context_encoder_pytorch icon indicating copy to clipboard operation
context_encoder_pytorch copied to clipboard

Pretrained model's result on test images

Open jingyi1997 opened this issue 7 years ago • 0 comments

Hi! I notice that the pretrained model's result on test images is about 15.79 percent for L1 loss while about 5.31 percent for L2 loss. However, the result reported in paper is about 9.37% for L1 Loss while about 1.96 for L2 loss. Could you provide some possible reasons for the difference? Thanks!

jingyi1997 avatar Dec 04 '18 07:12 jingyi1997