clementchadebec
/

reproduced_ciwae

reproducibility

Model card Files Files and versions

clementchadebec commited on Sep 7, 2022

Commit

625e7e6

·

1 Parent(s): 0a5809d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,6 +17,6 @@ This trained model reproduces the results of the official implementation of [1].
 | Model | Dataset | Metric | Obtained value | Reference value |
 |:---:|:---:|:---:|:---:|:---:|
-| CIWAE (beta=0.05) | Dyn. Binarized MNIST | NLL (5000 IS) | 84.79 (0.00) | 84.57 (0.09) |
 [1] Rainforth, Tom, et al. "Tighter variational bounds are not necessarily better." International Conference on Machine Learning. PMLR, 2018.

 | Model | Dataset | Metric | Obtained value | Reference value |
 |:---:|:---:|:---:|:---:|:---:|
+| CIWAE (beta=0.05) | Dyn. Binarized MNIST | NLL (5000 IS) | 84.74 (0.01) | 84.57 (0.09) |
 [1] Rainforth, Tom, et al. "Tighter variational bounds are not necessarily better." International Conference on Machine Learning. PMLR, 2018.