I just found a repository YOLOv5 from Github. It’s not just the models are accurate and fast but also easy to get and to use.

Just download the code, install some dependent libraries. And you can just run a simple command:

python3 detect.py --weights yolov5l.pt

Then it will automatically download the YOLO v5 Large model, process all images in inference/images, and put the annotated images into inference/output.

Let’s see some images predicted by YOLO v5 Large:

And every image cost no more than 2 seconds to predict on my laptop. Isn’t it awesome? At least it’s much better than my experiments…