GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.
GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.
GitHub is where people build software. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects.
pip install git+https://github.com/openai/sparse_autoencoder.git Code structure Seesae-viewerto see the visualizer code, hosted publiclyhere. Seemodel.pyfor details on the autoencoder model architecture. Seetrain.pyfor autoencoder training code. Seepaths.pyfor more details on the available autoen...
Library of autoencoders for sequential data. Contribute to shobrook/sequitur development by creating an account on GitHub.
Configs are located here: https://github.com/podgorskiy/ALAE/tree/master/configs. By default, it uses one for FFHQ dataset. You can change the config using -c parameter. To run on celeb-hq in 256x256 resolution, run:python interactive_demo.py -c celeba-hq256 ...
GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.
A fully differentiable set autoencoder. Contribute to PaccMann/fdsa development by creating an account on GitHub.
git clone git@github.com:iesl/diora.git cd diora Download the pre-trained model. wget http://diora-naacl-2019.s3.amazonaws.com/diora-checkpoints.zip unzip diora-checkpoints.zip (Optional) Download training data: To reproduce experiments from our NAACL submission, concatenate the data fromSNLI...
Autoencoder for Point Clouds. Contribute to charlesq34/pointnet-autoencoder development by creating an account on GitHub.