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
No confidence score for the predicted boxes #51
Comments
Dear @pordeli , No. You need the confidence scores to evaluate your detections. Best regards, |
Thanks for your reply. As long as I do not have the scores do you know a kind of code that I can use to get precision and recall and the curve for my 100 frames of the video? |
hello , |
@pordeli , Due to the behavior of the metric we apply you will need the confidences. I do not know any other code that you could use. |
@Ibmaria , For the detections you need to apply an object detector, such as YOLO, Faster R-CNN, Fast R-CNN, etc. They will provide the detection bounding boxes, classes and confidences. |
For the model i use ssd mobilenet , |
@Ibmaria , I never worked with mobilenet, so I dont know its output format. But you should get its output and convert it to the required format. |
@rafaelpadilla |
Dear @Ibmaria , You will need to create a script for that. It will take your detections to convert from the format mobilenet provides to the format and name required. Could you show me the detections format given by mobilenet? |
@rafaelpadilla |
@rafaelpadilla |
@Ibmaria , I do not have a script for that. If you provide the output format of the mobilenet, I might be able to help you. |
@Ibmaria , Was your problem solved? |
@rafaelpadilla |
I have ground truth boxes and predicted boxes from YOLO and DPM and Openpose algorithms. Their format is [ x y w h] and I do not have the confidence scores. Is it possible to use your python code for getting the precision and recall and the curve? I get the below error:
Metrics-master/lib/BoundingBox.py", line 45, in init
'For bbType='Detection', it is necessary to inform the classConfidence value.')
OSError: For bbType='Detection', it is necessary to inform the classConfidence value.
The text was updated successfully, but these errors were encountered: