reproduced_wae / README.md
clementchadebec's picture
Update README.md
f3afc34
metadata
language: en
tags:
  - pythae
  - reproducibility
license: apache-2.0

Downloading this model from the Hub

This model was trained with pythae. It can be downloaded or reloaded using the method load_from_hf_hub

>>> from pythae.models import AutoModel
>>> model = AutoModel.load_from_hf_hub(hf_hub_path="clementchadebec/reproduced_wae")

Reproducibility

This trained model reproduces the results of Table 1 in [1].

Model Dataset Metric Obtained value Reference value
WAE CELEBA 64 FID 56.5 55

[1] Tolstikhin, O Bousquet, S Gelly, and B Schölkopf. Wasserstein auto-encoders. In 6th International Conference on Learning Representations (ICLR 2018), 2018.