Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Ground truth in forward pass? #9

Open
Constantin771 opened this issue Dec 30, 2020 · 0 comments
Open

Ground truth in forward pass? #9

Constantin771 opened this issue Dec 30, 2020 · 0 comments

Comments

@Constantin771
Copy link

Constantin771 commented Dec 30, 2020

Hello, first of all thank you for the code!
I have a question about the forward pass in the srVAE model:

def forward(self, x, **kwargs):
""" Forward pass through the inference and the generative model. """
# y ~ f(x) (determinist)
y = self.compressed_transoformation(x)
# u ~ q(u| y)
u_q_mean, u_q_logvar = self.q_u(y)
u_q = self.reparameterize(u_q_mean, u_q_logvar)
# z ~ q(z| x, y)
z_q_mean, z_q_logvar = self.q_z(x)
z_q = self.reparameterize(z_q_mean, z_q_logvar)
# x ~ p(x| y, z)
x_logits = self.p_x((y, z_q))
# y ~ p(y| u)
y_logits = self.p_y(u_q)

It looks like p_x gets the ground truth y as input. Should this not be the y that is predicted by p_y instead?

Best regards!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant