Mask R-CNN Inception ResNet V2 1024x1024 TF2 Object Detection API Conversion

[Silviu1]

Hi, 

I have trained and saved my own TF2 Mask RCNN model. I am trying to optimize the saved_model.pb for faster inference. I first try to convert the model into a frozen graph as states here https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html#freeze-the-tensorflow-model but i get this error tensorflow.python.framework.errors_impl.InternalError: Tensorflow type 21 not convertible to numpy dtype.

Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "StatefulPartitionedCall/map/TensorArrayV2_2" node.

What can i do?

[RaeesaM_Intel]

Hi,

Thank you for posting in Intel Forums.

This issue seems to be related to Openvino. We've a separate forum for Openvino toolkit. So we're moving this case to Openvino toolkit forum for faster response.

Link to Forum : https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/bd-p/distribution-openvino-toolkit

Regards

Raeesa

[Iffa_Intel]

Hi,

This is a duplicate to this thread: https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Mask-R-CNN-Inception-ResNet-V2-1024x1024-Conversion/m-p/1300473#M24625

Please focus on the thread that I had share above and I'm closing this one.

Sincerely,

Iffa