Sold by: Amazon Web ServicesÂ
Deployed on AWS
YOLOv3 is a powerful network for fast and accurate object detection, powered by GluonCV.
Overview
Given an input image, this will return object coordinates and category predictions. The format of coordinates is encoded as (left, top, right, bottom) of the absolute pixel locations. This model is trained on COCO dataset with 80 common object categories. It can be used as fast and reliable general object detector.
Highlights
- This model can detect multiple objects on the input image.
- The results include category names, confidence scores, and absolute locations on the input image.
- Offers state-of-the-art performance with bounding box mAP of 37.0 compared to 33.0 in the original paper (https://arxiv.org/abs/1804.02767)
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m4.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m4.xlarge instance type, real-time mode | $0.00 |
ml.m4.xlarge Inference (Batch) Recommended | Model inference on the ml.m4.xlarge instance type, batch mode | $0.00 |
ml.m4.4xlarge Inference (Real-Time) | Model inference on the ml.m4.4xlarge instance type, real-time mode | $0.00 |
ml.m5.4xlarge Inference (Real-Time) | Model inference on the ml.m5.4xlarge instance type, real-time mode | $0.00 |
ml.m5.12xlarge Inference (Real-Time) | Model inference on the ml.m5.12xlarge instance type, real-time mode | $0.00 |
ml.m4.16xlarge Inference (Real-Time) | Model inference on the ml.m4.16xlarge instance type, real-time mode | $0.00 |
ml.m5.2xlarge Inference (Real-Time) | Model inference on the ml.m5.2xlarge instance type, real-time mode | $0.00 |
ml.c4.4xlarge Inference (Real-Time) | Model inference on the ml.c4.4xlarge instance type, real-time mode | $0.00 |
ml.m5.xlarge Inference (Real-Time) | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.00 |
ml.c5.9xlarge Inference (Real-Time) | Model inference on the ml.c5.9xlarge instance type, real-time mode | $0.00 |
Vendor refund policy
This product is offered for free. If there are any questions, please contact us for further clarifications.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Fix scaling problem for object locations
Additional details
Inputs
- Summary
Usage Instructions: Supported content types are image/jpeg, image/png and image/bmp.
AWS APIs can be used to invoke the model after endpoint creation, for example, using aws-cli:
aws sagemaker-runtime invoke-endpoint --endpoint-name your_endpoint_name --body fileb://img.jpg --content-type image/jpeg --custom-attributes '{"threshold": 0.2}' --accept json >(cat) 1>/dev/null
The confidence score threshold can be configured in range (0, 1).
- Input MIME type
- image/jpeg, image/png, image/bmp
See Input Summary
See Input Summary
Resources
Vendor resources
Support
Vendor support
Model supported is available from GluonCV. Search for questions and open new issues to ask questions. https://gluon-cv.mxnet.io/index.htmlÂ
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
DeepLab is a powerful model for image semantic segmentation, powered by GluonCV.
Single Shot MultiBox Detector (SSD) is a powerful network for fast and accurate object detection, powered by GluonCV.
Faster RCNN is a powerful network for accurate object detection, powered by GluonCV.
Image feature extraction and ImageNet category prediction using extremely fast MobileNet, provided by GluonCV
Customer reviews
H. M
Easy to use
Reviewed on May 20, 2021
Review from a verified AWS customer
I could make an inference endpoint using this model package with relatively short amount of time. It also works with short latency with cheapest instance available.
Excellent YOLO Model
Amazing
Reviewed on May 01, 2019
Review from a verified AWS customer
A very good model to deploy to an endpoint and very simple to use. Very accurate and a excellent implementation o YOLOV3.