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 do you generate samples on a trained sagemaker model? #18

Open NoahDolev opened 5 years ago

NoahDolev commented 5 years ago

Hi,

Thanks for a cool implementation. Your notebook ends at fitting - now I am a little bit confused on how to actually generate samples on the fit sagemaker model?

Can you just deploy and predict?

Thanks!

akanimax commented 5 years ago

@NoahDolev, Please check this script => https://github.com/akanimax/BMSG-GAN/blob/master/sourcecode/generate_samples.py Not sure how you could run it on SageMaker. @markstrefford, perhaps you could help.

Thanks!

Best regards, @akanimax

markstrefford commented 5 years ago

Let me look into it. How urgent is this @NoahDolev?

NoahDolev commented 5 years ago

Hi @markstrefford , thanks for taking a look, mate. Not urgent.