algorithm/pytorch-tutorial
1
0
Fork 0
mirror of https://github.com/yunjey/pytorch-tutorial.git synced 2025-07-05 08:26:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

tutorial updated

Browse Source
This commit is contained in:
yunjey
2017-05-28 20:30:15 +09:00
committed by GitHub
parent 92875f0669
commit f28838931c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tutorials/03-advanced/variational_auto_encoder/README.md
View File

@ -1,4 +1,4 @@
## Variational Auto-Encoder
# Variational Auto-Encoder
[Variational Auto-Encoder(VAE)](https://arxiv.org/abs/1312.6114) is one of the generative model. From a neural network perspective, the only difference between the VAE and the Auto-Encoder(AE) is that the latent vector z in VAE is stochastically sampled. This solves the problem that the AE learns identity mapping and can not have meaningful representations in latent space. In fact, the VAE uses [reparameterization trick](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/variational_auto_encoder/main.py#L40-L44) to enable back propagation without sampling z directly from the mean and variance.
#### VAE loss
@ -21,4 +21,4 @@ $ python main.py
## Results
Real image | Reconstruced image
:-------------------------:|:-------------------------:
![alt text](png/real.png) | ![alt text](png/reconst.png)
![alt text](png/real.png) | ![alt text](png/reconst.png)