please report a bug to PyTorch. ONNX Expand input shape constraint not satisfied.

最新推荐文章于 2025-05-08 13:26:19 发布

原创最新推荐文章于 2025-05-08 13:26:19 发布 · 1.7k 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

标签

#bug #pytorch #python

python环境同时被 3 个专栏收录

11 篇文章

订阅专栏

mmaction

3 篇文章

订阅专栏

onnx

2 篇文章

订阅专栏

在尝试将PyTorch模型转换为ONNX格式时遇到了RuntimeError，错误信息涉及到`input_shape_value==reshape_value||input_shape_value==1||reshape_value==1 INTERNAL ASSERT FAILED`。该问题可能源于ONNX形状推理过程中输入和重塑约束不满足。目前在GitHub上未找到明确的解决方案。寻求帮助以解决PyTorch ONNX导出过程中的形状约束冲突。

Qwen3-32B-Chat 私有部署镜像 | RTX4090D 24G 显存 CUDA12.4 优化版

Qwen

文本生成

Qwen3

本镜像基于 RTX 4090D 24GB 显存 + CUDA 12.4 + 驱动 550.90.07 深度优化，内置完整运行环境与 Qwen3-32B 模型依赖，开箱即用。

项目场景：

RuntimeError: input_shape_value == reshape_value || input_shape_value == 1 || reshape_value == 1INTERNAL ASSERT FAILED at "..\\torch\\csrc\\jit\\passes\\onnx\\shape_type_inference.cpp
":520, please report a bug to PyTorch. ONNX Expand input shape constraint not satisfied.

问题描述

提示：这里描述项目中遇到的问题：

模型在转onnx的时候遇到的错误，在git上查找到相同的错误，但也没有明确的解决方式，有哪位大佬帮忙解答一下

Traceback (most recent call last):
  File "tools\deployment\pytorch2onnx.py", line 165, in <module>
    pytorch2onnx(
  File "tools\deployment\pytorch2onnx.py", line 68, in pytorch2onnx
    torch.onnx.export(
  File "D:\miniconda3\lib\site-packages\torch\onnx\__init__.py", line 275, in export
    return utils.export(model, args, f, export_params, verbose, training,
  File "D:\miniconda3\lib\site-packages\torch\onnx\utils.py", line 88, in export
    _export(model, args, f, export_params, verbose, training, input_names, output_names,
  File "D:\miniconda3\lib\site-packages\torch\onnx\utils.py", line 689, in _export
    _model_to_graph(model, args, verbose, input_names,
  File "D:\miniconda3\lib\site-packages\torch\onnx\utils.py", line 463, in _model_to_graph
    graph = _optimize_graph(graph, operator_export_type,
  File "D:\miniconda3\lib\site-packages\torch\onnx\utils.py", line 200, in _optimize_graph
    graph = torch._C._jit_pass_onnx(graph, operator_export_type)
  File "D:\miniconda3\lib\site-packages\torch\onnx\__init__.py", line 313, in _run_symbolic_function
    return utils._run_symbolic_function(*args, **kwargs)
  File "D:\miniconda3\lib\site-packages\torch\onnx\utils.py", line 994, in _run_symbolic_function
    return symbolic_fn(g, *inputs, **attrs)
  File "D:\miniconda3\lib\site-packages\torch\onnx\symbolic_opset9.py", line 473, in expand_as
    return g.op("Expand", self, shape)
  File "D:\miniconda3\lib\site-packages\torch\onnx\utils.py", line 890, in _graph_op
    torch._C._jit_pass_onnx_node_shape_type_inference(n, _params_dict, opset_version)
RuntimeError: input_shape_value == reshape_value || input_shape_value == 1 || reshape_value == 1INTERNAL ASSERT FAILED at "..\\torch\\csrc\\jit\\passes\\onnx\\shape_type_inference.cpp
":520, please report a bug to PyTorch. ONNX Expand input shape constraint not satisfied.