RuntimeError: Input, output and indices must be on the current device

最新推荐文章于 2024-08-08 14:10:49 发布

明泽.

最新推荐文章于 2024-08-08 14:10:49 发布

阅读量2k

点赞数

文章标签： python

本文链接：https://blog.youkuaiyun.com/qq_36955294/article/details/115674911

版权

本文档记录了在将PyTorch模型转换为ONNX格式时遇到的‘Input, output and indices must be on the current device’错误。重点在于如何定位并解决设备不匹配的问题，适合PyTorch开发者进行参考。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Traceback (most recent call last):
File "detect.py", line 236, in <module>
    detect()
File "detect.py", line 47, in detect
    torch.onnx.export(model,               # model being run
File "/home/zjkj/miniconda3/envs/yolov5/lib/python3.8/site-packages/torch/onnx/__init__.py", line 271, in export
    return utils.export(model, args, f, export_params, verbose, training,
File "/home/zjkj/miniconda3/envs/yolov5/lib/python3.8/site-packages/torch/onnx/utils.py", line 88, in export
    _export(model, args, f, export_params, verbose, training, input_names, output_names,
File "/home/zjkj/miniconda3/envs/yolov5/lib/python3.8/site-packages/torch/onnx/utils.py", line 694, in _export
    _model_to_graph(model, args, verbose, input_names,
File "/home/zjkj/miniconda3/envs/yolov5/lib/python3.8/site-packages/torch/onnx/utils.py", line 502, in _model_to_graph
    params_dict = torch._C._jit_pass_onnx_constant_fold(graph, params_dict,
RuntimeError: Input, output and indices must be on the current device