[Bug]: use igpu in nuc, yolov10 output is weird

[ylab604]

OpenVINO Version

2024

Operating System

Ubuntu 20.04 (LTS)

Device used for inference

GPU

Framework

PyTorch

Model used

Yolov10

Issue description

model yolo v10 int8
[test on cpu]

when use cpu, result is good

[test on igpu]

Step-by-step reproduction

i think
if "GPU" in device.value or "NPU" in device.value:
pass
ov_model.reshape({0: [1, 3, 640, 640]})
this code has problem

when i use fp32 model with openvino, adapt with reshape({0: [1, 3, 640, 640]}) output result was weird but remove reshape case was good.

Relevant log output

plz check the bug at igpu

Issue submission checklist

• I'm reporting an issue. It's not a question.
• I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
• There is reproducer code and related data files such as images, videos, models, etc.

[Aznie-Intel]

Hi @ylab604 which OpenVINO demos/samples you are running?

[ylab604]

Hi @ylab604 which OpenVINO demos/samples you are running?

convert yolov10 openvino tutorial
https://docs.openvino.ai/2024/notebooks/yolov10-optimization-with-output.html#run-openvino-inference-on-auto-device-using-ultralytics-api

openvino ver ==2024.1
other version is not work at igpu(output is weird and dynamic shape not work)

[Aznie-Intel]

@ylab604 I have validated the tutorial on GPU and CPU from OpenVINO 2024 and it is working fine.

Which other version is not working at igpu? For your information, this tutorial is only available and validated in the OpenVINO 2024 version. Can you explain how you run in the tutorial in other version and what version you are using?

[ylab604]

@ylab604 I have validated the tutorial on GPU and CPU from OpenVINO 2024 and it is working fine.

Which other version is not working at igpu? For your information, this tutorial is only available and validated in the OpenVINO 2024 version. Can you explain how you run in the tutorial in other version and what version you are using?

did you check in igpu and os? i checked in intel nuc. unbuntu 20.04
2024.0 weird output
2024.1 right result
2024.2 weird output
would you check in unbuntu or nuc?

[Aznie-Intel]

Hi @ylab604 Yes. I have also validated with Ubuntu 20.04 (Intel NUC) and it is working fine from my end.

What is the specific Intel Processor you are using?

[ylab604]

Hi @ylab604 Yes. I have also validated with Ubuntu 20.04 (Intel NUC) and it is working fine from my end.

What is the specific Intel Processor you are using?

would you tell me specific version of openvino? openvino==2024.??

and what is the os version of ubuntu? 20.04?

and how about int8 model?

[Aznie-Intel]

@ylab604 I am running with OpenVINO 2024.0,2024.1 and 2024.2 for all precision with no issues.

[ylab604]

@Aznie-Intel
nuc 11 gen
processor : 7
vendor_id : GenuineIntel
cpu family : 6
model : 140
model name : 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz
stepping : 1
microcode : 0xb6
cpu MHz : 3000.000
cache size : 12288 KB
physical id : 0
siblings : 8
core id : 3
cpu cores : 4
apicid : 7
initial apicid : 7
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes

=============================================
i check the jupyter notebook

[ylab604]

@Aznie-Intel
the problem is Ultralytics ver.
i used old version

thankyou