’IndexError: list index out of range’ when running val.py with yolov9-c-converted.pt

[kurokei3333]

I am encountering an IndexError: list index out of range when running the val.py script with the yolov9-c-converted.pt weights file. The error occurs during the COCO-JSON dictionary saving process. Below are the details of the error and the steps to reproduce it.

##Environment:

• Python version: 3.8.12
• Torch version: 1.11.0a0+b6df043
• CUDA version: 0 (NVIDIA RTX A6000, 48677MiB)
• YOLOv5 commit: 1e33dbb

##Command
python3 val.py --img 640 --batch 8 --conf 0.001 --iou 0.7 --device 0 --data /workspace/yolov9/data/coco.yaml --weights /workspace/yolov9color/weights/yolov9-c-converted.pt

##Error log
val: data=/workspace/yolov9/data/coco.yaml, weights=['/workspace/yolov9color/weights/yolov9-c-converted.pt'], batch_size=8, imgsz=640, conf_thres=0.001, iou_thres=0.7, max_det=300, task=val, device=0, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=False, dnn=False, min_items=0
YOLOv5 🚀 1e33dbb Python-3.8.12 torch-1.11.0a0+b6df043 CUDA:0 (NVIDIA RTX A6000, 48677MiB)

Fusing layers...
gelan-c summary: 467 layers, 25472640 parameters, 64944 gradients, 102.8 GFLOPs
val: Scanning /workspace/yolov9/datasets/coco/val2017.cache... 4952 images, 48 backgrounds, 0 corrupt: 100%|██████████| 5000/5000 00:00
Class Images Instances P R mAP50 mAP50-95: 0%| | 0/625 00:00
Traceback (most recent call last):
File "val.py", line 389, in
main(opt)
File "val.py", line 362, in main
run(**vars(opt))
File "/opt/conda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
return func(*args, **kwargs)
File "val.py", line 244, in run
save_one_json(predn, jdict, path, class_map) # append to COCO-JSON dictionary
File "val.py", line 46, in save_one_json
'category_id': class_map[int(p[5])],
IndexError: list index out of range