Ben

@pluviosilla you should be able to just use standard methods like `pip install keras-tqdm`. Just make sure you activate the correct conda environment first. The package is pure python so...

Shouldn't have to make that folder yourself. Run setup.py from wherever you checked out the code and it should create that folder. What errors are you getting? Use `setup.py install`...

I don't see an attachment...

You're on an old version which matched keras 1. Current version works on keras 1 and 2. C:\Anaconda3\envs\aind-dog\lib\site-packages\keras_tqdm-1.0.7-py3.5.egg\keras_tqdm\tqdm_callback.py Version on pypi is 2.0.1 uploaded on 2017-04-08. Not sure how u...

Are you running the Notebook TQDM or the Console TQDM? Console running in Jupyter might do that. Send a screenshot or the notebook if you're still having something weird.

Hi @manuelepalmeri . Might be some issues on tensorflow that I haven't been testing until recently. Just worked through a lot of keras compatibility issues. Some weirdness with batchnormalization in...

Of course! `keras-adversarial` is just a tool for combining multiple `keras` models into a single training function and a single call to the GPU. If you can build the separate...

`simple_gan` is a helper if you're doing something simple. If you're doing something different, build Keras models with all of the inputs and outputs of the right shapes and build...

@JaneyWit No problem. If you have a single GPU call that generates fakes and trains on them you should see a performance boost over generating fakes on the GPU, concatenating...

gfake, greal, dfake and dreal are all discriminator output targets. (gfake, dfake) and (greal, dreal) are the same output tensors and loss functions with different targets, one for generator one...