Sold by: Starlight Retail
Deployed on AWS
Developer-preview SageMaker model package scaffold for structured retail shelf image analysis workflows.
Overview
ShelfOps Vision is a SageMaker model package draft for retail computer-vision workflows that turn shelf images into structured JSON signals for shelf gaps, missing facings, low-stock zones, and planogram-compliance review. This listing is currently prepared as a developer-preview scaffold: the container, SageMaker packaging, validation contract, sample notebook, and Marketplace delivery artifacts are in place, while production model weights and benchmarking remain pending before any public paid release. Buyers deploy the package into their own AWS account and invoke it through SageMaker endpoints or batch transform jobs. Image data remains in buyer-controlled infrastructure.
Highlights
- SageMaker-compatible /ping and /invocations container contract
- Structured JSON output for shelf gaps, missing facings, low-stock zones, and planogram-review signals
- Buyer-owned deployment model with no external data egress from SageMaker
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
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
This product is available free of charge. Free 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.
Vendor refund policy
This developer preview is provided free of charge; no refunds apply.
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) .
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
Adds image-derived baseline shelf anomaly detection in place of the original scaffold mock output. This limited preview is intended for packaging, SageMaker invocation, and buyer-workflow validation before public paid release.
Additional details
Inputs
- Summary
JSON request containing a base64-encoded retail shelf image and optional inference settings, or raw image/jpeg or image/png bytes for direct endpoint invocation.
- Limitations for input type
- Baseline heuristic preview uses deterministic image analysis rather than trained production weights. Validate accuracy and latency on representative shelf imagery before public paid release.
- Input MIME type
- application/json, image/jpeg, image/png
{"image":"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","image_format":"png","image_id":"sample-shelf-001","options":{"return_boxes":true,"min_confidence":0.25,"planogram_id":"<optional>"}}
https://starlight-marketplace-assets-590183841796.s3.amazonaws.com/shelfops-vision/validation.ipynb
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
image | Base64-encoded image bytes for application/json requests. | Required for JSON requests. | Yes |
image_format | Input image format. | jpeg or png. | Yes |
options.min_confidence | Minimum detection confidence threshold. | Number from 0.0 to 1.0. | No |
Support
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.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.