Hi team,
AWS Rekognition - Detect Labels returns empty results.
This is the result of n8n node:
This is the result of Postman request:
Also, I’ve tested to send incorrect data to both bucket and object name the result was same empty result.
Thank you for your help.
Hi @samaritan, I am very sorry to hear you’re having trouble with the node. I was able to reproduce the problem and have added it to our backlog for a closer look. We’ll keep you updated on the progress.
Hi @samaritan. How is going?
Did you solve or work around this issue?
I have the same problem.
Thank you
I coded a Lambda function that can be triggered via API, and I’m using HTTP Request to process my images. If this work around is ok for you, I can share my code.
Thanks
Perhaps @sirdavidoff can share an also share an update on where we are with the bugfix, seeing peeps keep running into this?
Hi,
This is the code I’m using in Lambda. Please don’t forget to set Lambda roles for accessing S3 bucket and Rekognition service.
#Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-custom-labels-developer-guide/blob/master/LICENSE-SAMPLECODE.)
import boto3
import io
from decimal import Decimal
import json
import urllib.request
import urllib.parse
import urllib.error
def show_custom_labels(model,bucket,photo, min_confidence):
client=boto3.client('rekognition')
response = client.detect_custom_labels(Image={'S3Object': {'Bucket': bucket, 'Name': photo}},
MinConfidence=min_confidence,
ProjectVersionArn=model)
return response['CustomLabels']
def lambda_handler(event,context):
req = json.loads(event['body'])
bucket = req['bucketName']
key = req['object']
photo=key
model='<<YOUR MODEL ARN>>'
min_confidence=10
try:
label_count=show_custom_labels(model,bucket,photo, min_confidence)
return {
'statusCode': 200,
'headers': {'Content-Type': 'application/json'},
'body': json.dumps(label_count)
}
except Exception as err:
return {
'statusCode': 200,
'headers': {'Content-Type': 'application/json'},
'body': json.dumps(str(err))
}
if __name__ == "__main__":
main()
Thank you a lot @samaritan
i’ll implement and return were to share with you my result.
Best Reguards
Hi @samaritan
I adapted your code to Detect Moderation Labels and work fine.
Thank you again
#Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-custom-labels-developer-guide/blob/master/LICENSE-SAMPLECODE.)
import boto3
import io
from decimal import Decimal
import json
import urllib.request
import urllib.parse
import urllib.error
def shows_detect_moderation_labels(bucket,photo, min_confidence):
client=boto3.client('rekognition')
response = client.detect_moderation_labels(Image={'S3Object': {'Bucket': bucket, 'Name': photo}},
MinConfidence=min_confidence)
return response['ModerationLabels']
def lambda_handler(event,context):
bucket = event.get('bucketName')
key = event.get('object')
photo=key
min_confidence=50
try:
label_count=shows_detect_moderation_labels(bucket,photo, min_confidence)
return {
'statusCode': 200,
'headers': {'Content-Type': 'application/json'},
'body': (label_count)
#'body': json.dumps(label_count)
}
except Exception as err:
return {
'statusCode': 400,
'headers': {'Content-Type': 'application/json'},
'body': json.dumps(str(err))
}
if __name__ == "__main__":
main()