Didrik Nielsen

Hi, I'd say the simplest would be to start from e.g. this example: https://github.com/didriknielsen/survae_flows/blob/master/examples/mnist_vae.py and add some bijective transformations after the VAE on line 50 (the layers are specified from...

Hi again, In theory, the layer might become non-invertible, but it will be very unlikely to happen (won't really happen in practice). If you get an error I would suspect...

Hey! Thanks! I'd be happy to share the pre-trained models. Do you know of any good sites for sharing large files publicly? Each model is ~1GB.

Thanks for the suggestions! I will try GitHub release. I'm a bit busy for the moment, but I will release the weights early next week.

Released the weights now! https://github.com/didriknielsen/survae_flows/releases/tag/v1.0.0

That is a good question. I'm not sure what the best source is currently. It seems available as a torrent here, which might be the best as long as there...

Hi, thanks for your question! This is the number of dimensions in your data. By default, this layer applies the abs transformation to every element in the data, hence you...

Hi, Thanks for your interest! This is a good idea, I will see if I can find time to write an introductory tutorial soon :-)

Hey! As mentioned before, if you want to map between x and z, you can do this simply using: ```python # x to z: for t in flow.transforms: x, _...

> The issue is in the `Conv1x1` module. the calculation of `torch.slogdet` is much slower on GPU than CPU Hi, Thanks! This is gold. I tried on my computer I...