Unable to Run Benchmark_app for ONNX Model on GPU

• Inferred ONNX model with OpenVINO™ 2023.0 Benchmark_app on CPU and GPU.
• Inference success on CPU but failed on GPU.

Currently, dynamic shape support for GPU is a preview feature and has the following limitations:

• It mainly supports Natural Language Processing (NLP) models. Not all operations and optimization pass and support dynamic shapes. As a result, a given model may crash or experience significant performance drops.
• Due to the dominant runtime overhead on the host device, dynamic shapes may perform worse than static shapes on a discrete GPU.
• Dynamic rank is not supported.

Refer to GPU Device for more information.