The difference of performance
Closed this issue · 3 comments
HitBadTrap commented
Hi! I'm confused about why is the performance of MDM, MLD, and MotionDiffuse in Table 2 different from that in the original paper. Could you tell me which paper the performance in Table 2 comes from?
L-Sun commented
The Table.2 use evaluation/run.py
to calculate metrics. The difference of metrics may be from these reasons:
- since the implement of dataloader has some differences from those paper, the different order of loading makes the performance not exactly same
- This result was obtained through distributed computing, so there may be some differences.
- random seed influence
For more details, you can review the implement of evaluation/run.py
and dataloader
L-Sun commented
The former. all data is calculated using evaluation/run.py including other
methods.
HitBadTrap ***@***.***> 于2024年6月22日周六 14:17写道:
… Sorry, what I mean is, where does the data in Table 2 of your paper come
from? Is it through your own experiments or from other papers? If it is the
latter, could you please provide the title of the cited paper?
—
Reply to this email directly, view it on GitHub
<#6 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AE4HYSWIER6SJ275QVVZ6PLZIUJIBAVCNFSM6AAAAABJLQOLPCVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOBTHAZTIMZSGI>
.
You are receiving this because you commented.Message ID:
***@***.***>
--
TECH OTAKUS SAVE THE WORLD
HitBadTrap commented
Thank you for your feedback.