How to make inference to a keras model hosted on AWS SageMaker via AWS Lambda function?

Question

I have a pre-trained keras model which I have hosted on AWS using AWS SageMaker. I've got an endpoint and I can make successful predictions using the Amazon SageMaker Notebook instance.

What I do there is that I serve a .PNG image like the following and the model gives me correct prediction.

file= s3.Bucket(bucketname).download_file(filename_1, 'normal.png')
file_name_1='normal.png'


import sagemaker
from sagemaker.tensorflow.model import TensorFlowModel

endpoint = 'tensorflow-inference-0000-11-22-33-44-55-666' #endpoint

predictor=sagemaker.tensorflow.model.TensorFlowPredictor(endpoint, sagemaker_session)
data = np.array([resize(imread(file_name), (137, 310, 3))])
predictor.predict(data)

Now I wanted to make predictions using a mobile application. For that I wrote a Lambda function in python and attached an API gateway to it. My Lambda function is the following.

import os
import sys

CWD = os.path.dirname(os.path.realpath(__file__))
sys.path.insert(0, os.path.join(CWD, "lib"))

import json
import base64
import boto3
import numpy as np
from scipy import signal
from scipy.signal import butter, lfilter
from scipy.io import wavfile
import scipy.signal as sps
import io
from io import BytesIO
import matplotlib.pylab as plt
from matplotlib import pyplot as plt
import matplotlib.image as mpimg
from datetime import datetime
from skimage.io import imread
from skimage.transform import resize
from PIL import Image

ENDPOINT_NAME = 'tensorflow-inference-0000-11-22-33-44-55-666'
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    s3 = boto3.client("s3")
    
    # retrieving data from event.
    get_file_content_from_postman = event["content"]
    
    # decoding data.
    decoded_file_name = base64.b64decode(get_file_content_from_postman)
    
    image = Image.open(io.BytesIO(decoded_file_name))

    data = np.array([resize(imread(image), (137, 310, 3))])
    
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME, ContentType='text/csv', Body=data)
        
    result = json.loads(response['Body'].read().decode())
    
    return result

The third last line is giving me error 'PngImageFile' object has no attribute 'read'. Any idea what I am missing here?

Marcin · Accepted Answer · 2021-04-05 11:35:50Z

1

If io.BytesIO(decoded_file_name) correctly represents your image data (though the name decoded_file_name suggests that its only file name, not actual image data), then you don't need to use PIL. Just use it directly:

data = np.array([resize(imread(io.BytesIO(decoded_file_name)), (137, 310, 3))])

answered Apr 5, 2021 at 11:35

Marcin

241k16 gold badges315 silver badges368 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Muhammad Arsalan Hassan Over a year ago

Yes I've checked io.BytesIO(decoded_file_name) is representing image data. The problem is that when I make the request via API Gateway then it gives me error which is

"Parameter validation failed:\nInvalid type for parameter Body, value: [[[[0.25353752 0.39823243 0.91831497]\n   [0.25353752 0.39823243 0.91831497]\n ...   type: <class 'numpy.ndarray'>, valid types: <class 'bytes'>, <class 'bytearray'>, file-like object"

Marcin Over a year ago

@MuhammadArsalanHassan This is new issue. As I wrote before, you probably have multiple issues. Since your example is not-reproducible, you can only solve them one-by-one, rather then all at once.

Muhammad Arsalan Hassan · Accepted Answer · 2021-04-10 11:05:04Z

I was missing one thing which was causing this error. After receiving the image data I used python list and then json.dump that list (of lists). Below is the code for reference.

import os
import sys

CWD = os.path.dirname(os.path.realpath(__file__))
sys.path.insert(0, os.path.join(CWD, "lib"))

import json
import base64
import boto3
import numpy as np
import io
from io import BytesIO
from skimage.io import imread
from skimage.transform import resize

# grab environment variable of Lambda Function
ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    s3 = boto3.client("s3")
    
    # retrieving data from event.
    get_file_content_from_postman = event["content"]
    
    # decoding data.
    decoded_file_name = base64.b64decode(get_file_content_from_postman)
    
    data = np.array([resize(imread(io.BytesIO(decoded_file_name)), (137, 310, 3))])
    
    payload = json.dumps(data.tolist())
    
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME, ContentType='application/json', Body=payload)
        
    result = json.loads(response['Body'].read().decode())
    
    return result

Collectives™ on Stack Overflow

How to make inference to a keras model hosted on AWS SageMaker via AWS Lambda function?

2 Answers 2

2 Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

2 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related