OpenVINO version: 2020.1
MO command line:
python3 mo_tf.py --input_model /media/xavier/Modelle2020/mobilenetv2_deeplabv3/mobilev2deep.pb --input 0:MobilenetV2/Conv/Conv2D --input_shape [1,481,641,3] --output ResizeBilinear_2 --output_dir /media/xavier/Modelle2020/openvino/mobilenetv2_deeplabv3
.PB File: As .ZIP File attached
Error Output after mo-tf:
[ ERROR ] Exception occurred during running replacer "fusing" (<class 'extensions.middle.fusings.Fusing'>): After partial shape inference were found shape collision for node Add2_ (old shape: [ 1 241 321 32], new shape: [ 1 241 321 -1])
Before 2020.1 I was using 2019.3 there the Outputfrom mo-tf was:
List of operations that cannot be converted to Inference Engine IR:
[ ERROR ] FusedBatchNormV3 (59)
I got the Information that the FusedBatchNormV3 Problem would be saved in 2020.1 and so it was. But since 2020.1 there is the new "Add2_" Problem described above.
Please help if you can.
Hello, Horst Androsch.
OpenVINO toolkit does not support FusedBatchNormV3 layer conversion. Please find the following topic for the workaround provided by one of users - https://software.intel.com/en-us/forums/intel-distribution-of-openvino-toolkit/topic/831459
Also, please take a look at this similar issue reported for ONNX model conversion - https://software.intel.com/en-us/forums/intel-distribution-of-openvino-toolkit/topic/832585
Hope this helps.