search

xuebinqin / BASNet

Code for CVPR 2019 paper. BASNet: Boundary-Aware Salient Object Detection
MIT License
1.35k stars 249 forks source link

how to change confidence threshold ? #35

Closed raghavgurbaxani closed 4 years ago

raghavgurbaxani commented 4 years ago

Hi Thank you for the great work on this repository. How do I change the confidence value of the prediction in basnet_test.py ? Thanks ... :)

xuebinqin commented 4 years ago

Thanks for your interests. Sorry I couldn't understand your question? What do you mean about "change the confidence value"? The output of the network is the probability map and then normalized to exactly [0,1] by normPRED () . It is then normalized to [0,255] and saved as images. If you want to binarize the results, you just have to write you own functions and threshold that.

On Fri, Feb 14, 2020 at 11:34 AM Raghav Gurbaxani notifications@github.com wrote:

Hi Thank you for the great work on this repository. How do I change the confidence value of the prediction in basnet_test.py ? Thanks ... :)

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/NathanUA/BASNet/issues/35?email_source=notifications&email_token=ADSGORILPHKFQRVLLUA64YDRC3PZ7A5CNFSM4KVNP4S2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4INUWBVA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORPRKHB5N65TGGUHYPLRC3PZ7ANCNFSM4KVNP4SQ .

-- Xuebin Qin PhD Candidate Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/