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
Question about get_det_bboxes function #45
Comments
In training, the semantic_score is calucated in here: Therefore the test code you mentioned above is in line with training. |
I know how the semantic_score be calculated, my question is why the scores used in training are semantic_score but when testing will first calculate semantic_score with softmax and then use the code above to count the seen/unseen scores ? |
In training, the classification loss function is |
But in training did not calculate
before calculate the loss |
I got your problem, in inference:
or directly the scores only have the numerical difference, the relative rank has not changed. You can remove these lines and the performance of seen classes will not be changed. I add this process only for be consistency with unseen classes. |
But the scores are belong to seen, why they can be used as unseen scores.
the results can be used as unseen scores |
For unseen scores, this line |
In your experience, does this part can be used in training?
the loss will be
|
I did not try this before, you can have a try and good luck. |
Thanks for reply |
Hi i'm confuse about why need to count this as the final score ?
because when in training the score will be semantic_score that is not same as
above does it have special meaning and why the score can work?
The text was updated successfully, but these errors were encountered: