yolov5，部署相关

Question

在您的那个yolov5的教程中，我按照您的方法修改了这行代码

（shape = tuple((y[0] if isinstance(y, tuple) else y).shape) # model output shape）

```后
再运行这段代码之后依然报错。

```python
python export.py --weights yolov5n.pt --data data/coco128.yaml --include onnx --opset 12 --batch-size 1

报错为：

(torchreid) PS D:\diverse project\yolov5-master> python export.py --weights yolov5n.pt --data data/coco128.yaml --include onnx --opset 12 --batch-size 1
export: data=data/coco128.yaml, weights=['yolov5n.pt'], imgsz=[640, 640], batch_size=1, device=cpu, half=False, inplace=False, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=12, verbose=False, workspace=4, nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, conf_thres=0.25, include=['onnx']
YOLOv5  2023-6-18 Python-3.9.16 torch-2.0.1+cpu CPU

Fusing layers... 
YOLOv5n summary: 213 layers, 1867405 parameters, 0 gradients
Traceback (most recent call last):
  File "D:\diverse project\yolov5-master\export.py", line 863, in <module>
    main(opt)
  File "D:\diverse project\yolov5-master\export.py", line 858, in main
    run(**vars(opt))
  File "C:\Users\Peace\AppData\Roaming\Python\Python39\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "D:\diverse project\yolov5-master\export.py", line 760, in run
    shape = tuple(y[0].shape)  # model output shape
TypeError: 'NoneType' object is not subscriptable

请问您知道怎么解决吗

Answer 1

在报错信息中，错误发生在获取 y[0].shape 这一步，
而出现了 'NoneType' object is not subscriptable 的错误。这表明 y 的值为 None，无法对 None 对象进行索引操作。不知道你的y定义的是什么，最好确保一下y对象不是空的