GRUSequence opset5 not supported on GPU in OpenVINO 2023.1 – How to run GRU model on GPU?

[BCPRAVEEN1234]

hello,

I am trying to run a PyTorch GRU model on intel GPU using OpenVINO 2023.1.
My model is a GRU classifier

I converted it to OpenVINO IR using ovc  tool with .xml and .bin files 

now i tried  to run the benchmark on cpu i got the results

now i tried to run on the gpu i got this error  i gave this command

!benchmark_app -m "D:\open_vino\open_vino_installation\gru_models\gru_model.xml" -d GPU.0 -b 1 -i D:\open_vino\open_vino_installation\gru_models\inputs_bs1 --api async

[Step 1/11] Parsing and validating input arguments
[ INFO ] Parsing input parameters
[Step 2/11] Loading OpenVINO Runtime
[ INFO ] OpenVINO:
[ INFO ] Build ................................. 2023.1.0-12185-9e6b00e51cd-releases/2023/1
[ INFO ] 
[ INFO ] Device info:
[ INFO ] GPU
[ INFO ] Build ................................. 2023.1.0-12185-9e6b00e51cd-releases/2023/1
[ INFO ] 
[ INFO ] 
[Step 3/11] Setting device configuration
[ WARNING ] Performance hint was not explicitly specified in command line. Device(GPU.0) performance hint will be set to PerformanceMode.THROUGHPUT.
[ WARNING ] Batch size is set. Auto batching will be disabled
[Step 4/11] Reading model files
[ INFO ] Loading model files
[ INFO ] Read model took 9.99 ms
[ INFO ] Original model I/O parameters:
[ INFO ] Model inputs:
[ INFO ]     input_ids (node: input_ids) : i64 / [...] / [?,?]
[ INFO ] Model outputs:
[ INFO ]     logits (node: logits) : f32 / [...] / [?,2]
[Step 5/11] Resizing model to match image sizes and given batch
[ WARNING ] Batch dimension is not specified for input 'input_ids'. The first dimension will be interpreted as batch size.
[ INFO ] Model batch size: 1
[ INFO ] Reshaping model: 'input_ids': [1,?]
[ INFO ] Reshape model took 1.00 ms
[Step 6/11] Configuring input of the model
[ INFO ] Model inputs:
[ INFO ]     input_ids (node: input_ids) : i64 / [N,...] / [1,?]
[ INFO ] Model outputs:
[ INFO ]     logits (node: logits) : f32 / [...] / [1,2]
[Step 7/11] Loading the model to the device
[ ERROR ] Exception from src\inference\src\core.cpp:117:
[ GENERAL_ERROR ] Exception from src\plugins\intel_gpu\src\plugin\program.cpp:463:
Operation: GRUSequence_54 of type GRUSequence(opset5) is not supported

Traceback (most recent call last):
  File "D:\open_vino\open_vino_installation\openvino_env\lib\site-packages\openvino\tools\benchmark\main.py", line 407, in main
    compiled_model = benchmark.core.compile_model(model, benchmark.device, device_config)
  File "D:\open_vino\open_vino_installation\openvino_env\lib\site-packages\openvino\runtime\ie_api.py", line 543, in compile_model
    super().compile_model(model, device_name, {} if config is None else config),
RuntimeError: Exception from src\inference\src\core.cpp:117:
[ GENERAL_ERROR ] Exception from src\plugins\intel_gpu\src\plugin\program.cpp:463:
Operation: GRUSequence_54 of type GRUSequence(opset5) is not supported

please read this please help me regarding this 

[Peh_Intel]

Hi BCPRAVEEN1234,

I would recommend you to upgrade to latest OpenVINO version and re-convert the model and test running on GPU again.

Regards,

Peh

[Peh_Intel]

Hi BCPRAVEEN1234,

I would recommend you to upgrade to latest OpenVINO version and re-convert the model and test running on GPU again.

Regards,

Peh