Model not working with custom YOLOv8 weights

[userkw]

I'm encountering an issue with my YOLOv8 model when attempting to use custom weights. Despite specifying the appropriate configuration parameters, the model does not seem to be detecting objects correctly. Below, I've outlined the specifics of the problem along with relevant code snippets and command line execution details:

""
model = YOLO('yolov8_cus.pt') # Loading custom YOLOv8 weights
model.overrides['conf'] = 0.3 # NMS confidence threshold
model.overrides['iou'] = 0.4 # NMS IoU threshold
model.overrides['agnostic_nms'] = False # NMS class-agnostic
model.overrides['max_det'] = 1000 # Maximum number of detections per image
names = model.names
""

cmd line i used :!python track_v8.py --source cas_yl.mp4 --track

[bharath5673]

what is the error?

…

On Tue, Mar 19, 2024 at 9:01 PM userkw ***@***.***> wrote: I'm encountering an issue with my YOLOv8 model when attempting to use custom weights. Despite specifying the appropriate configuration parameters, the model does not seem to be detecting objects correctly. Below, I've outlined the specifics of the problem along with relevant code snippets and command line execution details: "" model = YOLO('yolov8_cus.pt') # Loading custom YOLOv8 weights model.overrides['conf'] = 0.3 # NMS confidence threshold model.overrides['iou'] = 0.4 # NMS IoU threshold model.overrides['agnostic_nms'] = False # NMS class-agnostic model.overrides['max_det'] = 1000 # Maximum number of detections per image names = model.names "" cmd line i used :!python track_v8.py --source cas_yl.mp4 --track — Reply to this email directly, view it on GitHub <#29>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AIBKZLLIESCIWZ6OFS7ZMILYZBK63AVCNFSM6AAAAABE5ZYE5OVHI2DSMVQWIX3LMV43ASLTON2WKOZSGE4TKMRZGY3DMMA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[userkw]

The problem arises when I use my model here:
model = YOLO('yolov8_cus.pt')
The tracker doesn't track anything, but when I use a pre-trained model like yolov8.pt, it works well.

[userkw]

@bharath5673 when i use my custom model i get this error i rename my custom model best.pt :yolov5s:
(env1) C:\Users\elkis\OneDrive\Desktop\StrongSORT-YOLO>python track_v5.py --source casgenerale_yl.mp4 --yolo-weights weights/yolov5s.pt --img 640
track_v5: yolo_weights=['weights/yolov5s.pt'], strong_sort_weights=C:\Users\elkis\OneDrive\Desktop\StrongSORT-YOLO\weights\osnet_x0_25_msmt17.pt, config_strongsort=strong_sort/configs/strong_sort.yaml, source=casgenerale_yl.mp4, imgsz=[640, 640], conf_thres=0.5, iou_thres=0.5, max_det=1000, device=, show_vid=False, save_txt=False, save_conf=False, save_crop=False, save_vid=False, nosave=False, count=False, draw=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs\track, name=exp, exist_ok=False, line_thickness=2, hide_labels=False, hide_conf=False, hide_class=False, half=False, dnn=False
YOLOv5 2024-3-22 Python-3.8.18 torch-2.2.1+cpu CPU

Traceback (most recent call last):
File "track_v5.py", line 411, in
main(opt)
File "track_v5.py", line 406, in main
run(**vars(opt))
File "C:\Users\elkis\anaconda3\envs\env1\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "track_v5.py", line 114, in run
model = DetectMultiBackend(yolo_weights, device=device, dnn=dnn, data=None, fp16=half)
File "C:\Users\elkis\OneDrive\Desktop\StrongSORT-YOLO\yolov5\models\common.py", line 334, in init
model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse)
File "C:\Users\elkis\OneDrive\Desktop\StrongSORT-YOLO\yolov5\models\experimental.py", line 80, in attempt_load
ckpt = torch.load(attempt_download(w), map_location='cpu') # load
File "C:\Users\elkis\anaconda3\envs\env1\lib\site-packages\torch\serialization.py", line 1026, in load
return _load(opened_zipfile,
File "C:\Users\elkis\anaconda3\envs\env1\lib\site-packages\torch\serialization.py", line 1438, in _load
result = unpickler.load()
File "C:\Users\elkis\anaconda3\envs\env1\lib\site-packages\torch\serialization.py", line 1431, in find_class
return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'DetectionModel' on <module 'models.yolo' from 'C:\Users\elkis\OneDrive\Desktop\StrongSORT-YOLO\yolov5\models\yolo.py'>