yolov5-6.0运行train.py时遇到的问题集锦

问题1： 

 File "yolov5-6.0\models\yolo.py", line 116, in __init__
    m.anchors /= m.stride.view(-1, 1, 1)
RuntimeError: The size of tensor a (3) must match the size of tensor b (0) at non-singleton dimension 0

原因分析：
这可能是因为6.0的工程下载了个5.0的模型，所以不匹配, 但问题不能解决
[https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5s.pt]
打开yolo.py中的class Detect(nn.Module):屏蔽部分，该屏蔽部分用于模型转换成onnx

问题2： 

  File "yolov5-6.0\lib\site-packages\torchvision\extension.py", line 48, in _assert_has_ops
    raise RuntimeError(
RuntimeError: Couldn't load custom C++ ops. This can happen if your PyTorch and torchvision versions are incompatible, or if you had errors while compiling torchvision from source. For further information on the compatible versions, check https://github.com/pytorch/vision#installation for the compatibility matrix. Please check your PyTorch version with torch.__version__ and your torchvision version with torchvision.__version__ and verify if they are compatible, and if not please reinstall torchvision so that it matches your PyTorch install.

问题3： 

D:anaconda3\envs\yolov5-6.0\lib\site-packages\torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: '[WinError 127] 找不到指定的程序。'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
原因分析： 
  torch 和 torchvision匹配问题
  pip install --upgrade torch==2.2.0 torchvision -i https://pypi.tuna.tsinghua.edu.cn/simple/
  用以上指令更新，问题2和问题3属于同一个问题

  
问题4：  

    File "yolov5-6.0\utils\plots.py", line 112, in text
    w, h = self.font.getsize(text)  # text width, height
AttributeError: 'FreeTypeFont' object has no attribute 'getsize'

原因分析：

参考博文 ‘FreeTypeFont‘ object has no attribute ‘getsize‘报错解决_freetypefont' object has no attribute 'getsize-CSDN博客

问题出在 库 Pillow 中的 getsize 函数，getsize已弃用，将在Pillow 10（2023-07-01）中删除。
解决方法： 那么打开yolo5环境，降低版本即可，例如下方的：

pip uninstall -y Pillow
pip install Pillow==9.5.0 -i https://pypi.tuna.tsinghua.edu.cn/simple/ 

问题5：

indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1)))

RuntimeError: result type Float can't be cast to the desired output type __int64

解决方法： 参考博文

YOLOv5训练报错：indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1)))-CSDN博客

在在loss.py文件里修改第L177行

gain = torch.ones(7, device=targets.device).long()