Downloads · 30 days
0
reproduced_miwae
clementchadebec/reproduced_miwae
reproduced_miwae 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 Sep 7, 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
- Sep 7, 2022
- Updated
- Sep 7, 2022
- SHA
- 938be9ac
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_miwae")
Reproducibility
This trained model reproduces the results of the official implementation of [1].
| Model | Dataset | Metric | Obtained value | Reference value |
|---|---|---|---|---|
| MIWAE (M=8, K=8) | Dyn. Binarized MNIST | NLL (5000 IS) | 85.09 (0.00) | 84.97 (0.10) |
[1] Rainforth, Tom, et al. "Tighter variational bounds are not necessarily better." International Conference on Machine Learning. PMLR, 2018.
- Library
- pythae
- License
- apache-2.0
- Languages
- en
- Created
- Sep 7, 2022
- Updated
- Sep 7, 2022