Uploading SVAE in clementchadebec/reproduced_svae

README.md

@@ -2,21 +2,12 @@
 language: en
 tags:
 - pythae
-- reproducibility
 license: apache-2.0
 ---
 
+### Downloading this model from the Hub
 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_svae")
+>>> model = AutoModel.load_from_hf_hub(hf_hub_path="your_hf_username/repo_name")
 ```
-
-## Reproducibility
-This trained model reproduces the results of Table 1 in [1].
-
-| Model | Dataset | Metric | Obtained value | Reference value |
-|:---:|:---:|:---:|:---:|:---:|
-| SVAE | Dyn. Binarized MNIST | NLL (500 IS) | 93.27 (0.69) | 93.16 (0.31) |
-
-[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.

decoder.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09242b1de07ffe3da265bc976462d66d7cce37df843fd3a2ee011660d5610d4
-size 949607
+oid sha256:e21c1b588f00114f1351ac17d5b92b5d41a54594d9f1f7cd7eedf2c9afdbd5f7
+size 949605

encoder.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d6afb3966a90ce05cd4a22788c28eb32dc6580ca5e5e392e4213cbd5e1cffb
-size 947600
+oid sha256:9ac24b7f6f3251b1d59aac762d2795e11ceedccee0585c742b2009260ddd7e57
+size 947603

environment.json

@@ -1 +1 @@
-{"name": "EnvironmentConfig", "python_version": "3.7"}
+{"name": "EnvironmentConfig", "python_version": "3.8"}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5224bd4270b1e3d9c3ca01a853fa21665cc9751fede894827d28872aee48e736
-size 1890235
+oid sha256:c1045f911cd91cb5b131d4f8d22c096af345e22e2df7959f26d9648bc9df98d7
+size 1890427