Tood's onnx file request
hjfdsssdg opened this issue · comments
Hello, I was not able to export the onnx file successfully using mmdet.Is there a Tood onnx file available? I would like to further visualize the network structure for learning, thank you!
@hjfdsssdg Sorry, we have not exported the onnx file.
did anyone manage to export to ONNX? im getting :
Traceback (most recent call last): File "tools/deployment/pytorch2onnx.py", line 319, in <module> pytorch2onnx( File "tools/deployment/pytorch2onnx.py", line 42, in pytorch2onnx torch.onnx.export( File "/opt/conda/lib/python3.8/site-packages/torch/onnx/__init__.py", line 332, in export return utils.export(model, args, f, export_params, verbose, training, File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 113, in export _export(model, args, f, export_params, verbose, training, input_names, output_names, File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 769, in _export _model_to_graph(model, args, verbose, input_names, File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 515, in _model_to_graph graph = _optimize_graph(graph, operator_export_type, File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 230, in _optimize_graph graph = torch._C._jit_pass_onnx(graph, operator_export_type) File "/opt/conda/lib/python3.8/site-packages/torch/onnx/__init__.py", line 386, in _run_symbolic_method return utils._run_symbolic_method(*args, **kwargs) File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 899, in _run_symbolic_method return symbolic_fn(g, *args) File "/opt/conda/lib/python3.8/site-packages/mmcv/ops/deform_conv.py", line 36, in symbolic return g.op( File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 1005, in _graph_op n = g.insertNode(_newNode(g, opname, outputs, *args, **kwargs)) File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 958, in _newNode _add_attribute(n, k, v, aten=aten) File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 936, in _add_attribute return getattr(node, kind + "_")(name, value) TypeError: i_(): incompatible function arguments. The following argument types are supported: 1. (self: torch._C.Node, arg0: str, arg1: int) -> torch._C.Node