Amazon SageMaker

This model recognizes the welding action by identifying the light and sparks emitted by the process. The model operates under different lighting conditions. It can be utilized via a standard set of video surveillance cameras with low video resolution. It can be applied to measure the efficiency of welding worker operation.

Input

Supported content types: image/jpeg, image/png, application/x-image

Output

Content type: text/html Sample output:

b'0.9801'

Invoking endpoint

AWS CLI Command

You can invoke endpoint using AWS CLI:

aws sagemaker-runtime invoke-endpoint --endpoint-name "endpoint-name" --body fileb://input.jpg --content-type image/jpeg --accept text/html out.txt

Substitute the following parameters:

• "endpoint-name" - name of the inference endpoint where the model is deployed
• input.jpg - input image to do the inference on
• image/jpeg - MIME type of the given input image (above)
• out.txt - filename where the inference results are written to

Python

Real-time inference snippet (more detailed example can be found in sample notebook):

runtime = boto3.Session().client(service_name='runtime.sagemaker')
bytes_image = open('path-to-img', 'rb').read()
response = runtime.invoke_endpoint(EndpointName='endpoint-name', ContentType='image/jpeg', Body=bytes_image)
response = response['Body'].read()
welding_prob = float(response)

Resources

• Sample input images
• Sample Notebook

If you have any questions feel free to contact us info@agmis.eu or fill our https://agmis.lt/contacts/

Description
Sample Notebook
Sample Images