Converting ONNX dynamic input model to Tensorflow

[sontr-n]

Describe the bug Cannot convert ONNX with dynamic input to Tensorflow To Reproduce

1. converting Pytorch model to ONNX model was used Resnext50_32x4d with dynamic batch size

dummy_input = torch.randn(1, 3, 224, 224)
dynamic_axes = {"input": {0: "batch"}, "output": {0: "batch"}}
torch.onnx.export(model, 
            dummy_input,
            'dyanmic_model.onnx', 
            input_names=["input"], output_names=["output"], 
            verbose=True, 
            dynamic_axes=dynamic_axes
)

2. converting ONNX to Tensorflow onnx-tf convert -i dynamic_model.onnx -o tf_model

Python, ONNX, ONNX-TF, Tensorflow version

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

• Python version: 3.8.5
• ONNX version: 1.8.1
• ONNX-TF version: 1.7.0
• Tensorflow version: 2.4.1

Additional context WITHOUT dynamic input, I was able to convert with NO any errors.

[Siddharth1India]

Any update on this?