notifications You must be signed in to change notification settings
Fork 7.1k
Star 17.1k

Code
Issues 886
Pull requests 241
Actions
Projects 1
Wiki
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Actions
Projects
Wiki
Security
Insights

ROIPool: Support for all datatypes#632

Merged

fmassa merged 13 commits intopytorch:layerspytorch/vision:layersfrom

varunagrawal:roi-pool-bugfixvarunagrawal/vision:roi-pool-bugfixCopy head branch name to clipboard

Oct 18, 2018

Conversation Commits13 (13)Checks Files changed

Merged

ROIPool: Support for all datatypes#632
fmassa merged 13 commits intopytorch:layersfrom
varunagrawal:roi-pool-bugfix

Commits

Commits on Oct 17, 2018

Use of torch7 naming scheme for ROIAlign forward and backward
varunagrawal
committed
use common cuda helpers in ROIAlign
varunagrawal
committed
use .options() in favor of .type() where applicable
varunagrawal
committed
Added tests for forward pass of ROIAlign, as well as more consistent naming scheme for CPU vs CUDA
varunagrawal
committed
working ROIAlign cuda backwards pass
varunagrawal
committed
working ROIAlign backwards pass for CPU
varunagrawal
committed
added relevant headers for ROIAlign backwards
varunagrawal
committed
tests for ROIAlign layer
varunagrawal
committed
replace .type() with .options() for tensor initialization in ROIAlign layers
varunagrawal
committed
support for Half types in ROIAlign
varunagrawal
committed
gradcheck tests for ROIAlign
varunagrawal
committed
updated ROIPool on CPU to work with all datatypes
varunagrawal
committed
updated and cleaned tests for ROI Pooling
varunagrawal
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.