search

CVMI-Lab / UHDM

(ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
Apache License 2.0
207 stars 28 forks source link

Training dataset information of mix.pth (hugging face) #25

Open shubhoppo opened 1 year ago

shubhoppo commented 1 year ago

Hi, Thanks for the great work, Could you please specify all the dataset used for training of hugging face model https://huggingface.co/spaces/ECCV2022/Screen_Image_Demoireing/tree/main "mix.pth"

XinYu-Andy commented 1 year ago

Hi, Thanks for the great work, Could you please specify all the dataset used for training of hugging face model https://huggingface.co/spaces/ECCV2022/Screen_Image_Demoireing/tree/main "mix.pth"

Sorry for the late reply - my research has shifted away from this area, so I haven't been keeping up with this repo much.

About the demo config: it's pretty straightforward. You'll just need to write a new dataloader that can handle merging and loading multiple datasets. For handling large images, go for cropping, and for the TIP2018 dataset, resize it firstly and then do cropping. All the specific details for these implementations are mentioned in the paper, so you can check them out there. No extra parameter tweaking needed beyond that. Hope this helps!