ljjcoder

Why are your settings not in accordance with the standards of ssl, UDA and SSDA?

2

Thank you for your excellent work. I'm curious why you didn't keep the same settings as before to experiment? For example, in the SSL field, the commonly used data sets...

how to get the trainset on places2?

8

Thank you for your excellent work. In your paper, you introduced how to get 256x256 images from original images on celebA and Paris StreetView. but for places2, how do you...

how to test fid？

6

when I run the command python ./scripts/fid_score.py --path /userhome/inpaint_bord/data/places2_gt_1000/ /userhome/edge-connect-master/checkpoints/results/ (the /userhome/inpaint_bord/data/places2_gt_1000/ contains 1000 really images and /userhome/edge-connect-master/checkpoints/results/ contains 1000 inpainted images), the process is seized up and stopped. the...

some questions about performs

1

it is excellent work! I have some questions about your method. The performance produced by the code is 60.2 and 74.3. I notice that it produced by meta-batch. if i...

question about different version of code.

1

Thanks for your excellent work. I found that the results in cifar100 are different in different versions of paper. I noticed that your code also changed five months ago. I...

replace the unmask regions with Ground Truth

1

@MathiasGruber Thank you very much for sharing your work！I am a little puzzled whether the final output of your test code directly uses the convolution prediction result as the final...

the bad result on rect mask

2

@shepnerd thanks for your excellent work！I notice you release the stroke model on places2，it works well on stoke mask。 but when I finetune the model with rect mask from your...

@crashmoon 感谢您优秀的工作！从您的论文中可以看到，您用了4个生成器逐步补全缺失mask。有一点好奇的是，如果训练的mask和测试的mask不一致，我该融合这四个mask的结果。好比，我用64*64的mask训练，测试时我用64*48的mask测试，那么第一个生成器得到结果，哪些部分是可以保留的，作为第二阶段的输入？

It is a great job! But I have some questions: when I train the the deformation sub-network, it raises a error: File "onlyBasetwoLoss.py", line 18, in from datasets import oneShotUnsuperviseCls...

about seeds

8

thanks for your excellent works! can you give me your seeds on cifar100? （1，2，3，4，5？）