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

PaddleOcrDetector.MaxSize decreased from 2048 to 1536 #42

Merged
merged 1 commit into from
Apr 20, 2023
Merged

PaddleOcrDetector.MaxSize decreased from 2048 to 1536 #42

merged 1 commit into from
Apr 20, 2023

Conversation

n0099
Copy link
Contributor

@n0099 n0099 commented Apr 18, 2023

13b76b5#diff-fe166047fad0e78128ef92aa38f03b583d73fe3a81cdd1057b39676de8418c9aR14
but why?

And I've noticed if providing null(so no downsampling is done) as the MaxSize:

private static Mat MatResize(Mat src, int? maxSize)
{
if (maxSize == null) return src.Clone();

Detecor.Run() will consume several gigabytes of memory before return.

@sdcb sdcb merged commit 5687fb0 into sdcb:master Apr 20, 2023
@sdcb
Copy link
Owner

sdcb commented Apr 20, 2023

thanks

@sdcb
Copy link
Owner

sdcb commented Apr 20, 2023

https://github.com/sdcb/PaddleSharp/commit/13b76b51d9097421bf3819e4cd37e6e2d062d251#diff-fe166047fad0e78128ef92aa38f03b583d73fe3a81cdd1057b39676de8418c9aR14
but why?

Because TensorRT default size suggested 1536

@n0099
Copy link
Contributor Author

n0099 commented Apr 20, 2023

But not everyone is using NVIDIA TensorRT.

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

Successfully merging this pull request may close these issues.

2 participants