Interpolate image size such that it never fails #14
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
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Outdated suggestions cannot be applied.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.
Hi. You don't know me. I stumbled on your fork. Thought it was grand. Had a small problem, though.
The image dimensions I was passing through wasn't dividing evenly, so simply scaling by a factor of 2 was causing an off-by one in the dimensions.
This change makes it always match the same image dimensions when resizing. Thought you might want it?
For reference, I'm only using the model definition with my own training loop, and the image sizes I'm passing in is 1080p (1920x1080; wxh)
Fair warning: I haven't trained anything from scratch with these changes.