Skip to content

Revert "Submission for Model ZOO - HAT models"#226

Closed
bartoszptak wants to merge 1 commit intodevelfrom
revert-222-devel
Closed

Revert "Submission for Model ZOO - HAT models"#226
bartoszptak wants to merge 1 commit intodevelfrom
revert-222-devel

Conversation

@bartoszptak
Copy link
Contributor

Reverts #222

  • HAT_SRx4_ImageNet-pretrain.onnx does not work?

Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR reverts the addition of HAT (Hybrid Attention Transformer) models to the Model ZOO documentation due to a reported issue with the HAT_SRx4_ImageNet-pretrain.onnx model not working properly.

Key changes:

  • Removes all 6 HAT model entries (HAT x2/x3/x4 and HAT-L x2/x3/x4) from the Super Resolution Models table

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

|[Hybrid Attention Transformer - Large (HAT-L X2)](https://github.com/ArturWoz/HAT-onnx/releases/download/release/HAT-L_SRx2_ImageNet-pretrain.onnx) |64 | Set it same as input data |X2 |[Model](https://github.com/XPixelGroup/HAT) originally trained by Xiangyu Chen et. al. converted to onnx format | [Image](https://github.com/ArturWoz/HAT-onnx/blob/main/examples/HAT-L_SRx2_ImageNet-pretrain.onnx.png)|
|[Hybrid Attention Transformer - Large (HAT-L X3)](https://github.com/ArturWoz/HAT-onnx/releases/download/release/HAT-L_SRx3_ImageNet-pretrain.onnx) |64 | Set it same as input data |X3 |[Model](https://github.com/XPixelGroup/HAT) originally trained by Xiangyu Chen et. al. converted to onnx format | [Image](https://github.com/ArturWoz/HAT-onnx/blob/main/examples/HAT-L_SRx3_ImageNet-pretrain.onnx.png)|
|[Hybrid Attention Transformer - Large (HAT-L X4)](https://github.com/ArturWoz/HAT-onnx/releases/download/release/HAT-L_SRx4_ImageNet-pretrain.onnx) |64 | Set it same as input data |X4 |[Model](https://github.com/XPixelGroup/HAT) originally trained by Xiangyu Chen et. al. converted to onnx format | [Image](https://github.com/ArturWoz/HAT-onnx/blob/main/examples/HAT-L_SRx4_ImageNet-pretrain.onnx.png)|

Copy link

Copilot AI Dec 23, 2025

Choose a reason for hiding this comment

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

This line introduces inconsistent formatting with a pipe character followed by no content. This should be removed entirely to maintain a clean table structure. The line should simply be blank (no pipe character).

Copilot uses AI. Check for mistakes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants