Downloads · 30 days
0
reproduced_iwae
clementchadebec/reproduced_iwae
reproduced_iwae is a machine learning model from clementchadebec. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pythae. The card lists the license as apache-2.0.
This model was trained with pythae. It can be downloaded or reloaded using the method loadfromhfhub
Access
Public
Updated Aug 19, 2022
Repo size
3.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl1.7 MB · 50%
At a glance
- Library
- pythae
- License
- apache-2.0
- Access
- Public
- Created
- Aug 19, 2022
- Updated
- Aug 19, 2022
- SHA
- 15b2fa08
Model card
From the Hugging Face model README
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_iwae")
Reproducibility
This trained model reproduces the results of Table 1 in [1].
| Model | Dataset | Metric | Obtained value | Reference value |
|---|---|---|---|---|
| IWAE (n_samples=5) | Binary MNIST | NLL (5000 IS) | 87.85 (0.01) | 87.6 |
| IWAE (n_samples=50) | Binary MNIST | NLL (5000 IS) | 86.82 (0.01) | 87.1 |
[1] Burda, Y. et al, Importance Weighted Autoencoders, ArXiv:1509.00519
- Library
- pythae
- License
- apache-2.0
- Languages
- en
- Created
- Aug 19, 2022
- Updated
- Aug 19, 2022