Open MeenalNarkhede opened 2 years ago
Hi!
What I can see from the stack trace, your model probably contains tensor types that are not yet supported. If you want you can share the model and I could take a quick look. You can also fix it yourself and open a PR.
Trying to convert YOLOv5s tag2 model (https://github.com/ultralytics/yolov5/tree/v2.0) from ONNX to Keras and getting the following error.
onnx2keras.py:52: OptimizationMissingWarning: Transpose inserted. Please report at https://github.com/AxisCommunications/onnx-to-keras/issues warnings.warn("Transpose inserted. Please report at https://github.com/AxisCommunications/onnx-to-keras/issues", OptimizationMissingWarning) Traceback (most recent call last): File "onnx2keras.py", line 707, in
Fire(main)
File "/home/user/anaconda3/envs/onnx2keras/lib/python3.8/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/home/user/anaconda3/envs/onnx2keras/lib/python3.8/site-packages/fire/core.py", line 466, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/home/user/anaconda3/envs/onnx2keras/lib/python3.8/site-packages/fire/core.py", line 681, in _CallAndUpdateTrace
component = fn(*varargs, *kwargs)
File "onnx2keras.py", line 695, in main
model = onnx2keras(onnx.load(infile))
File "onnx2keras.py", line 642, in onnx2keras
output_tensors = ops.make_op(node.op_type, inputs, attrs)
File "onnx2keras.py", line 18, in makeop
return getattr(self, 'op' + op_type.lower())(inputs, **attrs)
File "onnx2keras.py", line 574, in op_transpose
x = ensure_data_format(x, OnnxConstant)
File "onnx2keras.py", line 56, in ensure_data_format
raise NotImplementedError
NotImplementedError