Help us understand the problem. What is going on with this article?

Yolo v3のさまざまな実装

お使いの環境での最適な実装は、お使いの環境によって違ってきます。
ぜひ、調査してみることをおすすめします。

フレームワーク ソースコードのURL ドキュメントのURL 解説記事
OpenCV ---- https://docs.opencv.org/master/da/d9d/tutorial_dnn_yolo.html
OpenVino https://github.com/PINTO0309/OpenVINO-YoloV3 https://github.com/intel-iot-devkit/smart-video-workshop/tree/master/presentations
Keras https://github.com/qqwweee/keras-yolo3 ------ https://qiita.com/yoyoyo_/items/10d550b03b4b9c175d9c
Chainer https://github.com/chainer/chainercv/tree/master/examples/yolo ------
Tensorflow https://github.com/wizyoung/YOLOv3_TensorFlow ------
darknet https://github.com/AlexeyAB/darknet https://pjreddie.com/darknet/
darknet -https://github.com/pjreddie/darknet ------

Intel のOpenVinoの資料によれば、オリジナルのcaffeモデルから数倍の高速化ができるとのことである。
Yoloもcaffeモデルがあり、同様に高速化が期待できそうだ。
https://github.com/intel-iot-devkit/smart-video-workshop/blob/master/presentations/01-Introduction-to-Intel-Smart-Video-Tools.pdf

TinierYolo

https://github.com/Xilinx/QNN-MO-PYNQ/tree/master/qnn

https://ru-clip.net/video/D1RxIp76rpc/object-detection-on-the-pynq-z1-and-movidius-neural-compute-stick.html

Why do not you register as a user and use Qiita more conveniently?
  1. We will deliver articles that match you
    By following users and tags, you can catch up information on technical fields that you are interested in as a whole
  2. you can read useful information later efficiently
    By "stocking" the articles you like, you can search right away
Comments
Sign up for free and join this conversation.
If you already have a Qiita account
Why do not you register as a user and use Qiita more conveniently?
You need to log in to use this function. Qiita can be used more conveniently after logging in.
You seem to be reading articles frequently this month. Qiita can be used more conveniently after logging in.
  1. We will deliver articles that match you
    By following users and tags, you can catch up information on technical fields that you are interested in as a whole
  2. you can read useful information later efficiently
    By "stocking" the articles you like, you can search right away