Instructions to use clementchadebec/reproduced_vamp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- pythae
How to use clementchadebec/reproduced_vamp with pythae:
from pythae.models import AutoModel model = AutoModel.load_from_hf_hub("clementchadebec/reproduced_vamp") - Notebooks
- Google Colab
- Kaggle
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_vamp")
Reproducibility
This trained model reproduces the results of Table 1 in [1].
| Model | Dataset | Metric | Obtained value | Reference value |
|---|---|---|---|---|
| VAMP (K=500) | Binary MNIST | NLL (5000 IS) | 85.79 (0.00) | 85.57 |
[1] Jakub Tomczak and Max Welling. Vae with a vampprior. In International Conference on Artificial Intelligence and Statistics, pages 1214–1223. PMLR, 2018.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support