yolov7代码报错

yolov7 代码报错

以下是版本配置

import torch
import torchvision
print("torch:",torch.__version__) #1.7.0
print("torchvision:",torchvision.__version__) #0.8.1+cu110
print('GPU:',torch.cuda.is_available())#cuda是否可用 TRUE
print(torch.cuda.device_count())#返回GPU的数量 1
print(torch.version.cuda) #11.0
print(torch.backends.cudnn.version()) #8004
x = torch.rand(5, 3)
print(x)

yolo v7运行时报错

Traceback (most recent call last):
  File "E:/pycharmProject/yolov7-tiny-Efiicientvit/train.py", line 615, in <module>
    train(hyp, opt, device, tb_writer)
  File "E:/pycharmProject/yolov7-tiny-Efiicientvit/train.py", line 94, in train
    model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
  File "E:\pycharmProject\yolov7-tiny-Efiicientvit\models\yolo.py", line 618, in __init__
    self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
  File "E:\pycharmProject\yolov7-tiny-Efiicientvit\models\yolo.py", line 940, in parse_model
    m = timm.create_model(m, pretrained=args[0], features_only=True)
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\_factory.py", line 118, in create_model
    **kwargs,
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\mobilenetv3.py", line 676, in mobilenetv3_small_100
    model = _gen_mobilenet_v3('mobilenetv3_small_100', 1.0, pretrained=pretrained, **kwargs)
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\mobilenetv3.py", line 400, in _gen_mobilenet_v3
    model = _create_mnv3(variant, pretrained, **model_kwargs)
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\mobilenetv3.py", line 263, in _create_mnv3
    **kwargs)
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\_builder.py", line 399, in build_model_with_cfg
    strict=pretrained_strict,
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\_builder.py", line 186, in load_pretrained
    state_dict = load_state_dict_from_hf(pretrained_loc)
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\timm\models\_hub.py", line 183, in load_state_dict_from_hf
    return safetensors.torch.load_file(cached_safe_file, device="cpu")
  File "D:\py\anaconda\envs\pytorch\lib\site-packages\safetensors\torch.py", line 261, in load_file
    result[k] = f.get_tensor(k)
AttributeError: module 'torch' has no attribute 'frombuffer'
```python

请问具体是什么问题，怎么解决

你这根本就不是yolov7啊，请确认下你的项目版本要求的torch版本是多少，我估计是版本问题，特别是这个timm和safetensors包的torch要求版本多少

【相关推荐阅读】

• 你可以参考下这个问题的回答, 看看是否对你有帮助, 链接: https://ask.csdn.net/questions/7419677
• 这篇博客也不错, 你可以看下利用yolov7训练自己的数据集； yolov7的安装与使用 ； yolov7源码解读
• 您还可以看一下 李立宗老师的YOLOv1论文深度解析（8小时原汁原味逐句解析YOLO论文）课程中的 卷积层小节, 巩固相关知识点
  

如果你已经解决了该问题, 非常希望你能够分享一下解决方案, 写成博客, 将相关链接放在评论区, 以帮助更多的人 ^-^