Fixed reduced duration of output video bug + scale passed as timestep bug.#96
Merged
hzwer merged 3 commits intohzwer:mainfrom Sep 2, 2024
Merged
Fixed reduced duration of output video bug + scale passed as timestep bug.#96hzwer merged 3 commits intohzwer:mainfrom
hzwer merged 3 commits intohzwer:mainfrom
Conversation
AhmedAhmedEG
changed the title
Owner
|
Hi, I think the inference fps seems to be OK. Because the origin frames will be directly put into write buffer. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The calculation of output video fps was getting performed on the given multiplier, while the inference used a value of (multiplier - 1), causing the video writer to incorrectly interpreting the output video and highly reduces the duration.
Also in the case of ssim > 0.996, the inference gets the scale passed right away without specifying the name of the argument, causing the scale value getting passed as the timestep value, which is a huge problem.
I am not sure how such a big issue is left here...
I have written a full refactor for the video inference script, correcting all the PEP violations and segregating the code into multiple classes for higher readability, I plan to post it here after #23 gets merged.