search

AxisCommunications / onnx-to-keras

Convert onnx models exported from pytorch to tensorflow keras models with focus on performace and highleve compatibility.
MIT License
25 stars 13 forks source link

TfKerasOperations' object has no attribute 'op_expand' #9

Open anilsathyan7 opened 3 years ago

anilsathyan7 commented 3 years ago

I got this error during onnx to keras conversion:

Traceback (most recent call last):
  File "onnx2keras.py", line 579, in <module>
    Fire(main)
  File "/usr/local/lib/python3.6/dist-packages/fire/core.py", line 138, in Fire
    component_trace = _Fire(component, args, parsed_flag_args, context, name)
  File "/usr/local/lib/python3.6/dist-packages/fire/core.py", line 468, in _Fire
    target=component.__name__)
  File "/usr/local/lib/python3.6/dist-packages/fire/core.py", line 672, in _CallAndUpdateTrace
    component = fn(*varargs, **kwargs)
  File "onnx2keras.py", line 571, in main
    model = onnx2keras(onnx.load(infile))
  File "onnx2keras.py", line 559, in onnx2keras
    output_tensors = ops.make_op(node.op_type, inputs, attrs)
  File "onnx2keras.py", line 17, in make_op
    return getattr(self, 'op_' + op_type.lower())(*inputs, **attrs)
AttributeError: 'TfKerasOperations' object has no attribute 'op_expand'

Is this an unsupported operation issue?

hakanardo commented 3 years ago

Yes. Can share a minimal pytorch network needing it?