Trouble with quality of results using pretrained model about deepfillv2_pytorch

[csqiangwen]

It is a little weird. This case should be easily handled by this inpainting algorithm.

Have you tried another image?

[wmmin]

I also hava a same problem,use your pretrained model,the result was bad.And I used your code to traing celeba_hq datasets,the results also wsa bad.Why is it happen?

[AlonzoLeeeooo]

Excuse me. My training samples are also poor in quality. (trained for about 125K iterations) Do I need to train it longer? Or the model itself is mistaken?


P.S. The 1st pic is ground truth, the 2nd pic is the result. (Also it was in 256 resolution but the paper said it can reach 512)

[wmnj]

me too

[Tiuuuuu]

me too

[AlonzoLeeeooo]

Excuse me. My training samples are also poor in quality. (trained for about 125K iterations) Do I need to train it longer? Or the model itself is mistaken? P.S. The 1st pic is ground truth, the 2nd pic is the result. (Also it was in 256 resolution but the paper said it can reach 512)

I have tried another PyTorch code implementation of DeepFill-v2 using mmcv and it works. You may refer to it if you are interested.