Amazon Bedrock Titan 이미지 생성기로 Amazon Rekognition 데이터 세트 만들기

prompt = "photo-realistic"
negative_prompt = "bad quality, low resolution, cartoon"
numberOfImages = 1   # Range: 1 to 5 
quality = "standard" # Options: standard or premium
height = 512        # Supported height list in the docs 
width = 512          # Supported width list in the docs
cfgScale = 6      # Range: 1.0 (exclusive) to 10.0
seed = 2000     # Range: 0 to 214783647

body = json.dumps(
    {
        "taskType": "IMAGE_VARIATION",
        "imageVariationParams": {
             "text": prompt,  # Optional,
             "negativeText": negative_prompt,   # Optional,
             "images": [image_to_base64(original)], # One image is required
         },
        "imageGenerationConfig": {
            "numberOfImages": numberOfImages,   
            "quality": quality,  
            "height": height,
            "width": width,
            "cfgScale": cfgScale, 
            "seed": seed 
        }
    }
)

modelId = "amazon.titan-image-generator-v1"

response = bedrock_runtime.invoke_model(
    body=body, 
    modelId=modelId,
    accept="application/json", 
    contentType="application/json"
)
response_body = json.loads(response.get("body").read())

images = [Image.open(BytesIO(base64.b64decode(base64_image))) for base64_image in response_body.get("images")]

def image_to_base64(img) -> str:
    """Convert a PIL Image or local image file path to a base64 string for Amazon Bedrock"""
    if isinstance(img, str):
        if os.path.isfile(img):
            print(f"Reading image from file: {img}")
            with open(img, "rb") as f:
                return base64.b64encode(f.read()).decode("utf-8")
        else:
            raise FileNotFoundError(f"File {img} does not exist")
    elif isinstance(img, Image.Image):
        buffer = io.BytesIO()
        img.save(buffer, format="PNG")
        return base64.b64encode(buffer.getvalue()).decode("utf-8")
    else:
        raise ValueError(f"Expected str (filename) or PIL Image. Got {type(img)}")

response = bedrock_runtime.invoke_model(
    body=body, 
    modelId=modelId,
    accept="application/json", 
    contentType="application/json"
)
response_body = json.loads(response.get("body").read())
images = [Image.open(BytesIO(base64.b64decode(base64_image))) for base64_image in response_body.get("images")]

for index, img in enumerate(images):
    IMAGE_KEY = prefix + "random_generated_" + datetime.today().strftime("%Y-%m-%d-%H:%M:%S") + "-" + str(index) + ".png"
    in_mem_file = io.BytesIO()
    img.save(in_mem_file, format=img.format)
    in_mem_file.seek(0)
    s3.upload_fileobj(
        Fileobj=in_mem_file,
        Bucket=BUCKET,
        Key=IMAGE_KEY,
        ExtraArgs={"ContentType":"image/png"},
        Callback=None,
        Config=None)        

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "AWSRekognitionS3AclBucketRead20191011",
            "Effect": "Allow",
            "Principal": {
                "Service": "rekognition.amazonaws.com"
            },
            "Action": [
                "s3:GetBucketAcl",
                "s3:GetBucketLocation"
            ],
            "Resource": "arn:aws:s3:::<YOUR BUCKET>"
        },
        {
            "Sid": "AWSRekognitionS3GetBucket20191011",
            "Effect": "Allow",
            "Principal": {
                "Service": "rekognition.amazonaws.com"
            },
            "Action": [
                "s3:GetObject",
                "s3:GetObjectAcl",
                "s3:GetObjectVersion",
                "s3:GetObjectTagging"
            ],
            "Resource": "arn:aws:s3:::<YOUR BUCKET>/*"
        },
        {
            "Sid": "AWSRekognitionS3ACLBucketWrite20191011",
            "Effect": "Allow",
            "Principal": {
                "Service": "rekognition.amazonaws.com"
            },
            "Action": "s3:GetBucketAcl",
            "Resource": "arn:aws:s3:::<YOUR BUCKET>"
        },
        {
            "Sid": "AWSRekognitionS3PutObject20191011",
            "Effect": "Allow",
            "Principal": {
                "Service": "rekognition.amazonaws.com"
            },
            "Action": "s3:PutObject",
            "Resource": "arn:aws:s3:::<YOUR BUCKET>/*",
            "Condition": {
                "StringEquals": {
                    "s3:x-amz-acl": "bucket-owner-full-control"
                }
            }
        }
    ]
}

#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 PIL import Image, ImageDraw, ExifTags, ImageColor, ImageFont

def display_image(bucket,photo,response):
    # Load image from S3 bucket
    s3_connection = boto3.resource('s3')

    s3_object = s3_connection.Object(bucket,photo)
    s3_response = s3_object.get()

    stream = io.BytesIO(s3_response['Body'].read())
    image=Image.open(stream)

    # Ready image to draw bounding boxes on it.
    imgWidth, imgHeight = image.size
    draw = ImageDraw.Draw(image)

    # calculate and display bounding boxes for each detected custom label
    print('Detected custom labels for ' + photo)
    for customLabel in response['CustomLabels']:
        print('Label ' + str(customLabel['Name']))
        print('Confidence ' + str(customLabel['Confidence']))
        if 'Geometry' in customLabel:
            box = customLabel['Geometry']['BoundingBox']
            left = imgWidth * box['Left']
            top = imgHeight * box['Top']
            width = imgWidth * box['Width']
            height = imgHeight * box['Height']

            fnt = ImageFont.truetype('/Library/Fonts/Arial.ttf', 50)
            draw.text((left,top), customLabel['Name'], fill='#00d400', font=fnt)

            print('Left: ' + '{0:.0f}'.format(left))
            print('Top: ' + '{0:.0f}'.format(top))
            print('Label Width: ' + "{0:.0f}".format(width))
            print('Label Height: ' + "{0:.0f}".format(height))

            points = (
                (left,top),
                (left + width, top),
                (left + width, top + height),
                (left , top + height),
                (left, top))
            draw.line(points, fill='#00d400', width=5)

    image.show()

def show_custom_labels(model,bucket,photo, min_confidence):
    client=boto3.client('rekognition')

    #Call DetectCustomLabels
    response = client.detect_custom_labels(Image={'S3Object': {'Bucket': bucket, 'Name': photo}},
        MinConfidence=min_confidence,
        ProjectVersionArn=model)

    # For object detection use case, uncomment below code to display image.
    # display_image(bucket,photo,response)

    return len(response['CustomLabels'])

def main():

    bucket='MY_BUCKET'
    photo='MY_IMAGE_KEY'
    model='arn:aws:rekognition:us-east-1:<YOUR ACCOUNT>:project/<YOUR PROJECT>/version/damangedBoxPjt1.2023-12-06T23.34.44/1701873284276'
    min_confidence=95

    label_count=show_custom_labels(model,bucket,photo, min_confidence)
    print("Custom labels detected: " + str(label_count))


if __name__ == "__main__":
    main()