ROBOFLOW UNIVERSE

The Largest Resource of
Computer Vision Datasets and Pre-Trained Models

Datasets
750k+
Images
575m+
Pre-trained Models
175k+
Explore Universe

Deploy with 175,000+ Pre-Trained Models

Deploy to production, use for model assisted labeling, or as a training checkpoint.
conveyor belt with packages on itconveyor belt with packages on itconveyor belt with packages on itconveyor belt with packages on itconveyor belt with packages on it
Confidence Threshold: 100% 0% 100% Overlap Threshold: 50% 0% 100% Label Display Mode: Draw Labels
Try a model in the browser using your image or video data
ARM CPU
x86 CPU
Luxonis OAK
NVIDIA GPU
NVIDIA TRT
NVIDIA Jetson
Raspberry Pi
ARM CPU
x86 CPU
Luxonis OAK
NVIDIA GPU
NVIDIA TRT
NVIDIA Jetson
Raspberry Pi
Python
cURL
Javascript
Swift
.Net

from inference_sdk import InferenceHTTPClient

CLIENT = InferenceHTTPClient(
    api_url="https://detect.roboflow.com",
    api_key="****"
)

result = CLIENT.infer(your_image.jpg, model_id="safety-vests/5")
Use infinitely scalable cloud APIs with SDKs and code snippets directly in your application

Search 575,000+ Datasets for Any Use Case

Explore and analyze datasets containing 750 million+ images
Aerial
Drone view of a coastline.
Agriculture
Animals
Benchmark
Biology
CCTV
Construction
Damage and Risk Assesment
Documents
Energy and Utilites
Environment
Logistics
Manufacturing
Medical
Roboflow 100
Robotics
Collections of datasets and pre-trained models for specific use cases
model
YOLOv8
AND
stars:
> 80
model:
Datasets using the given model
type:
Datasets that are the given type
stars:
Datasets with the given amount of stars
image count:
Datasets containing the given amount of images
views:
Datasets with the given amount of views
Search and filter for relevant projects to find the best resources
Number of Images 10,126 0 missing annotations 9 null examples Number of Annotations 10,537 1.0 per image (average) Across 1 classes Average Image Size 0.14 mp from to 0.01 mp to 17.44 mp Median Image Ratio 472x303 wide Class Balance Overview of the number of annotations for each class in your dataset Classes License_Plate 10,537 Dimension Insights Overview of the sizes and aspect ratios of the images in your dataset. Size Distribution Sizes are based on the number of pixels in your images. small 87 medium 8,400 large 1,283 jumbo 356 > 1024x1024
license plate detection/4 93.4% mAP 95.7% precision 89.4% recall
Evaluate the health of datasets and accuracy of models before using them

Datasets and Models for Every Industry

Our goal is to democratize the power of computer vision for everyone
Making advancements in computer vision accessible to software developers and machine learning engineers
Making it easy to deploy models into production with a few lines of code
Making datasets available to be used for research and benchmarking
“Roboflow has been instrumental in accelerating our learning and deployment of innovative AI solutions”
Travis Turnbull Vice President & CIO, Pella Corporation
See customer stories
Ready to get started?

Join over 1 million developers building with Roboflow

Try it for FreeTalk to Sales