Kristian Klemon
Kristian Klemon
Thank you for the reply. I'm currently not 100% satisfied with my proposed approach and hence might a few more changes in the future.
@murnanedaniel you can either use [my fork](https://github.com/kklemon/pytorch-fid) of this repository, but which also hasn't been updated in a while and may no longer work or look for other implementations with...
The reconstructed images will generally have fewer details than the original one as VQ-VAE is essentially lossy compression. Possible options to mitigate this would be indeed for example perceptual losses....
Any news regarding this feature? I tried to use EasyDict in a config but it seems like that all config objects inheriting from dict are casted to actual dicts when...
Adding a `snapshot.json` in the root directory should be sufficient. Also, make sure that you are building the image from scratch. Apart from these suggestions, I would need to take...
I also encountered this problem while trying to run the _Nesting RecurrentSequentials_ demo. Indeed that super call in `RecurrentSequential` looks suspicious and should probably call `RecurrentModel`'s constructor instead of itself,...
Not the original author here, but my specific use case are linear RNNs. These will have an initial hidden state $h_0$ which can be provided as the first token and...
Are there any plans to merge this soon? This feature would be really useful.
Any update on this?
I have implemented this functionality in #540. > Currently the cursor is part of the terminal texture, so updating it would cause the entire scene to be redrawn (quite heavy)....