DistributionNotFound: The ‘pycocotools>=2.0‘ distribution was not found

        最近自己在搞YOLOv5目标检测学习,对模型的搭建遇到了很多问题,查看了很多资料,经过一些大神的回答,这个模型终于是跑起来了。把自己的错误总结整理一下。

错误一:

        AttributeError: Can't get attribute 'SPPF' on

改正:

        你去他的6.0版本的moudle里把SPPFF类复制到你的5.0里 或者

class SPPF(nn.Module):

# export-friendly version of nn.SiLU()

@staticmethod
def forward(x):
return x * torch.sigmoid(x)     这段加到models的common

错误二; 

         DistributionNotFound: The 'pycocotools>=2.0' distribution was not found and is required by the application

改正 :

        安装包https://pan.baidu.com/s/1nWQdPRtGwNnOO2DkxRuGuA提取码:i5d7

安装完直接解压复制其中pycocotools两个文件夹到conda环境…\Lib\site-packages之中

错误三:

        Error loading data from ../coco128/images/train2017/: train: ..\coco128\images\train2017 does not exist

改正;

        查看你下载的,需要将数据解压

错误四:

        ValueError: Media Bounding Box Debugger/Images is invalid. Please remove invalid filename characters

改正:

        pip uninstall wandb  在你的环境中卸载掉

错误五:

         parser.add_argument('--cfg', type=str, default='./models/yolov5s.yaml', help='model.yaml path')
改正:

        把cfg那行default填上

错误六: 

        Image Not Found

改正:

        不能有中文路径

错误七:

        Command 'pip install 'colorama; platform_system == "Windows"'' returned non-zero exit status 1.

改正 

        pip install colorama

  

你可能感兴趣的:(目标检测,深度学习,计算机视觉,python)