Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Deformable Convolutions support #635

Closed
vlordier opened this issue Feb 14, 2020 · 3 comments
Closed

Deformable Convolutions support #635

vlordier opened this issue Feb 14, 2020 · 3 comments
Labels
awaiting response Please respond to this issue to provide further clarification (status) feature request Functionality does not currently exist, would need to be created as a new feature (type)

Comments

@vlordier
Copy link

Description

TF and PyTorch gained recently gained Deformable Convolution support

Arxiv papers on Deformable Convolutions

Use cases

  • Having CoreML support for DCNv1 and v2 will enable to process equirectangular images with EquiConv (parametrised Deformable Convolutions) as introduced by Clara Fernandez-Labrador et al. on target (iOS CoreML).
    It will serve as a base for porting other work based on Deformable Convolutions, including 3D Deformable Convolutions)

Additional context

Deformable Convolutions enable to process equirectangular projection of 360 images in a coherent space.
image
@1duo 1duo added the feature request Functionality does not currently exist, would need to be created as a new feature (type) label Feb 14, 2020
@TobyRoseman
Copy link
Collaborator

@vlordier - which specific TensorFlow and PyTorch ops would you like to see supported?

@TobyRoseman TobyRoseman added the awaiting response Please respond to this issue to provide further clarification (status) label Oct 24, 2022
Birch-san pushed a commit to Birch-san/coremltools that referenced this issue Nov 27, 2022
@vishnu-anirudh
trained_betas ignored in some schedulers (apple#635)
3dacbb9 
* correcting the beta value assignment

* updating DDIM and LMSDiscreteFlax schedulers

* bringing back the changes that were lost as part of main branch merge
@TobyRoseman
Copy link
Collaborator

Since we have not heard back here, I'm going to close this issue. If we ever get the requested information, I'll reopen.

@Volutionn
Copy link

Related to #1889

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
awaiting response Please respond to this issue to provide further clarification (status) feature request Functionality does not currently exist, would need to be created as a new feature (type)
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@TobyRoseman @vlordier @1duo @Volutionn