Conversation
Basically train 4 but with the additional plot for latent space and some changes to the loss function i think? could have been reverted when i was working on it locally
Changed from plotting 1 dimension to all dimensions, generates n images in the output file for each dimension.
setaremalekiii
requested changes
Feb 5, 2026
setaremalekiii
left a comment
setaremalekiii
left a comment
Owner
There was a problem hiding this comment.
U are most likely clamping a lot of the logvars so when u graph them they're all cmalped to the same value
added the dimension ranking rotations
| mu = self.fc_mu(out) | ||
| logvar = self.fc_logvar(out) | ||
| # another value we can change if needed | ||
| logvar = torch.clamp(logvar, min=-10, max=10) |
Owner
There was a problem hiding this comment.
Here ur clamping ur logvars. Sorry, didn't mean to double comment on the whole PR, but yes, this line could cause everything to be the same
| os.makedirs(OUT_DIR, exist_ok=True) | ||
|
|
||
| # Load latents | ||
| Z = np.load(LATENTS_PATH) # (N, 64) |
Owner
There was a problem hiding this comment.
u could print the N here to see how many values are unique as well
Updated to load weights. Note that it defaults to my directory so you need to add the directory through --weight <path>
changed default latent size to 32
comment for __init__
2 options, use PCA or endpoint alignment. PCA identifies general direction of the chromosome to get the current angle of the chromosome and finds rotation needed to align to y-axis. Endpoint uses the endpoints to draw a straight line and finds the angle to make that straight line align to the y-axis
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
No description provided.