weixin_44820457的博客

Pytorch测试模型问题记录加载模型出现 RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available()因为模型是在GPU上训练的，然后我在CPU上加载就会报错，可以尝试下面方法：checkpoint = torch.load("xxx/model.pth") 改为checkpoint = torch.load("xxx/model.pth",map_location=

docker进入容器报 Error response from daemon: Container 681bf28df57… is not running记录一下进入docker中自己的容器报错https://blog.youkuaiyun.com/github_38336924/article/details/102504692

记录一下配置YOLOv5_5.0过程中的报错信息AttributeError: Can’t get attribute ‘SPPF’把utils/google_utils.py中的链接转换成v5.0 release # GitHub assets file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) try: response = requests.get(f'https:

解决方法：  去Tags6里面的model/common.py里面去找到这个SPPF的类,然后拷贝到Tags5的model/common.py里面,这样你的代码就也有这个类了,然后import warning包SPPF类代码：import warningsclass SPPF(nn.Module): # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher def __init__(self,