search

youtubevos / MaskTrackRCNN

MaskTrackRCNN for video instance segmentation based on mmdetection
Apache License 2.0
431 stars 75 forks source link

Mask size doesn't match #16

Open ZhangKKK opened 5 years ago

ZhangKKK commented 5 years ago

Hi. When I want to evaluate the results generated using your pretrained model on the codalab, the output log is like

creating index... index created! Running per image evaluation... Evaluate annotation type segm Mask sizes in video 4 and category 1 may not match! Mask sizes in video 5 and category 23 may not match! Mask sizes in video 6 and category 20 may not match! Mask sizes in video 7 and category 1 may not match! Mask sizes in video 8 and category 17 may not match! Mask sizes in video 9 and category 19 may not match! Mask sizes in video 11 and category 11 may not match! Mask sizes in video 12 and category 1 may not match! Mask sizes in video 14 and category 10 may not match! Mask sizes in video 14 and category 10 may not match!

When I check I notice that in valid_submission_sample.json the mask size seems to be [720, 1280] whie in the results.json generated by the pretrained.pth you give the size is [360, 640]. I am wondering why.

Thank you very much.

ruyueshuo commented 4 years ago

same error. any solution?

li-yanling commented 4 years ago

Hi, I got the same error. Is there any parameter I can change to increase the output file size? Thank you.

QingpingZheng commented 4 years ago

@ZhangKKK @ruyueshuo @li-yanling The error is raised because of the inconsistent size between test results and the original size. In order to retrival the result size to the original, you need to ensure the parameter 'rescale' in model should be true.