Commit
•
dffde81
1
Parent(s):
c510dc9
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,21 @@
|
|
| 2 |
language: en
|
| 3 |
tags:
|
| 4 |
- pythae
|
|
|
|
| 5 |
license: apache-2.0
|
| 6 |
---
|
| 7 |
|
| 8 |
-
### Downloading this model from the Hub
|
| 9 |
This model was trained with pythae. It can be downloaded or reloaded using the method `load_from_hf_hub`
|
| 10 |
```python
|
| 11 |
>>> from pythae.models import AutoModel
|
| 12 |
-
>>> model = AutoModel.load_from_hf_hub(hf_hub_path="
|
| 13 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language: en
|
| 3 |
tags:
|
| 4 |
- pythae
|
| 5 |
+
- reproducibility
|
| 6 |
license: apache-2.0
|
| 7 |
---
|
| 8 |
|
|
|
|
| 9 |
This model was trained with pythae. It can be downloaded or reloaded using the method `load_from_hf_hub`
|
| 10 |
```python
|
| 11 |
>>> from pythae.models import AutoModel
|
| 12 |
+
>>> model = AutoModel.load_from_hf_hub(hf_hub_path="clementchadebec/reproduced_svae")
|
| 13 |
```
|
| 14 |
+
|
| 15 |
+
## Reproducibility
|
| 16 |
+
This trained model reproduces the results of Table 1 in [1].
|
| 17 |
+
|
| 18 |
+
| Model | Dataset | Metric | Obtained value | Reference value |
|
| 19 |
+
|:---:|:---:|:---:|:---:|:---:|
|
| 20 |
+
| SVAE | Dyn. Binarized MNIST | NLL (500 IS) | 93.13 (0.01) | 93.16 (0.31) |
|
| 21 |
+
|
| 22 |
+
[1] Tim R Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, and Jakub M Tomczak. Hyperspherical variational auto-encoders. In 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018, pages 856–865. Association For Uncertainty in Artificial Intelligence (AUAI), 2018.
|