-
Notifications
You must be signed in to change notification settings - Fork 269
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
Getting Less Accuracy on High resolution images #113
Comments
the input resolution is highly influencing the receptive field so that lead
to different "data distribution" when you change the resolution. The
accuracy degradation kind of make sense under current configuration.
…On Sun, Mar 17, 2024 at 10:28 PM Kaustubh-cpu ***@***.***> wrote:
@xuebinqin <https://github.com/xuebinqin> @DengPingFan
<https://github.com/DengPingFan> @PINTO0309 <https://github.com/PINTO0309>
@16673161214 <https://github.com/16673161214>
Hello Authors ,
As i have finetune and trained the model on 1024 Resolution but when i am
trying to do the inference on higher resolution its accuracy directly goes
down to -20% where as at the same time when i resized the image to 1024 and
did the inference then the accuracy is bit good as compared to high
resolution images results
—
Reply to this email directly, view it on GitHub
<#113>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ADSGORPK3TFMM3GMFKUY2QDYYZ3Q3AVCNFSM6AAAAABE243LFKVHI2DSMVQWIX3LMV43ASLTON2WKOZSGE4TCMRWGU3TAMY>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
--
Xuebin Qin
PhD
Department of Computing Science
University of Alberta, Edmonton, AB, Canada
Homepage: https://xuebinqin.github.io/
|
@xuebinqin Same Problem i am also facing can you guide us for the better results on high resolution images |
@x hello sir , |
No help from the auther's |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
@xuebinqin @DengPingFan @PINTO0309 @16673161214
Hello Authors ,
As i have finetune and trained the model on 1024 Resolution but when i am trying to do the inference on higher resolution its accuracy directly goes down to -20% where as at the same time when i resized the image to 1024 and did the inference then the accuracy is bit good as compared to high resolution images results
The text was updated successfully, but these errors were encountered: