Sold by: MphasisÂ
Deployed on AWS
This solution provides explanations for the predictions of a user-provided image classification model on their datasets.
Overview
Explainable AI for Image Classification is designed to diagnose robustness and explainability of model predictions during model development process and production stages. The solution helps developers to ensure transparency and interpretability in deep learning models for computer vision tasks. It generates activation maps of the images highlighting the most important features the model learned for classification. For example, for defect detection in circuit board manufacting, the model might highlight defected solder joints or speciifc components on the circuit board. This solution also demonstrates the confidence scores of the explanations quantifying the interpretability of ML models.
Highlights
- Explainable AI for Image Classification inputs pytorch based deep learning models trained on specific tasks and provides explainibility of model predictions with confidence scores. This solution can aid in explaining model predictions for computer vision tasks in the fields of medical imaging & diagnosis, statellite imaging, detecting defects and anamolies in manufacturing etc.
- Explainable AI for Image Classification provides confidence score of explainability using advanced evaluation framework. The confidence score and evaluation framework evaluates the explanation based on features with least and most attention. The value of metric ranges from -1 to 1, with higher positive value depicting good explanation capability.
- PACE - ML is Mphasis Framework and Methodology for end-to-end machine learning development and deployment. PACE-ML enables organizations to improve the quality & reliability of the machine learning solutions in production and helps automate, scale, and monitor them. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
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 |
|---|---|---|
ml.m5.2xlarge Inference (Batch) Recommended | Model inference on the ml.m5.2xlarge instance type, batch mode | $8.00/host/hour |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $8.00/host/hour |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $8.00/host/hour |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $8.00/host/hour |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $8.00/host/hour |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $8.00/host/hour |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $8.00/host/hour |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $8.00/host/hour |
ml.c4.2xlarge Inference (Batch) | Model inference on the ml.c4.2xlarge instance type, batch mode | $8.00/host/hour |
ml.m4.10xlarge Inference (Batch) | Model inference on the ml.m4.10xlarge instance type, batch mode | $8.00/host/hour |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
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
latest stable release on 29th June, 2023.
Additional details
Inputs
- Summary
This package expects a "Inputs.zip" file which contains two sub-directories: "model" and "inf_data".
The "model" subdirectory conatins the model in *.pth file and a config.json file. The "inf_data" subdirectory contains the images for inferencing.
- Limitations for input type
- For models it supports pytorch based models only.
- Input MIME type
- application/zip, text/plain
https://github.com/Mphasis-ML-Marketplace/explainable-ai-for-image-classification/tree/main/input/Inputs
https://github.com/Mphasis-ML-Marketplace/explainable-ai-for-image-classification/tree/main/input/Inputs
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
*.pth file | This file should contain the model architecture and state_dicts. | Type: Continuous | Yes |
config.json | The keys should be model_filename, label mapping and target_layer. The label mapping is the integer mapping of the string labels in integers. The target layer is the pre-classifier head layer of your model. | Type: FreeText | Yes |
inf_data/ | The inputs images needs to be *.png. | Type: Continuous | Yes |
Resources
Vendor resources
Support
Vendor support
For any assistance, please reach out at:
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
DeepDetector by DuckDuckGoose AI: Detect and explain deepfakes in images and videos with 99% accuracy. API-ready, fast, transparent, and future-proof against evolving threats.
Blackshark ORCA™ HUNTR is a no-code AI/ML object detection development environment that enables rapid prototyping, training and execution of AI/ML models by anyone on any kind of RGB imagery - no experience necessary.
Learns from visual data to detect objects, patterns, outliers and irregularities. Designed to integrate easily with your existing cloud/ on-premise/ hybrid infrastructure.
Kyndryl + Teradata’s FNOL GenAI solution on AWS automates claims intake and intelligent document processing end-to-end. Customers submit claims via web or Amazon Connect IVR; files are uploaded to Amazon S3 with pre-signed URLs and scanned by Amazon GuardDuty. Documents are processed with Amazon Textract, Amazon Comprehend, and Amazon Rekognition; Amazon Bedrock generates claim summaries, while Amazon SageMaker powers fraud scoring. Orchestration runs serverlessly on AWS Lambda (with AWS Step Functions where needed). Outputs and metadata are stored in Amazon Aurora PostgreSQL with AWS KMS and AWS Secrets Manager; integration via Amazon API Gateway/EventBridge. Teradata VantageCloud adds vector search/RAG for faster adjudication and cross-claim insights.
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.