Open Suppersine opened 1 year ago
File"train_aux.py" ,Line245,in train, Add an argument "names" to the "create_dataloader" create_dataloader(train_path, imgsz, batch_size, gs, opt, names,...)
Also this one. what makes the dimensions of targets & gain unequal in your {--cfg yolov7-w6.yaml} subarchitecture when run by train_aux,py?
I was running a custom training with this .ipynb command `# Commence Training P6-Models %cd ~/yolov7-obb-lxcly/
!python train_aux.py \ --weights yolov7-w6.pt \ --cfg cfg/training/yolov7-w6.yaml \ --data ~/datasets/roboflow/dataabs.yaml \ --hyp data/hyp.scratch.custom.p6.yaml \ --epochs 20 \ --batch-size 16 \ --img-size 1280 1280 \ --workers 4 \ --device 0 \ --exist-ok \ --name 'YOLOV7-test-p6'`
and then your train_aux.py throws this error