search

akanimax / BMSG-GAN

[MSG-GAN] Any body can GAN! Highly stable and robust architecture. Requires little to no hyperparameter tuning. Pytorch Implementation
MIT License
629 stars 105 forks source link

How to quick test for trained model #26

Closed Johnson-yue closed 4 years ago

Johnson-yue commented 4 years ago

Hi, I have train the MSG-GAN model with flower-102 dataset, and I have trained model weight. So, how can I quick test this model to generate same flower from noise ??

Will I write load network and generate code ?? or you have this code but Not show then in ReadMe

Would you update ReadMe about how to test ?? this is better for use, thank you

akanimax commented 4 years ago

@Johnson-yue,

You can use the demo.py for this. Hope this helps.

Best regards, @akanimax

Johnson-yue commented 4 years ago

Thank，I try it later