soltkreig
commented
1 year ago UPD:
set opset_version=12 in deploy config and I got the other error:
IndexError: index_select(): Index is supposed to be a vector
frame #1: at::native::index_select_out_cpu_(at::Tensor const&, long, at::Tensor const&, at::Tensor&) + 0x3a9 (0x7f4bb95e0739 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #2: at::native::index_select_cpu_(at::Tensor const&, long, at::Tensor const&) + 0xe6 (0x7f4bb95e26f6 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #3: <unknown function> + 0x1d3a4c2 (0x7f4bb9cda4c2 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #4: at::_ops::index_select::redispatch(c10::DispatchKeySet, at::Tensor const&, long, at::Tensor const&) + 0xb9 (0x7f4bb9875649 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #5: <unknown function> + 0x3253be3 (0x7f4bbb1f3be3 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #6: <unknown function> + 0x3254215 (0x7f4bbb1f4215 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #7: at::_ops::index_select::call(at::Tensor const&, long, at::Tensor const&) + 0x166 (0x7f4bb98f5296 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so)
frame #8: torch::jit::onnx_constant_fold::runTorchBackendForOnnx(torch::jit::Node const*, std::vector<at::Tensor, std::allocator<at::Tensor> >&, int) + 0x1b5f (0x7f4c62fa41cf in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_python.so)
frame #9: <unknown function> + 0xbbd6f2 (0x7f4c62feb6f2 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_python.so)
frame #10: torch::jit::ONNXShapeTypeInference(torch::jit::Node*, std::map<std::string, c10::IValue, std::less<std::string>, std::allocator<std::pair<std::string const, c10::IValue> > > const&, int) + 0xa8e (0x7f4c62ff0f3e in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_python.so)
frame #11: <unknown function> + 0xbc4a44 (0x7f4c62ff2a44 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_python.so)
frame #12: <unknown function> + 0xb35200 (0x7f4c62f63200 in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_python.so)
frame #13: <unknown function> + 0x2a585b (0x7f4c626d385b in /home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/lib/libtorch_python.so)
<omitting python frames>
(function ComputeConstantFolding)
Traceback (most recent call last):
File "/home/jovyan/people/Murtazin/mmdeploy/tools/torch2onnx.py", line 85, in <module>
main()
File "/home/jovyan/people/Murtazin/mmdeploy/tools/torch2onnx.py", line 47, in main
torch2onnx(
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 356, in _wrap
return self.call_function(func_name_, *args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 326, in call_function
return self.call_function_local(func_name, *args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 275, in call_function_local
return pipe_caller(*args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 107, in __call__
ret = func(*args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/pytorch2onnx.py", line 98, in torch2onnx
export(
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 356, in _wrap
return self.call_function(func_name_, *args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 326, in call_function
return self.call_function_local(func_name, *args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 275, in call_function_local
return pipe_caller(*args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 107, in __call__
ret = func(*args, **kwargs)
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/onnx/export.py", line 131, in export
torch.onnx.export(
File "/home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/onnx/__init__.py", line 316, in export
return utils.export(model, args, f, export_params, verbose, training,
File "/home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/onnx/utils.py", line 107, in export
_export(model, args, f, export_params, verbose, training, input_names, output_names,
File "/home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/onnx/utils.py", line 724, in _export
_model_to_graph(model, args, verbose, input_names,
File "/home/jovyan/people/Murtazin/mmdeploy/mmdeploy/apis/onnx/optimizer.py", line 11, in model_to_graph__custom_optimizer
graph, params_dict, torch_out = ctx.origin_func(*args, **kwargs)
File "/home/user/conda/envs/mmaction2dev/lib/python3.9/site-packages/torch/onnx/utils.py", line 544, in _model_to_graph
params_dict = torch._C._jit_pass_onnx_constant_fold(graph, params_dict,
IndexError: index_select(): Index is supposed to be a vecto
RunningLeon
Checklist
Describe the bug
Hi, I use dev-1.x branch. I'm trying to convert model but got the error below:
I found that I can change opset version from 11 to 12 here:
mmdeploy/mmdeploy/apis/onnx/export.pybut I didn't helpReproduction
Environment
Error traceback