Error in detect_dual.py: s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string

[JFMeyer2k]

I am training a YoloV9-e model by

python3 train_dual.py --workers 4 --device 0 --batch 8 --data data/custom.yaml --img 650 --cfg models/detect/yolov9-e.yaml --weights 'yolov9-e.pt' --name yolov9-e --hyp hyp.scratch-high.yaml --min-items 0 --epochs 500 --close-mosaic 15

If I want to run an inference with

python3 detect_dual.py --nosave --save-txt --conf-thres 0.1 --imgsz 650 --weights '/yolo/yolov9//runs/train/yolov9-e/weights/best.pt' --source '/images/' --project '/images/'--name 'inference' --device 0

I get the error:

detect_dual: weights=['/home/ec2-user/yolo/yolov9//runs/train/yolov9-e/weights/best.pt'], source=/home/ec2-user/yolo/images/inference/Test/Hudl_Focus_Flex_FAI_vs_Netherlands_team_only_1/images_orig/, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.1, iou_thres=0.45, max_det=1000, device=0, view_img=False, save_txt=True, save_conf=False, save_crop=False, nosave=True, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=/home/ec2-user/yolo/images/inference/Test/Hudl_Focus_Flex_FAI_vs_Netherlands_team_only_1/images_orig/, name=inference, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1
YOLO 🚀 v0.1-104-g5b1ea9a Python-3.10.9 torch-2.3.1+cu121 CUDA:0 (NVIDIA L4, 22491MiB)

Fusing layers... 
yolov9-e summary: 839 layers, 68553982 parameters, 0 gradients, 240.7 GFLOPs
Traceback (most recent call last):
  File "/home/ec2-user/yolo/yolov9/detect_dual.py", line 233, in <module>
    main(opt)
  File "/home/ec2-user/yolo/yolov9/detect_dual.py", line 228, in main
    run(**vars(opt))
  File "/opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/ec2-user/yolo/yolov9/detect_dual.py", line 132, in run
    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
KeyError: 2

I already followed the advice from #11, #162, and #50

Where @WongKinYiu explicitly mentioned to

yolo-*.yaml: use detect_dual.py.
gelan-*.yaml: use detect.py.

However, even though I am using detect_dual.py and tried changing utils/general.py according to the previously mentioned issue (see above), I still get the above error.

Update:

• I left utils/general.py unchanged and only changed detect_dual.py as described by #373, specifically fix detect.py, keyerror exception in class names dict #86