hs457681503

Results 4 comments of hs457681503

Hey, how about your test results with pretrained model?

> > 我已经通过运行test_matrics.py > > 并使用作者发布的经过预训练的mobilenet模型在GOPRO数据集上测试了图像， > > 但是我得到PSRN = 26.89和SSIM = 0.814，而不是28.17和0.925。 > > 有没有人获得更高的结果？ > > Why didn't I change the author code, the d-loss that came out...

征好友，交流该项目

> [email protected] qq，457681503，有想交流问题的小伙伴可以加我，一起交流

TypeError: Cannot handle this data type: (1, 1, 12), |u1

> 我刚才也试了使用python2.7运行，效果会比经过我修改后使用python3生成的图片，从直观效果上看会好很多 你好，我也出现了这个问题，请问你是怎么改的代码呢？可以加我吗？qq是 457681503

size mismatch for encoder.weight: copying a param with shape torch.Size([5450, 300]) from checkpoint, the shape in current model is torch.Size([279, 300]).

> I tried "eval_coco.yml" but got the errors below: > size mismatch for encoder.weight: copying a param with shape torch.Size([27297, 300]) from checkpoint, the shape in current model is torch.Size([5450,...