reproduced_vae / README.md
clementchadebec's picture
Update README.md
09ee598
---
language: en
tags:
- pythae
- reproducibility
library_name: pythae
license: apache-2.0
---
This model was trained with pythae. It can be downloaded or reloaded using the method `load_from_hf_hub`
```python
>>> from pythae.models import AutoModel
>>> model = AutoModel.load_from_hf_hub(hf_hub_path="clementchadebec/reproduced_vae")
```
## Reproducibility
This trained model reproduces the results of the VAE used in Table 1 in [1].
| Model | Dataset | Metric | Obtained value | Reference value |
|:---:|:---:|:---:|:---:|:---:|
| VAE | Binary MNIST | NLL (200 IS) | 89.78 (0.01) | 89.9 |
[1] Danilo Rezende and Shakir Mohamed. Variational inference with normalizing flows. In International Conference on Machine Learning, pages 1530–1538. PMLR, 2015