search

Royalvice / DocDiff

ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.
https://www.aibupt.com/
MIT License
234 stars 24 forks source link

Questions about data #17

Closed wst2333 closed 11 months ago

wst2333 commented 1 year ago

Hi, When I train model on my dataset, I found there is a question. I wonder what the difference between the input and training data. In my view, input is a blurred one and ground truth is a sharp one. So what about the training data？Is it same with ground truth?

Royalvice commented 1 year ago

I'm a bit confused about your explanation. Detailed explanations about the model's training data as well as inputs and outputs are provided in both the code and the original text.