Inference on custom dataset

[kartikgupta2607]

Hey there, thank you for the great work! Is there any inference script using which we can run the pre-trained model on custom video (without ground truth) and get the output for the MOTS task (preferably instance_id masks for each frame)? I tried using the demo script from MMTracking, but there were dependency issues for the versions of MMCV and MMDet while using PCAN.

[lkeab]

Hi, you can modify the dataloader here to let it read image sequence only from the video directories w/o reading the corresponding GT labeling. Or you can generate fake annotation GT to mimick the current GT format with empty mask and box labels.