search

jingyuanli001 / RFR-Inpainting

The source code for CVPR 2020 accepted paper "Recurrent Feature Reasoning for Image Inpainting"
MIT License
355 stars 76 forks source link

When I can finish the training/fine-tuning process? #2

Closed Toland12 closed 4 years ago

Toland12 commented 4 years ago

Hi, thanks for your shared work. I try to train a new model with some additional masks in Celeba-HQ, and I found there is no STOP ITERS NUMBER for training/fine-tuning process. Could you plz share when I can finish the training/fine-tuning?

jingyuanli001 commented 4 years ago

Hi, thanks for your shared work. I try to train a new model with some additional masks in Celeba-HQ, and I found there is no STOP ITERS NUMBER for training/fine-tuning process. Could you plz share when I can finish the training/fine-tuning?

Thanks for pointing this out, we will update the code to include this. For Celeb-HQ data, you can start finetuning after 350,000 iterations and end training after 600,000 iterations. But this suggestion is only for the case where the batch size is 6 (i.e. 3,600,000 images have passed though the network during training). More iterations are needed for smaller batch size.