ultralytics_yolov5.md

layout	background-class	body-class	category	title	summary	image	author	tags	github-link	github-id	featured_image_1	featured_image_2	accelerator
hub_detail	hub-background	hub	researchers	YOLOv5	YOLOv5 in PyTorch > ONNX > CoreML > TFLite	ultralytics_yolov5_img0.jpg	Ultralytics LLC	vision scriptable	https://github.com/ultralytics/yolov5	ultralytics/yolov5	ultralytics_yolov5_img1.jpg	ultralytics_yolov5_img2.png	cuda-optional

Before You Start

Start from a working python environment with Python>=3.8 and PyTorch>=1.6 installed, as well as PyYAML>=5.3 for reading YOLOv5 configuration files. To install PyTorch see https://pytorch.org/get-started/locally/. To install dependencies:

pip install -U PyYAML  # install dependencies

Model Description

 

YOLOv5 is a family of compound-scaled object detection models trained on COCO 2017, and includes built-in functionality for Test Time Augmentation (TTA), Model Ensembling, Rectangular Inference, Hyperparameter Evolution.

Model	APval	APtest	AP50	SpeedGPU	FPSGPU		params	FLOPS
YOLOv5s	37.0	37.0	56.2	2.4ms	416		7.5M	13.2B
YOLOv5m	44.3	44.3	63.2	3.4ms	294		21.8M	39.4B
YOLOv5l	47.7	47.7	66.5	4.4ms	227		47.8M	88.1B
YOLOv5x	49.2	49.2	67.7	6.9ms	145		89.0M	166.4B
YOLOv5x + TTA	50.8	50.8	68.9	25.5ms	39		89.0M	354.3B

** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8.

Load From PyTorch Hub

To load YOLOv5 from PyTorch Hub for inference with PIL, OpenCV, Numpy or PyTorch inputs:

import cv2
import torch
from PIL import Image

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True).fuse().autoshape()  # for PIL/cv2/np inputs and NMS

# Images
for f in ['zidane.jpg', 'bus.jpg']:  # download 2 images
    print(f'Downloading {f}...')
    torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/' + f, f)
img1 = Image.open('zidane.jpg')  # PIL image
img2 = cv2.imread('bus.jpg')[:, :, ::-1]  # OpenCV image (BGR to RGB)
imgs = [img1, img2]  # batched list of images

# Inference
results = model(imgs, size=640)  # includes NMS

# Results
results.print()  # print results to screen
results.show()  # display results
results.save()  # save as results1.jpg, results2.jpg... etc.

# Data
print('\n', results.xyxy[0])  # print img1 predictions
#          x1 (pixels)  y1 (pixels)  x2 (pixels)  y2 (pixels)   confidence        class
# tensor([[7.47613e+02, 4.01168e+01, 1.14978e+03, 7.12016e+02, 8.71210e-01, 0.00000e+00],
#         [1.17464e+02, 1.96875e+02, 1.00145e+03, 7.11802e+02, 8.08795e-01, 0.00000e+00],
#         [4.23969e+02, 4.30401e+02, 5.16833e+02, 7.20000e+02, 7.77376e-01, 2.70000e+01],
#         [9.81310e+02, 3.10712e+02, 1.03111e+03, 4.19273e+02, 2.86850e-01, 2.70000e+01]])

Citation

Contact

Issues should be raised directly in the repository. For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.