yolov5 4.0.10

Packaged version of the Yolov5 object detector

Packaged YOLOv5 Object Detector

You can finally install YOLOv5 object detector using pip and integrate into your project easily.

Overview

This package is up-to-date with the latest release of ultralytics/yolov5.

Installation

• Install yolov5 using pip (for Python >=3.7):

pip install yolov5

• Install yolov5 using pip (for Python 3.6):

pip install "numpy>=1.18.5,<1.20" "matplotlib>=3.2.2,<4"
pip install yolov5

Basic Usage

from PIL import Image
from yolov5 import YOLOv5

# set model params
model_path = "yolov5/weights/yolov5s.pt" # it automatically downloads yolov5s model to given path
device = "cuda" # or "cpu"

# init yolov5 model
yolov5 = YOLOv5(model_path, device)

# load images
image1 = Image.open("yolov5/data/images/bus.jpg")
image2 = Image.open("yolov5/data/images/zidane.jpg")

# perform inference
results = yolov5.predict(image1)

# perform inference with higher input size
results = yolov5.predict(image1, size=1280)

# perform inference with test time augmentation
results = yolov5.predict(image1, augment=True)

# perform inference on multiple images
results = yolov5.predict([image1, image2], size=1280, augment=True)

Tutorials

• Train Custom Data
• Transfer Learning with Frozen Layers

Scripts

You can download and use train.py, detect.py and test.py scripts after installing the package via pip:

Training

Run commands below to reproduce results on COCO dataset (dataset auto-downloads on first use). Training times for YOLOv5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the largest --batch-size your GPU allows (batch sizes shown for 16 GB devices).

$ python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
                                         yolov5m                                40
                                         yolov5l                                24
                                         yolov5x                                16

Inference

detect.py runs inference on a variety of sources, downloading models automatically from the latest YOLOv5 release and saving results to runs/detect.

$ python detect.py --source 0  # webcam
                            file.jpg  # image
                            file.mp4  # video
                            path/  # directory
                            path/*.jpg  # glob
                            rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
                            rtmp://192.168.1.105/live/test  # rtmp stream
                            http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream

To run inference on example images in data/images:

$ python detect.py --source data/images --weights yolov5s.pt --conf 0.25

Status

Builds for the latest commit for Windows/Linux/MacOS with Python3.6/3.7/3.8:

Status for the train/detect/test scripts: