Issue to load IR or ONNX model on NCS2+Raspberry Pi4

[fredf]

Error when loading a model converted using MMDeploy on RPi4 (OpenVino 2021.4.2):

1. >>> net = ie.read_network(model="end2end.xml", weights="end2end.bin")
2. >>> exec_net = ie.load_network(network=net, device_name="MYRIAD")
3. Traceback (most recent call last):
4. File "<stdin>", line 1, in <module>
5. File "ie_api.pyx", line 403, in openvino.inference_engine.ie_api.IECore.load_network
6. File "ie_api.pyx", line 442, in openvino.inference_engine.ie_api.IECore.load_network
7. RuntimeError: [ GENERAL_ERROR ]
8. /home/jenkins/agent/workspace/private-ci/ie/build-linux-debian_9_arm/b/repos/openvino/inference-engine/src/vpu/common/src/ngraph/transformations/dynamic_to_static_shape.cpp:199 DynamicToStaticShape transformation encountered dynamic node Tile_1450 of type Tile ver. 0, but only [Ceiling ver. 0, Clamp ver. 0, Concat ver. 0, Convert ver. 0, Exp ver. 0, ExpGatherElements ver. 0, Floor ver. 0, Log ver. 0, MatMul ver. 0, Relu ver. 0, ...] types are supported for dynamic nodes

OpenVino 2022.1 not found

Thank you

[Hairul_Intel]

Hi fredf,

Thank you for reaching out to us.

Please share details regarding your model, is it a custom or pre-trained model, the topology, source repository, etc.

For your information, this error occurs when the model is not supported on MYRIAD devices.

The supported models for MYRIAD Plugin is available on the following pages:

• Intel’s Pre-Trained Models Device Support
• Public Pre-Trained Models Device Support

Regards,

Hairul

[Hairul_Intel · Accepted solution]

Hi fredf,

Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.

Regards,

Hairul