跑YOLO模型时出现IndexError: too many indices for tensor of dimension 3

最近做项目，在跑对比实验的时候出现了问题，自己本来是在跑YOLOV10的，然后需要跑V8的对比实验，想着两者相似就直接切换模型去跑了，然后就报错了233。

错误如下，大伙可以自行比对一下情况

Traceback (most recent call last): File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\dzj-train.py", line 29, in <module> results = model.train(data='MY_DATA.yaml', epochs=100, imgsz=640, device=[0,], workers=0, batch=4, cache=True, amp=False, save_json=True) File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\engine\model.py", line 657, in train self.trainer.train() File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\engine\trainer.py", line 213, in train self._do_train(world_size) File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\engine\trainer.py", line 430, in _do_train self.metrics, self.fitness = self.validate() File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\engine\trainer.py", line 552, in validate metrics = self.validator(self) File "D:\Anaconda\main\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\engine\validator.py", line 187, in __call__ preds = self.postprocess(preds) File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\models\yolo\detect\val.py", line 86, in postprocess return ops.non_max_suppression( File "D:\pythonproject\deeplearning\DropDectect\yolov5s-main\ultralytics\utils\ops.py", line 218, in non_max_suppression prediction = prediction['one2many'][0] IndexError: too many indices for tensor of dimension 3 进程已结束,退出代码1

上网查了原因，总之就是因为张量维数出错了，各位打开自己的ultralytics\utils\ops.py文件，找到我下面的那几行语句（我的在216行），其中第二行是跑YOLOV10才需要带上的，把他注释掉就行，当然你要是不放心，可以直接去GitHub随便找个V8项目，把他的ops.py拷过来也行，其实就是让他恢复初始状态就行，自己加的东西记得注释掉。