百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
E

examples-camera

> 编程语言
开源

一些小代码片段,展示如何将摄像头图像流式传输到 Coral 设备。

393 stars0 点赞0 次浏览
访问官网GitHub

工具介绍

一些小代码片段,展示如何将摄像头图像流式传输到 Coral 设备。

Edge TPU simple camera examples

This repo contains a collection of examples that use camera streams together with the TensorFlow Lite API with a Coral device such as the USB Accelerator or Dev Board.

Installation

  1. First, be sure you have completed the setup instructions for your Coral device. If it's been a while, repeat to be sure you have the latest software.

    Importantly, you should have the latest TensorFlow Lite runtime installed (as per the Python quickstart)).

  2. Clone this Git repo onto your computer:

    bash
    mkdir google-coral && cd google-coral
    
    git clone https://github.com/google-coral/examples-camera.git --depth 1
  3. Download the models:

    bash
    cd examples-camera
    
    sh download_models.sh

    These canned models will be downloaded and extracted to a new folder all_models.

Further requirements may be needed by the different camera libraries, check the README file for the respective subfolder.

Contents

  • Gstreamer Python examples using gstreamer to obtain camera images. These examples work on Linux using a webcam, Raspberry Pi with the Raspicam and on the Coral DevBoard using the Coral camera. For the former two you will also need a Coral USB Accelerator to run the models.
  • Raspicam Python example using picamera. This is only intended for Raspberry Pi and will require a Coral USB Accelerator. Use install_requirements.sh to make sure all the dependencies are present.
  • PyGame Python example using pygame to obtain camera frames. Use install_requirements.sh to make sure all the dependencies are present.
  • OpenCV Python example using OpenCV to obtain camera frames. Use install_requirements.sh to make sure all the dependencies are present.
  • NativeApp C++ example using gstreamer to obtain camera frames. See README in the nativeapp directory on how to compile for the Coral DevBoard.

Canned models

For all the demos in this repository you can change the model and the labels file by using the flags flags --model and --labels. Be sure to use the models labeled _edgetpu, as those are compiled for the accelerator - otherwise the model will run on the CPU and be much slower.

For classification you need to select one of the classification models and its corresponding labels file:

inception_v1_224_quant_edgetpu.tflite, imagenet_labels.txt
inception_v2_224_quant_edgetpu.tflite, imagenet_labels.txt
inception_v3_299_quant_edgetpu.tflite, imagenet_labels.txt
inception_v4_299_quant_edgetpu.tflite, imagenet_labels.txt
mobilenet_v1_1.0_224_quant_edgetpu.tflite, imagenet_labels.txt
mobilenet_v2_1.0_224_quant_edgetpu.tflite, imagenet_labels.txt

mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite, inat_bird_labels.txt
mobilenet_v2_1.0_224_inat_insect_quant_edgetpu.tflite, inat_insect_labels.txt
mobilenet_v2_1.0_224_inat_plant_quant_edgetpu.tflite, inat_plant_labels.txt

For detection you need to select one of the SSD detection models and its corresponding labels file:

mobilenet_ssd_v1_coco_quant_postprocess_edgetpu.tflite, coco_labels.txt
mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite, coco_labels.txt
mobilenet_ssd_v2_face_quant_postprocess_edgetpu.tflite, coco_labels.txt

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月17日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言