search

jaanli / variational-autoencoder

Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)
https://jaan.io/what-is-variational-autoencoder-vae-tutorial/
MIT License
1.14k stars 256 forks source link

Graphs for pyTorch version #10

Closed TheodoreGalanos closed 5 years ago

TheodoreGalanos commented 5 years ago

Hello! Thanks for your implementation it was really helpful to try and set it up on my own dataset!

Was wondering if you had a script somewhere that includes the sampling graphs for the pyTorch version, as I feel they were only included in the TF code.

Thanks in advance!

Kind regards, Theodore.

jaanli commented 5 years ago

Thanks Theodore—I'm not sure what you mean by sampling graphs. Can you give me an example or point to the place in the code in the TF version?

TheodoreGalanos commented 5 years ago

@altosaar apologies I think I misphrased it, I meant if there was code for pyTorch that samples and visualizes the prior distribution of the model in order to generate the visualizations that you show in your blog. I hope that's not too much, it's fine if they aren't available!

jaanli commented 5 years ago

Ah I understand—if you need it feel free to write it (it should mirror the tensorflow version; ping me if you get stuck!), and submit a pull request :)