深度学习error记录（自用|持续更新）

最新推荐文章于 2024-07-23 17:03:22 发布

叶青古

最新推荐文章于 2024-07-23 17:03:22 发布

阅读量1.4k

点赞数 2

分类专栏： ML/DL/数据结构与算法 python 自用文章标签：深度学习 pytorch

本文链接：https://blog.csdn.net/qq_31681523/article/details/117084628

版权

本文记录了在深度学习过程中遇到的几个典型错误及其解决办法，包括：CUDA后端运行torchvision::nms出错、train.py命令缺少数据路径、模型加载时state_dict不匹配以及张量尺寸不匹配的问题。通过调整torchvision版本、修正argparse参数定义、调整模型加载策略和处理图像模式，可以解决这些问题。

摘要由CSDN通过智能技术生成

1.RuntimeError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend.
2.train.py: error: the following arguments are required: data
3.Missing key(s) in state_dict,Unexpected key(s) in state_dict
4.RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0

1.RuntimeError: Could not run ‘torchvision::nms’ with arguments from the ‘CUDA’ backend.

Traceback (most recent call last):
    File "/opt/yyl/yolov5/train.py", line 543, in <module>
        train(hyp, opt, device, tb_writer)
    File "/opt/yyl/yolov5/train.py", line 355, in train
        results, maps, times = test.test(data_dict,
    File "/opt/yyl/yolov5/test.py", line 122, in test
        out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
    File "/opt/yyl/yolov5/utils/general.py", line 560, in non_max_suppression
        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
    File "/root/anaconda3/envs/py38_torch16/lib/python3.8/site-packages/torchvision/ops/boxes.py", line 42, in nms
       return torch.ops.torchvision.nms

最低0.47元/天解锁文章

叶青古

关注

2
点赞
踩
6

收藏

觉得还不错? 一键收藏
0
评论
深度学习error记录（自用|持续更新）

目录1.RuntimeError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend.1.RuntimeError: Could not run ‘torchvision::nms’ with arguments from the ‘CUDA’ backend.Traceback (most recent call last): File "/opt/yyl/yolov5/train.py", line
复制链接

扫一扫

专栏目录