error：Exception occurred during running replacer "fusing"

[penser]

C:\ProgramFiles\IntelSWTools\openvino_2020.3.194\deployment_tools\model_optimizer>

python mo_tf.py --input_model test.pb --input_shape [1,1280,512,1]

Model Optimizer arguments:
Common parameters:
- Path to the Input Model: C:\Program Files (x86)\IntelSWTools\openvino_2020.3.194\deployment_tools\model_optimizer\test.pb
- Path for generated IR: C:\Program Files (x86)\IntelSWTools\openvino_2020.3.194\deployment_tools\model_optimizer\.
- IR output name: test
- Log level: ERROR
- Batch: Not specified, inherited from the model
- Input layers: Not specified, inherited from the model
- Output layers: Not specified, inherited from the model
- Input shapes: [1,1280,512,1]
- Mean values: Not specified
- Scale values: Not specified
- Scale factor: Not specified
- Precision of IR: FP32
- Enable fusing: True
- Enable grouped convolutions fusing: True
- Move mean values to preprocess section: False
- Reverse input channels: False
TensorFlow specific parameters:
- Input model in text protobuf format: False
- Path to model dump for TensorBoard: None
- List of shared libraries with TensorFlow custom layers implementation: None
- Update the configuration file with input/output node names: None
- Use configuration file used to generate the model with Object Detection API: None
- Use the config file: None
Model Optimizer version:
2020-08-07 10:28:21.981240: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_100.dll'; dlerro
r: cudart64_100.dll not found
2020-08-07 10:28:21.992116: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your
machine.

[ ERROR ] Exception occurred during running replacer "fusing" (<class 'extensions.middle.fusings.Fusing'>): After partial shape inference were found
shape collision for node segment/conv1/BatchNorm/FusedBatchNormV3/beta (old shape: [ 1 1280 512 32], new shape: [ 1 1280 512 -1])

How to solve this problem？Please help me！

[Munesh_Intel · Accepted solution]

Hi Sun Guan,

OpenVINO toolkit does not support FusedBatchNormV3 layer conversion. 

More information about Supported Framework Layers is available at the following page:

https://docs.openvinotoolkit.org/2020.4/openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layer...

I suggest you have a look at the following thread, which contains a workaround provided by our active community member.

https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/MobileNetV3-SSD-FusedBatchNormV3-layer...

Regards,

Munesh

[Munesh_Intel]

Hi Sun Guan,

This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.

Regards,

Munesh

[Luis_at_Intel]

@penser, try using  --disable_nhwc_to_nchw in your MO command and see if that makes any difference. 

Regards,

Luis