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

Bad testing result #48

Closed adkAurora closed 2 years ago

adkAurora commented 3 years ago

i have trained RFRNet on my own dataset, i got great trainng result ,but the test result is terrible, the difference between trainset and testset is different mask , could u help me?

image

jingyuanli001 commented 3 years ago

Have you fine-tuned the model? The testing results might be distorted due to insufficient fine-tuning. Besides, the format of the testing mask might also be important, please ensure that the mask has only 0 and 1 in it.