New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Why my reference flow downloaded model doesn't produce the right result. #37
Comments
Your configs look fine. Have you followed the steps in the |
Thanks for your reply. |
Are you using the script |
Yes, I used the script you mentioned, "scripts/extraction_optical_flow.sh". |
Your flow frames indeed look different from what I got. Here I have the same first sequence for your references. Just to note that the flow model is trained with TVL1 optical flow, which is provided by the Please have a look at whether you are using the TVL1 algorithm for flow extraction. |
Maybe that is the reason. |
Good to know the reason. Yes, you can train your own models using other optical flow algorithms while the performance might be similar. But the reference model is trained with TVL1, so using other algorithms in testing will yield incompetent results. |
I retrain the flow model with the UCF101 frames extracted by extract_flow_cpu. But it converges hardly. |
|
@yonghenglh6 |
@yonghenglh6 |
Hi:
When I test the reference model download from website a. The flow model produce very low accuracy.
Here is my config:
It produced the Final accuracy 13.278916% on UCF101 split 1.
While the only-rgb model produced the Final accuracy 86.037706%.
Are there any mistake for my config? Or any other body get the same accuracy number as mine?
Seeking for help~~
The text was updated successfully, but these errors were encountered: