You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the bug
I'm trying to convert a tensorflow 2 model to onnx and although I get a model at the end, I just can't use it because some of the OPs were not converted to onnx.
Urgency
Very important to get it to work soon.
System information
OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows
Tensorflow Version: 2.8
Python version: 3.8
To Reproduce
I ran the command : python -m tf2onnx.convert --saved-model model_v0 --opset 15 --output model_v0.onnx
The model that I used is model_v0.zip
Additional context
The exact errors that I got are these:
ERROR - Tensorflow op [StatefulPartitionedCall/attend_copy_parse_model/mul: SparseDenseCwiseMul] is not supported
ERROR - Tensorflow op [StatefulPartitionedCall/attend_copy_parse_model/SparseReduceSum: SparseReduceSum] is not supported
ERROR - Unsupported ops: Counter({'SparseDenseCwiseMul': 1, 'SparseReduceSum': 1})
Thanks in advance!
The text was updated successfully, but these errors were encountered:
Describe the bug
I'm trying to convert a tensorflow 2 model to onnx and although I get a model at the end, I just can't use it because some of the OPs were not converted to onnx.
Urgency
Very important to get it to work soon.
System information
To Reproduce
I ran the command :
python -m tf2onnx.convert --saved-model model_v0 --opset 15 --output model_v0.onnx
The model that I used is model_v0.zip
Additional context
The exact errors that I got are these:
ERROR - Tensorflow op [StatefulPartitionedCall/attend_copy_parse_model/mul: SparseDenseCwiseMul] is not supported
ERROR - Tensorflow op [StatefulPartitionedCall/attend_copy_parse_model/SparseReduceSum: SparseReduceSum] is not supported
ERROR - Unsupported ops: Counter({'SparseDenseCwiseMul': 1, 'SparseReduceSum': 1})
Thanks in advance!
The text was updated successfully, but these errors were encountered: