Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6492 Discussions

Having different calculation result between cpu and npu with nan, inf op.

WilsonChen0723
Beginner
1,029 Views

Hi.

 

I'm having different results for the same calculation with different processing units.

And it will result in precision error in the final.

 

Result using NPU
-- out_0132__model_dep_encoder_Resize_NPU.npy
(0,1, 8, 0) [ nan, inf, 0.206299, 0.40625,
(0,1,11, 0) [ -inf, nan, 0.136963, 0.171631,

Result using CPU
-- out_0132__model_dep_encoder_Resize_CPU.npy
(0,1, 8, 0) [ 0.313762, 0.260029, 0.206297, 0.406028,
(0,1,11, 0) [ 0.005915, 0.0714487, 0.136982, 0.171628,

 

Attached files :

- model_input_n_output.zip : models, input npy, the output npy for the CPU, NPU.
- openvino_benchmark_app_src.zip : In order to save the result into npy, we made some changes to the benchmark_app source code(0_before : origin file、1_after : with fix)
- benchmark_app_custom_result_log.txt : The executing log for benchmark_app

 

Please help, thank you.

0 Kudos
3 Replies
Hairul_Intel
Moderator
988 Views

Hi WilsonChen0723,

Thank you for reaching out to us.

 

We noticed from your log text file that you're using OpenVINO version 2023.1.0.

 

As such, please install the latest OpenVINO 2023.2 version through the OpenVINO archives on the download page and see if the issue is resolved.

 

Furthermore, please do share your device information (CPU, Operating System, etc.) with us.

 

 

Regards,

Hairul


0 Kudos
Hairul_Intel
Moderator
886 Views

Hi WilsonChen0723,

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


0 Kudos
WilsonChen0723
Beginner
809 Views

Hi,

 

CPU : Intel® Core™ Ultra 5 processor 135H

OS : Windows 11 enterprise.

■ 2023.2
-- out_0132__model_dep_encoder_Resize_NPU.npy
(0,1, 8, 0)    [          nan,       -273.75,      0.206299,       0.40625,
(0,1,11, 0)    [          inf,           nan,      0.136963,      0.171631,
-- out_0132__model_dep_encoder_Resize_CPU.npy
(0,1, 8, 0)    [     0.313762,      0.260029,      0.206297,      0.406028,
(0,1,11, 0)    [     0.005915,     0.0714487,      0.136982,      0.171628,

■ 2023.1
-- out_0132__model_dep_encoder_Resize_NPU.npy
(0,1, 8, 0)    [          nan,           inf,      0.206299,       0.40625,
(0,1,11, 0)    [         -inf,           nan,      0.136963,      0.171631,
-- out_0132__model_dep_encoder_Resize_CPU.npy
(0,1, 8, 0)    [     0.313762,      0.260029,      0.206297,      0.406028,
(0,1,11, 0)    [     0.005915,     0.0714487,      0.136982,      0.171628,

 

0 Kudos
Reply