SysCV/pcan

The time it takes to train the model?

f414158949 opened this issue · 2 comments

f414158949 commented

In your paper, I find "Our model is trained with initial learning rate 0.0025 on 4 GPUs using SGD, and executes with a speed of 15.0 FPS on ResNet-50.". and could you tell me the type of GPU and the time it takes to train the PCAN model on the BDD100K segmentation tracking dataset? (Using the the initial model weights from BDD100k MOT tracking set and not using the the initial model weights) thanks

lkeab commented

RTX gpu and less than 5 hours (in my impression)

f414158949 commented

if we do not use the initial model weights from BDD100k MOT tracking set according to pcan/GET_STARTED.md, how long will it take to train the PCAN model?

"On BDD100K, we build PCAN by
extending the two-stage MOT method [29] with our temporal segmentation modules. We follow the
same training strategy of QDTrack-mots [29]. More details can be found in supplemental material."
Is there any detail about training MOT method QDTrack-mots? thanks.