Skip to main content

Packaged version of the Yolov5 object detector

Project description

Packaged YOLOv5 Object Detector

Downloads CI CPU testing Package CPU testing

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

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: CI CPU testing

Status for the train/detect/test scripts: Package CPU testing

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

yolov5-4.0.11.tar.gz (743.1 kB view details)

Uploaded Source

Built Distribution

yolov5-4.0.11-py36.py37.py38-none-any.whl (750.9 kB view details)

Uploaded Python 3.6Python 3.7Python 3.8

File details

Details for the file yolov5-4.0.11.tar.gz.

File metadata

  • Download URL: yolov5-4.0.11.tar.gz
  • Upload date:
  • Size: 743.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.2

File hashes

Hashes for yolov5-4.0.11.tar.gz
Algorithm Hash digest
SHA256 f9b6d17d442a8e8b2249004a4d17d0bfd2e02015d657f78d8ecb1af3d0eff20d
MD5 8c641d33e69a87ff56885aa0e4004423
BLAKE2b-256 ceaf3675e6bbf5df9f3f7a430214700e743c1d9bb9db4a5666cebfd87dfc9edc

See more details on using hashes here.

File details

Details for the file yolov5-4.0.11-py36.py37.py38-none-any.whl.

File metadata

  • Download URL: yolov5-4.0.11-py36.py37.py38-none-any.whl
  • Upload date:
  • Size: 750.9 kB
  • Tags: Python 3.6, Python 3.7, Python 3.8
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.2

File hashes

Hashes for yolov5-4.0.11-py36.py37.py38-none-any.whl
Algorithm Hash digest
SHA256 c20ebab79ee960156fd57a38a9b3db051cc84efc680485fd2001435fb2342a9b
MD5 864002c943ec9892a6fe9b59c06c687d
BLAKE2b-256 8f59b6f1d4bb3390f1ac74c11ed7f68d22bf523719d28d1971429edbf107bdc4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page