Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ValueError: Trying to share variable discriminator/d_h3_lin/Matrix, but specified shape (8192, 1) and found shape (25088, 1). #178

Closed
MankowitzProjects opened this issue May 25, 2017 · 16 comments · Fixed by #296

Comments

@MankowitzProjects
Copy link

Hi,

When I clone your repo, download the datasets and run the code, this is the error that I get.
The issue comes from the assignment of variable h4 in the discriminator when calling the linear() function.

Any ideas of what the problem might be?

Thanks!

@EnJiang
Copy link

EnJiang commented May 27, 2017

same

@CheungXu
Copy link

me too

@zhanary
Copy link

zhanary commented Jun 2, 2017

I have ever had this error, it is because I didn't type the right input command

@CheungXu
Copy link

CheungXu commented Jun 2, 2017

And it seems that the size of input and output must be the same.(Parameter "input_height", "input_width' and "output_height", "output_width" ). It works as I do so.

@MankowitzProjects
Copy link
Author

Thanks, it was the input command in my case. I tried running it from PyCharm. In the end, I didn't set the train and crop flags in main.py to true...

@EnJiang
Copy link

EnJiang commented Jun 5, 2017

For those who are viewing https://zhuanlan.zhihu.com/p/24767059 and trying to run this repo but ended up getting this error, be aware that code
python main.py --image_size 96 --output_size 48 --dataset anime --is_crop True --is_train True --epoch 300 --input_fname_pattern "*.jpg"
in the article is wrong. Check its comments for right command.

@hscspring
Copy link

这个可以(This command works):
python main.py --input_height 96 --input_width 96 --output_height 48 --output_width 48 --dataset faces --crop --train --epoch 300 --input_fname_pattern "*.jpg"

@chunfengshiliburuni
Copy link

I got samples(training set) those are 8*8. I want to get some pictures which are independent each other not stitching together.
Any advice is welcome .

@awonderfullife
Copy link

Thanks a lot, it works in my computer @hscspring

@ghost
Copy link

ghost commented Mar 9, 2018

@MankowitzProjects and it works~thanks

@bannima
Copy link

bannima commented Dec 22, 2018

thanks a lot! @hscspring

@lzzlxxlsz
Copy link

And there has any size requirements when using own data?height or width?and output height or width?thanks

@tanmaykansal
Copy link

Does anyone got a solution or cause of this error please tell

@989888
Copy link

989888 commented Feb 26, 2022

Does anyone got a solution or cause of this error please tell thank you

@TakenFromMe
Copy link

In fact,the value of input and output must be the same.

@lihh1023
Copy link

lihh1023 commented Oct 30, 2022 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.