search

Hangz-nju-cuhk / Rotate-and-Render

Code for Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images (CVPR 2020)
Creative Commons Attribution 4.0 International
489 stars 112 forks source link

Run bash/examples/train.sh, the loss value is incorrect #18

Closed nanfangzhe closed 4 years ago

nanfangzhe commented 4 years ago

Follow the steps in the readme.md file and use your own data set for training. D_Fake and D_Real are always 0, and the generated results are gray images similar to： (epoch: 2, iters: 74, time: 3.480) GAN: 3.844 GAN_Feat: 30.297 VGG: 6.472 D_Fake: 0.000 D_real: 0.000 What changes do I need to make

cLEARLoVE00 commented 4 years ago

Can you tell me how to prepare my own data, I order author's redeme.md, but get error: Namespace object has no attribute "face_vgg"

nanfangzhe commented 4 years ago

in train_options.py，Uncomment the author on line 54 in the file, you can train image

jolt2017 commented 4 years ago

in train_options.py，Uncomment the author on line 54 in the file, you can train image

hello i also got som problems, can i get your wechat number?

jolt2017 commented 4 years ago

Follow the steps in the readme.md file and use your own data set for training. D_Fake and D_Real are always 0, and the generated results are gray images similar to： (epoch: 2, iters: 74, time: 3.480) GAN: 3.844 GAN_Feat: 30.297 VGG: 6.472 D_Fake: 0.000 D_real: 0.000 What changes do I need to make

I got the same question with you, so did u solve it?

jolt2017 commented 4 years ago

I have not found a solution to this problem,if you find a solution,please tell me,thank you … ---Original--- From: "jolt2017"<notifications@github.com> Date: Wed, Aug 12, 2020 12:16 PM To: "Hangz-nju-cuhk/Rotate-and-Render"<Rotate-and-Render@noreply.github.com>; Cc: "Author"<author@noreply.github.com>;"nanfangzhe"<1508632217@qq.com>; Subject: Re: [Hangz-nju-cuhk/Rotate-and-Render] Run bash/examples/train.sh, the loss value is incorrect (#18) Follow the steps in the readme.md file and use your own data set for training. D_Fake and D_Real are always 0, and the generated results are gray images similar to： (epoch: 2, iters: 74, time: 3.480) GAN: 3.844 GAN_Feat: 30.297 VGG: 6.472 D_Fake: 0.000 D_real: 0.000 What changes do I need to make I got the same question with you, so did u solve it? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

i likely found the reason, but i don't know how to solve it...

jolt2017 commented 4 years ago

Great,what do you think is the reason? … ---Original--- From: "jolt2017"<notifications@github.com> Date: Wed, Aug 12, 2020 13:55 PM To: "Hangz-nju-cuhk/Rotate-and-Render"<Rotate-and-Render@noreply.github.com>; Cc: "Author"<author@noreply.github.com>;"nanfangzhe"<1508632217@qq.com>; Subject: Re: [Hangz-nju-cuhk/Rotate-and-Render] Run bash/examples/train.sh, the loss value is incorrect (#18) I have not found a solution to this problem,if you find a solution,please tell me,thank you … ---Original--- From: "jolt2017"<notifications@github.com> Date: Wed, Aug 12, 2020 12:16 PM To: "Hangz-nju-cuhk/Rotate-and-Render"<Rotate-and-Render@noreply.github.com>; Cc: "Author"<author@noreply.github.com>;"nanfangzhe"<1508632217@qq.com>; Subject: Re: [Hangz-nju-cuhk/Rotate-and-Render] Run bash/examples/train.sh, the loss value is incorrect (#18) Follow the steps in the readme.md file and use your own data set for training. D_Fake and D_Real are always 0, and the generated results are gray images similar to： (epoch: 2, iters: 74, time: 3.480) GAN: 3.844 GAN_Feat: 30.297 VGG: 6.472 D_Fake: 0.000 D_real: 0.000 What changes do I need to make I got the same question with you, so did u solve it? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. i likely found the reason, but i don't know how to solve it... — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

so can we communicate by wecat or ...?