Skip to content

Small code snippets that show how to stream camera images to a Coral device.

License

Notifications You must be signed in to change notification settings

FPSychotic/examples-camera

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Edge TPU simple camera examples

This repo contains a collection of examples that use camera streams together with the Edge TPU Python API.

Installation

Before you start using the examples run the download_models.sh script in order to download a selection of models. 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.

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

About

Small code snippets that show how to stream camera images to a Coral device.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 84.5%
  • Shell 15.5%