Is there any plan to support tf.uint32? #1802
Description
Describe the bug
Why tf.uint32 and tf.uint64 is not supported? I think ONNX support these two datatypes according to the link
System information
- OS Platform and Distribution (Linux Ubuntu 18.04):
- Tensorflow Version: (TF1.15.5)
- Python version: (Python 3.8)
- tf2onnx version: (tf2onnx 1.9.1)
Additional context
**Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/convert.py", line 605, in
main()
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/convert.py", line 245, in main
model_proto, _ = _convert_common(
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/convert.py", line 154, in _convert_common
g = process_tf_graph(tf_graph, const_node_values=const_node_values, kwargs)
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/tfonnx.py", line 504, in process_tf_graph
tensorflow_to_onnx(tf_graph, shape_override, const_node_values, ignore_default, use_default)
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/tf_utils.py", line 461, in tensorflow_to_onnx
return tflist_to_onnx(graph, shape_override, const_node_values, ignore_default, use_default)
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/tf_utils.py", line 406, in tflist_to_onnx
dtypes[out.name] = map_tf_dtype(out.dtype)
File "/usr/local/lib/python3.8/dist-packages/tf2onnx/tf_utils.py", line 112, in map_tf_dtype
dtype = TF_TO_ONNX_DTYPE[dtype]
KeyError: tf.uint32