Ekta

Thanks for your prompt reply! Your code has same gamma and beta for each of the 'adaptive_resblock' of the [generator](https://github.com/taki0112/MUNIT-Tensorflow/blob/master/MUNIT.py#L138). The original author's code has [different ](https://github.com/NVlabs/MUNIT/blob/master/networks.py#L134)gamma and beta for...

Thanks for your reply! Perhaps I am missing something...here is how I understood it: In the original author code, the [num_adain_params ](https://github.com/NVlabs/MUNIT/blob/master/networks.py#L147)returned by [get_num_adain_params ](https://github.com/NVlabs/MUNIT/blob/master/networks.py#L141)function is 4096. That is, there...

@rococohanna @cyun-404 will add the training code to the repository in the next few weeks. Thanks for your interest!

Thanks @LucasKirsten ! Apologies for the delayed response. Merging after testing.

hi @wenguanwang , please help me understand how to resolve the above issue?

thanks for your response @rdroste ! Will wait for your minimal example. :+1: Makes sense that with a new dataset, there would be work involved with hyper-parameter tuning. For plugging...

thanks @rdroste ! let me give this a try.

+1

Hi @Goutam-Kelam : is this pytorch implementation stable now? Would like to try it. Also, @kevinmcguinness : would you please provide the training prototxt that shows the loss function and...