algorithm/pytorch-tutorial
1
0
Fork 0
mirror of https://github.com/yunjey/pytorch-tutorial.git synced 2025-07-07 18:14:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

fixed typo

Browse Source
This commit is contained in:
Yunjey Choi
2018-01-09 17:28:16 +09:00
committed by GitHub
parent 1ec90fad72
commit 655c6df3ba
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/main.py
View File

@ -37,7 +37,7 @@ class VAE(nn.Module):
nn.Linear(h_dim, image_size), nn.Linear(h_dim, image_size),
nn.Sigmoid()) nn.Sigmoid())
def reparametrize(self, mu, log_var): def reparameterize(self, mu, log_var):
""""z = mean + eps * sigma where eps is sampled from N(0, 1).""" """"z = mean + eps * sigma where eps is sampled from N(0, 1)."""
eps = to_var(torch.randn(mu.size(0), mu.size(1))) eps = to_var(torch.randn(mu.size(0), mu.size(1)))
z = mu + eps * torch.exp(log_var/2) # 2 for convert var to std z = mu + eps * torch.exp(log_var/2) # 2 for convert var to std
@ -46,7 +46,7 @@ class VAE(nn.Module):
def forward(self, x): def forward(self, x):
h = self.encoder(x) h = self.encoder(x)
mu, log_var = torch.chunk(h, 2, dim=1) # mean and log variance. mu, log_var = torch.chunk(h, 2, dim=1) # mean and log variance.
z = self.reparametrize(mu, log_var) z = self.reparameterize(mu, log_var)
out = self.decoder(z) out = self.decoder(z)
return out, mu, log_var return out, mu, log_var