I have trained my data. But it doesn't work with your code.

[Filmimagine]

❔Question

I have trained my data. But it doesn't work with your code.

Additional context

PS D:\project-crop-row> python detect.py --img 320 --weights cropbest.pt --source "test1.mp4" --conf 0.4
Traceback (most recent call last):
File "D:\project-crop-row\detect.py", line 358, in
detect()
File "D:\project-crop-row\detect.py", line 63, in detect
model = attempt_load(weights, map_location=device) # load FP32 model
File "D:\project-crop-row\models\experimental.py", line 118, in attempt_load
ckpt = torch.load(w, map_location=map_location) # load
File "C:\Users\NITRO\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 712, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "C:\Users\NITRO\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 1049, in _load
result = unpickler.load()
File "C:\Users\NITRO\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 1042, in find_class
return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'DetectionModel' on <module 'models.yolo' from 'D:\project-crop-row\models\yolo.py'>

[WoodratTradeCo]

This is because the new and old versions of YOLOv5 are incompatible, and the yolo.py file under models is missing the DetectionModel module code. It is recommended that you make changes in the model by comparing the latest Yolo source code as following URL: https://blog.csdn.net/weixin_46389664/article/details/129306692

[Filmimagine]

@WoodratTradeCo
Thank you very much, I'll try it, do you have a way to contact you? in case i encounter a problem

[Filmimagine]

@WoodratTradeCo I can train my data from your code? how do you configure

I tried training from your file and it crashes.

D:\UAV\project-crop-row>python train.py --img 640 --batch 8 --epochs 100 --data config.yaml --weights yolov5.pt --workers 4 --cache --device 0
Traceback (most recent call last):
File "C:\Program Files\Python39\lib\logging\config.py", line 618, in configure
self.configure_logger(name, loggers[name])
File "C:\Program Files\Python39\lib\logging\config.py", line 794, in configure_logger
logger = logging.getLogger(name)
File "C:\Program Files\Python39\lib\logging_init_.py", line 2042, in getLogger
return Logger.manager.getLogger(name)
File "C:\Program Files\Python39\lib\logging_init_.py", line 1297, in getLogger
raise TypeError('A logger name must be a string')
TypeError: A logger name must be a string

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "D:\UAV\project-crop-row\train.py", line 497, in
set_logging(opt.global_rank)
File "D:\UAV\project-crop-row\utils\general.py", line 42, in set_logging
logging.config.dictConfig({
File "C:\Program Files\Python39\lib\logging\config.py", line 809, in dictConfig
dictConfigClass(config).configure()
File "C:\Program Files\Python39\lib\logging\config.py", line 620, in configure
raise ValueError('Unable to configure logger '
ValueError: Unable to configure logger -1