search

Nanyangny / CenterTrack-IOU

Source codes of CenterTrack++ in 2021 ICME Workshop on Big Surveillance Data Processing and Analysis
36 stars 10 forks source link

would you please suggest why the evaluation is NaN on mot17 #2

Open ssbilakeri opened 3 years ago

ssbilakeri commented 3 years ago

gt_type _val_half gt_files [] 09:32:11 INFO - Found 0 groundtruths and 7 test files. 09:32:11 INFO - Available LAP solvers ['lap', 'scipy'] 09:32:11 INFO - Default LAP solver 'lap' 09:32:11 INFO - Loading files. 09:32:11 WARNING - No ground truth for MOT17-02-FRCNN, skipping. 09:32:11 WARNING - No ground truth for MOT17-11-FRCNN, skipping. 09:32:11 WARNING - No ground truth for MOT17-04-FRCNN, skipping. 09:32:11 WARNING - No ground truth for MOT17-10-FRCNN, skipping. 09:32:11 WARNING - No ground truth for MOT17-05-FRCNN, skipping. 09:32:11 WARNING - No ground truth for MOT17-09-FRCNN, skipping. 09:32:11 WARNING - No ground truth for MOT17-13-FRCNN, skipping. 09:32:11 INFO - Running metrics 09:32:11 INFO - partials: 0.000 seconds. 09:32:11 INFO - mergeOverall: 0.001 seconds. Rcll Prcn GT MT PT ML FP FN IDs FM MOTA MOTP num_objects OVERALL nan% nan% 0 nan% nan% nan% nan% nan% nan% nan% nan% nan 0 09:32:11 INFO - partials: 0.000 seconds. 09:32:11 INFO - mergeOverall: 0.001 seconds. IDF1 IDP IDR Rcll Prcn GT MT PT ML FP FN IDs FM MOTA MOTP IDt IDa IDm num_objects OVERALL nan% nan% nan% nan% nan% 0 0 0 0 0 0 0 0 nan% nan 0 0 0 0 09:32:11 INFO - Completed

ssbilakeri commented 3 years ago

I'm able to run the code successfully. Would you please tell me the the significance of generating bounding box using ltrb approach