onnx/onnx-tensorflow

Squeeze and unsqueeze not implemented in opset version 13

krishnanpooja opened this issue · 2 comments

krishnanpooja commented

Describe the bug

Can't convert onnx model to TF frozen graph.

To Reproduce

onnx_model = onnx.load("input_path")  
tf_rep = prepare(onnx_model)
tf_rep.export_graph(export_dir)

Python, ONNX, ONNX-TF, Tensorflow version

This section can be obtained by running get_version.py from util folder.

  • Python version: 3.6.9
  • ONNX version: 1.10.2
  • ONNX-TF version: 1.9.0
  • Tensorflow version: 2.6
krishnanNuance commented

#981 (comment)
hi,
Will open the PR latest by tomorrow evening.
I have tested using opset version 13 and onnx-tf version 1.9.0.

  • 👍2