High CPU Usuage

[uwe72]

I were able to start the detect.py in order to do the detections of my IP-Camera using a mpeg/rtsp stream. Works well:

My problem is that the CPU is arround 60%.

I am using a NUC10i7FNH. Is there a way to decrease the CPU?

[glenn-jocher]

@uwe72 use a GPU?

[uwe72]

no, i don't use GPU

[glenn-jocher]

@uwe72 yes exactly. If you want to offload inference from your CPU you should use a GPU.

[uwe72]

@glenn-jocher
Thank you!

I am brave now and ask :-) sorry for this probably stupid beginner question: Has every hardware, or in my case my Intel NUC a GPU? If not, can i add or exchange anything on the hardware?

Second question: If the hardware has a GPU how can i start the software in docker in the GPU mode?

[glenn-jocher]

Supported GPUs are here: https://developer.nvidia.com/cuda-gpus#compute

For Docker see Docker quickstart guide below:

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are passing. These tests evaluate proper operation of basic YOLOv5 functionality, including training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu.

[uwe72]

Thanks!!!