Yolov7 ! ~ 2022 Summer ~ High-speed, high-precision object detection

We want to use a faster object detection model! !!

Why don’ t you choose the newest and best one?

Yolov7 ~ It was a new version of the high speed object detection series.

GitHub - WongKinYiu/yolov7: Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new…

It is 120% faster than Yolov5.

from original repo

How to use

Inference by pretrained model

For source, specify the image path, image folder path, or 0 (web camera).

I was able to infer in 0.057s on the GPU of Colab.

Training the model

Use on mobile devices

The repository provides the export scripts to TorchScript, ONNX, and CoreML, which can be easily converted to mobile format and used in the app.

Click here for the model I converted to CoreML (with NMS)

GitHub - john-rocky/CoreML-Models: Converted CoreML Model Zoo.

Train with your original data and create a useful app!

🐣

I’m a freelance engineer.
Work consultation
Please feel free to contact us with a brief development description.
rockyshikoku@gmail.com

I am making an app that uses Core ML and ARKit.
We send machine learning / AR related information.

GitHub

Twitter
Medium