search

Scalsol / mega.pytorch

Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
Other
565 stars 115 forks source link

Questions about training set #38

Closed ericayn closed 4 years ago

ericayn commented 4 years ago

Hello, I see that when you train the MEGA model, you sample once every 10 frames to consistent training set (datasets/ILSVRC2015/ImageSets/VID_train_every10frame.txt). FGFA methods also sample the training set (VID_train_15frame.txt). However, these two methods have propagated feature to adjacent frames, but samples in VID_train_every10frame.txt have lost the characteristics of adjacent frames. Does MEGA not require continuous image during training model? I am very confused about this. Could you please help me to answer this?

ericayn commented 4 years ago

I solved this.

Sanku-Yogesh commented 2 years ago

hi, could u please answer to this query https://github.com/Scalsol/mega.pytorch/issues/73#issue-754884469

Sanku-Yogesh commented 2 years ago

@ericayn