HAT icon indicating copy to clipboard operation
HAT copied to clipboard

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

Results 93 HAT issues
Sort by recently updated
recently updated
newest added

Hello! I used your code for the HAT-GAN model and further finetuned the model on my dataset. I converted the resulting `pth` model into `onnx` format. I tried to convert...

![HAT 现在转不了upscayl 模型](https://github.com/XPixelGroup/HAT/assets/6300501/c235862e-98eb-4404-b687-46bfa39e2c72) Error An error occurred in a PyTorch Convert To NCNN node: HAT is not supported for NCNN conversion at this time. Input values: • PyTorch Model: Value...

I want to train HAT-GAT using HAT_GAN_REAL_SRx4.yml and for 'pretrain_network_g' what pretrained model should I use and where i can get it from? please tell me thank you

Currently HAT tries to run on T4 on Replicate – and fails with OOM for images > 400px. Could you please change the GPU being used in Replicate to an...

## Description: While attempting to run the train.py script, I encountered a NameError issue during the validation process, specifically in the nondist_validation method. The problem is raised when the training...

hi, could i ask the difference between HAT_SRx4_ImageNet-pretrain.pth and HAT_SRx4.pth? I couldn't find an introduction for different model versions. Thanks a lot.

I am sure that my GPU and cuda is availiable, why this error happend?

I use the provided HAT_SRx4.pth and Set5 datasets, and run the `python hat/test.py -opt ./options/test/HAT_SRx4.yml` The results are follows: ` 2023-02-15 10:15:58,541 INFO: Loading HAT model from ./experiments/pretrained_models/HAT_SRx4.pth, with param...

Hello,when I train my custom dataset ,it will happens like: ![E4IAYU_8BB VW P{P{CC_6L](https://user-images.githubusercontent.com/67504959/199644833-c99c9dba-b224-49e8-b02d-87b706fcf2db.png) No object named 'HATModel' found in 'model' registry!" how can I slove it.

hi, did someone found the same error? i run the script: python hat/test.py -opt options/test/HAT_SRx4_ImageNet-LR.yml thanks!