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
Generated image for CoreML is all black #31
Comments
Could you please help me resolve this issue? |
@RahulBhalley it works well on my side. Please, provide more information about your environment to reproduce this issue. |
Thanks for replying @bes-dev! (Mentioning you to notify you.) I muted & changed some code to conquer some Neptune logger related error I mentioned in #30 issue. I made minor changes to Here's my system information (package list is long!): OS: macOS Monterey 12.2
|
I created a virtual environment with Python 3.7.12 and then install all the requirements. I also reverted all the code back to original except for commenting out the logger arguments. Now the package list is as follows:
Pinging you once again @bes-dev because it's really important for me. |
The observations are same as the previous one. Weird, why doesn't conversion work for me? |
I figured out by using your So I'm closing this issue. Thanks for quick response btw and your work too! |
Hi @bes-dev, thanks for your work!
I am actually not able to convert MobileStyleGAN correctly. I am using the following command:
But the generated image is all black. If I replace the synthesis network with the one provided here then the image does get generated fine. Meaning that
MappingNetwork.mlmodel
's parameters are loaded but not ofSynthesisNetwork.mlmodel
. Note that I do download themobilestylegan_ffhq_v2.ckpt
checkpoint and save it in root directory of this repository.The text was updated successfully, but these errors were encountered: