Image Embeddings using Singular Value Decomposition (SVD) can be used for semantic search, dimensionality reduction, and anomaly detection. Given a batch of images, singular values and vectors are computed using this algorithm.
Highlights
Images are automatically resized, reshaped to 1D to create data matrix before performing SVD
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.
You pay by the host hour, so charges track the time each instance runs. Pricing splits across three activities: training the algorithm, batch inference, and real-time inference. Within each activity, you pick one of five ml.c5 instance sizes, from xlarge up to 18xlarge. Larger instances carry more compute and a higher hourly rate. You can mix activities as your project moves from training to deployment. There is no upfront commitment; you are billed only for the hours you use on the instance sizes you choose.
Top-of-mind questions for buyers
What do the ml.c5 instance sizes mean for the compute I get each host hour?
Each ml.c5 size maps to a fixed CPU-and-memory spec. Moving from xlarge up to 18xlarge adds more vCPUs and memory per host hour. You pick the size based on your data and model size, then pay that size's hourly rate while the instance runs.
Am I charged when an instance is stopped or sitting idle between jobs?
Billing tracks host hours, so charges accrue only while an instance runs. Batch inference and training instances run for the job and then stop. Real-time inference instances stay running to serve requests, so they accrue hours until you shut them down.
How does batch inference billing differ from real-time inference billing?
Both meter host hours on the same ml.c5 sizes. Batch inference runs on a batch of images, then stops, so hours track the job length. Real-time inference keeps an instance live to answer requests on demand, so hours accrue continuously until you stop the endpoint.
www.rocketml.net
Helpful?
Vendor refund policy
We do not currently support refunds, but you can cancel at any time. Please contact us at info@rocketml.net
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the 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:
Algorithm training
Before deploying the model, train it with your data using the algorithm training process. You're billed for software and SageMaker infrastructure costs only during training. Duration depends on the algorithm, instance type, and training data size. When training completes, the model artifacts save to your Amazon S3 bucket. These artifacts load into the model when you deploy for real-time inference or batch processing. For more information, see Use an Algorithm to Run a Training Job .
Real-time inference
Deploy the model as an API endpoint for your applications. When you send data to the endpoint, SageMaker processes it and returns results by API response. The endpoint runs continuously until you delete it. You're billed for software and SageMaker infrastructure costs while the endpoint runs. AWS Marketplace models don't support Amazon SageMaker Asynchronous Inference. For more information, see Deploy models for real-time inference .
Batch transform
Deploy the model to process batches of data stored in Amazon Simple Storage Service (Amazon S3). SageMaker runs the job, processes your data, and returns results to Amazon S3. When complete, SageMaker stops the model. You're billed for software and SageMaker infrastructure costs only during the batch job. Duration depends on your model, instance type, and dataset size. AWS Marketplace models don't support Amazon SageMaker Asynchronous Inference. For more information, see Batch transform for inference with Amazon SageMaker AI .
Version release notes
Singular Value Decomposition on Images
Additional details
Inputs
Outputs
Hyperparameters
Channel specifications
Usage instructions
Sample notebooks
Inputs
Summary
See example notebook for example usage.
Real-time inference sample input data
See Input Summary
Batch transform sample input data
See Input Summary
Support
Vendor support
RocketML offers free support with email response as well as one-on-one office hours with our experienced solution architects. The service helps customers of all sizes and technical abilities to make best use of RocketML products and features. Subscribers and prospecting customers can contact us at the URL below or email support@rocketml.net <www.rocketml.net>
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.
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.