aws / aws/amazon-sagemaker-examples
[Example Request] send an image (and receive a mask back) from a Lambda function to a semantic segmentation model endpoint
- Dominant language
- Jupyter Notebook
- Stars
- 11k
- Forks
- 7k
- Avg merge
- 8h 29m
- Merged PRs (30d)
- 8
Description
**Describe the use case example you want to see**
I want to send an image (and receive a mask back) from a Lambda function to a semantic segmentation model endpoint that was trained and deployed using SageMaker Notebook.
**How would this example be used? Please describe.**
A website wants to train a semantic segmentation model and deploy it on AWS so that users can upload images on the website and the image can go to the trained semantic segmentation endpoint which returns a mask for floors in the image.
AWS Lambda, S3, Amazon SageMaker, API Gateway
**Describe what other services (other than SageMaker) are involved***
API Gateway, AWS Lambda, S3
**Describe which dataset could be used. Provide its location in s3://sagemaker-sample-files or another source.**
Pascal VOC2012 dataset - http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
Contributor guide
Research direction
No specific files or tests are named. Start by reviewing the repository's existing SageMaker Notebook examples and the requested AWS services—Lambda, S3, API Gateway, and SageMaker—to identify the closest integration pattern. Done should be a usable example showing an uploaded image reaching a semantic segmentation endpoint and returning a mask.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws, jupyter-notebook
- Domain
- backend-api-design, cloud, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 28/100