Scalsol / mega.pytorch

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

How to train with ONLY VID? #110

Open youzi260 opened 2 years ago

youzi260 commented 2 years ago

Hello, I want to train the network only with VID instead of DET. When I changed DATASETS_TRAIN in base_rcnn_1gpu. yaml and vid_R_101_C4_mega_1x. yaml , the following error occurred. How to solve it?

ValueError: Type mismatch (<class 'tuple'> vs. <class 'str'>) with values (() vs. VID_train_15frames) for config key: DATASETS.TRAIN