search

ispamm / NAF-DPM

NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement
MIT License
34 stars 4 forks source link

Inference single image by using pretrained checkpoints? #5

Open kerberosargos opened 5 months ago

kerberosargos commented 5 months ago

Hello thank you for your great job.

I have a question. is there any way to inference single image by using pretrained checkpoints?

Thank you in advance for your support.

Giordano-Cicchetti commented 3 months ago

Hi, and sorry for the late reply. Thank you for the question. Unfortunately, we have not provided a pipeline for direct inference of a single image. However, you can follow the instructions in the README file to install the dependencies and download the pretrained models. Then you can store the test image in a folder and reference that folder within the configuration file (Binarization/conf.yml or Deblurring/conf.yml) In addition, it is necessary to specify, within the configuration file, MODE=0. Once all the parameters have been set, simply run the command python main.py --config Binarization/conf.yml or python main.py --config Deblurring/conf.yml