yuxumin
Reproduced results on AQA-7
Hi, Thanks for this amazing work. I ran your code on AQA-7 dataset (with exactly same settings) but the results were a bit lower than the reported results in the paper. I was wondering if you could let me know whether this is the last version of your code or I need to use different settings to get the same results as you reported in the paper. Thanks
In the following table CoRe* is our reproduced results on AQA-7.
No and didn’t get any response from authors. Please let me know if you could sort it out. Thanks Amir
On Sun, 22 Jan 2023 at 10:48, lsh-atom @.***> wrote:
Hey! Did you solve the problem? I met the same question.
— Reply to this email directly, view it on GitHub https://github.com/yuxumin/CoRe/issues/3#issuecomment-1399452285, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHTVR756UXESGZNAUMDFQULWTUF75ANCNFSM54SSCKDQ . You are receiving this because you authored the thread.Message ID: @.***>
@lsh-atom @Plrbear The author did not give the weights for the "AQA-7" dataset, and the code did not specify the pytorch-related random seeds, it only set the random seeds. Maybe is it normal to see some small differences in the results?
