Why are the MAE and max F_beta higher in the test result used your pre-trained model than those in your paper?

[learnerRen]

I use your pre-trained model on HKU-IS and test on the result which has 0.030 MAE and 0.99 max F_beta!!(save and load the saliency map) Do I use the wrong way to test? Could you share how you test?

[xuebinqin]

If you download our code and pre-trained model directly from github and didn't change anything, there shouldn't be a problem of the testing. Please download and compute the mae and max F-beta of our provided saliency HKU-IS. It that gives the same results of your own test. There might be a problem of your evaluation code. We will release our evaluation code later.

On Sat, Aug 10, 2019 at 10:35 PM learnerRen notifications@github.com wrote:

I use your pre-trained model on HKU-IS and test on the result which has 0.030 MAE and 0.99 max F_beta!!(save and load the saliency map) Do I use the wrong way to test? Could you share how you test?

— 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/8?email_source=notifications&email_token=ADSGORP3MVOMQH4CBPF7ZLLQD6JKFA5CNFSM4IK26BR2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HESAVCA, or mute the thread https://github.com/notifications/unsubscribe-auth/ADSGORPWJST6BT47NRU3U4LQD6JKFANCNFSM4IK26BRQ .

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

[learnerRen]

If you download our code and pre-trained model directly from github and didn't change anything, there shouldn't be a problem of the testing. Please download and compute the mae and max F-beta of our provided saliency HKU-IS. It that gives the same results of your own test. There might be a problem of your evaluation code. We will release our evaluation code later. … On Sat, Aug 10, 2019 at 10:35 PM learnerRen @.***> wrote: I use your pre-trained model on HKU-IS and test on the result which has 0.030 MAE and 0.99 max F_beta!!(save and load the saliency map) Do I use the wrong way to test? Could you share how you test? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#8?email_source=notifications&email_token=ADSGORP3MVOMQH4CBPF7ZLLQD6JKFA5CNFSM4IK26BR2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HESAVCA>, or mute the thread https://github.com/notifications/unsubscribe-auth/ADSGORPWJST6BT47NRU3U4LQD6JKFANCNFSM4IK26BRQ . -- Xuebin Qin PhD Candidate Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/

Thanks~