I am converting encoder and decoder to onnx format.
Everything works fine but as soon as I compare torch_out with caffe2 model it gives AtrributError
np.testing.assert_almost_equal(torch_out.data.cpu().numpy(), c2_out, decimal=3)
In this I am getting AtrributError
Nonetype object has no attribute 'data'
torch_out=torch.onnx.export(model,x,model.onnx, verbose=True)
Export function gives the graph but when I print torch_out it prints None but it should print tensor value
And this is causing AtrributError when comparing torch_out with caffe2 model
【My problem is as follows】：
Traceback (most recent call last):
File "convert1.py", line 11, in
torch.onnx.export(model, dummy_input, "alexnet.onnx", verbose=False, input_names=input_names, output_names=output_names)
File "/root/anaconda3/lib/python3.6/site-packages/torch/onnx/init.py", line 168, in export
custom_opsets, enable_onnx_checker, use_external_data_format)
File "/root/anaconda3/lib/python3.6/site-packages/torch/onnx/utils.py", line 69, in export
use_external_data_format=use_external_data_format)
File "/root/anaconda3/lib/python3.6/site-packages/torch/onnx/utils.py", line 488, in _export
fixed_batch_size=fixed_batch_size)
File "/root/anaconda3/lib/python3.6/site-packages/torch/onnx/utils.py", line 334, in _model_to_graph
graph, torch_out = _trace_and_get_graph_from_model(model, args, training)
File "/root/anaconda3/lib/python3.6/site-packages/torch/onnx/utils.py", line 282, in _trace_and_get_graph_from_model
orig_state_dict_keys = _unique_state_dict(model).keys()
File "/root/anaconda3/lib/python3.6/site-packages/torch/jit/init.py", line 286, in _unique_state_dict
state_dict = module.state_dict(keep_vars=True)
AttributeError: 'collections.OrderedDict' object has no attribute 'state_dict'
How to solve this problem？
onnx
