search

USTC-Video-Understanding / I3D_Finetune

TensorFlow code for finetuning I3D model on UCF101.
144 stars 43 forks source link

Reproduce results #10

Open giladsharir opened 6 years ago

giladsharir commented 6 years ago

Hi, I'm trying to reproduce the results reported in the paper (and this repository) with the I3D model trained with only RGB on UCF-101 (split 1) . When I run test.py with the checkpoint provided in this repository (finetuned on UCF-101 RGB), I get a score of 89.4 . The authors of this repository report 94.7 . Do you have any idea why is there a discrepancy in the scores?

Catchher commented 6 years ago

Aha，I meet the same issue, particularly in Optical-Flow branch with only 83% acc.

vra commented 6 years ago

Hi @giladsharir and @Catchher , Thanks for trying our code and I am sorry for the inconvenience. I guess we have uploaded wrong checkpoints and we are figuring it out. Thanks for you patience.

Catchher commented 6 years ago

Thanks for ur reply, I'm looking forward to ur good news. @vra

tangshixiang commented 5 years ago

Hi, could you tell me whether you have uploaded the corrected checkpoints or not? Thank you~ @vra

sumeetssaurav commented 5 years ago

Hi, I'm trying to reproduce the results reported in the paper (and this repository) with the I3D model trained with only RGB on UCF-101 (split 1) . When I run test.py with the checkpoint provided in this repository (finetuned on UCF-101 RGB), I get a score of 89.4 . The authors of this repository report 94.7 . Do you have any idea why is there a discrepancy in the scores?

TaoXieSZ commented 5 years ago

I got 91% as the result, it is normal?

lanfeng4659 commented 5 years ago

Hi, I'm trying to reproduce the results reported in the paper (and this repository) with the I3D model trained with only RGB on UCF-101 (split 1) . When I run test.py with the checkpoint provided in this repository (finetuned on UCF-101 RGB), I get a score of 89.4 . The authors of this repository report 94.7 . Do you have any idea why is there a discrepancy in the scores?

have you settled the problem? I get the 91.5% scores using the shared model trained on the UCF101 RGB.