Input

Supported content types: image/jpeg

Output

Content type: text/csv Sample output:

a
b
c
d
e

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/csv 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):

predictor = model.deploy(1, 'ml.m4.xlarge', endpoint_name='sign-language-recogniser-inference')
with open('input.jpg', 'rb') as file:
    bytes_image = file.read()
sign_language_recogniser_output = predictor.predict(bytes_image)
with open('data/inference_output', 'wb') as file:
    file.write(sign_language_recogniser_output) 
with open('data/inference_output') as f:
        results = f.readlines()
        print(results[0])

Resources

• Sample input images
• Sample Notebook