We have a tensorflow python application on video analytic. The program CPU usage around 90 but the GPU usage is about 20. How to balance the usage to increase GPU usage and decrease cpu usage.
njuffa
2
You are likely to receive better / faster answers on a forum / mailing-list dedicated to Tensorflow.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Why over usage of CPU and under usage of GPU - python tensorflow | 1 | 663 | September 3, 2019 | |
GPU memory usage issue while using TensorFlow | 0 | 450 | April 20, 2020 | |
Full processing only in one GPU, how to leverage the processing to another GPU? | 1 | 1057 | April 16, 2019 | |
GPU functioning only at 16% with CUDA and cuDNN installed (Geforce GTX 750 Ti) | 5 | 2635 | May 26, 2018 | |
how do i find out if my tensorflow application uses the GPU? | 0 | 385 | March 8, 2020 | |
Difference of memory usage at each GPU model during tensorflow c++ inference | 3 | 1546 | November 20, 2019 | |
Why are Python samples not using tensorflow-gpu in nvcr.io/nvidia/tensorrt:19.05-py2 ? | 1 | 586 | July 3, 2019 | |
Same program Different memory usage on Different GPU | 2 | 1064 | April 2, 2022 | |
How to identify whether the memory used by the current graphics card comes from the memory module or from the graphics card itself | 3 | 454 | March 9, 2022 | |
Slower inference times when running multiple programs | 0 | 395 | May 6, 2019 |