Definition of a U net model using pytorch#1328
Definition of a U net model using pytorch#1328karlo-con-k wants to merge 6 commits intopytorch:mainfrom
Conversation
… evaluation. In particular to training a U-Net model.
|
Hi @karlo-con-k! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
✅ Deploy Preview for pytorch-examples-preview canceled.
|
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
|
Hi! 👋 The automated workflows in this PR are currently pending approval and appear to have been canceled (e.g., Netlify preview). Just wanted to confirm if there's anything I need to update on my end, or if a maintainer could approve the workflows when available. Thank you! |
|
Apologies @karlo-con-k it's no longer a priority for me to be reviewing new model submissions in examples/ - I'd rather ensure the existing set is high quality so would be happier accepting PRs for that |
3 participants
Summary
This pull request introduces the implementation of the U-Net model for image segmentation tasks (using the paper 'U-Net: Convolutional Networks for Biomedical Image Segmentation' as reference), including:
A base ModelUNet class with a flexible architecture for different input sizes.
A derived modeluNet class for smaller input sizes, with additional functionality to return intermediate outputs from the downsampling layers.