changed nn.Tanh() output layers to nn.Sigmoid() #63
+22
−22
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Had the same issue with the VanillaVAE out-of-the-box when converting first iteration samples to a PIL Image. Commenting to bump this up. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The input image is normalized between 0-1, so the output should be a nn.Sigmoid() layer instead of nn.Tanh(). Note that nn.Tanh() may also work, but using nn.Sigmoid() is more appropriate and will make the learning easier since the network can now only output values between 0-1 every pixel.