pnnx segment fault

[iamfaith]

error log | 日志或报错信息 | ログ

############# pass_level2

Program received signal SIGSEGV, Segmentation fault. pnnx::pnnx_graph_rewrite (graph=..., pass=0x555559052c60, opindex=@0x7fffffffd614: 0) at /home/faith/ncnn/tools/pnnx/src/pass_level2.cpp:984 984 cur = graph.ops[cur_index]; (gdb) where #0 pnnx::pnnx_graph_rewrite (graph=..., pass=0x555559052c60, opindex=@0x7fffffffd614: 0) at /home/faith/ncnn/tools/pnnx/src/pass_level2.cpp:984 #1 0x00005555555ffaba in pnnx::pass_level2 (g=...) at /home/faith/ncnn/tools/pnnx/src/pass_level2.cpp:1415 #2 0x00005555555ca184 in main (argc=2, argv=0x7fffffffd9a8) at /home/faith/ncnn/tools/pnnx/src/main.cpp:335 (gdb) bt #0 pnnx::pnnx_graph_rewrite (graph=..., pass=0x555559052c60, opindex=@0x7fffffffd614: 0) at /home/faith/ncnn/tools/pnnx/src/pass_level2.cpp:984 #1 0x00005555555ffaba in pnnx::pass_level2 (g=...) at /home/faith/ncnn/tools/pnnx/src/pass_level2.cpp:1415 #2 0x00005555555ca184 in main (argc=2, argv=0x7fffffffd9a8) at /home/faith/ncnn/tools/pnnx/src/main.cpp:335

model | 模型 | モデル

1. original model

yolov5 6.2 onnx

how to reproduce | 复现步骤 | 再現方法

pnnx yolov5n.onnx

[wzyforgit]

You need input torchscript instead of onnx

[nihui]

针对onnx模型转换的各种问题，推荐使用最新的pnnx工具转换到ncnn In view of various problems in onnx model conversion, it is recommended to use the latest pnnx tool to convert your model to ncnn

pip install pnnx
pnnx model.onnx inputshape=[1,3,224,224]

详细参考文档 Detailed reference documentation https://github.com/pnnx/pnnx https://github.com/Tencent/ncnn/wiki/use-ncnn-with-pytorch-or-onnx#how-to-use-pnnx