AWS Lambda 将图像文件发送到 Amazon Sagemaker [英] AWS Lambda send image file to Amazon Sagemaker

问题描述

我有下一个问题，我尝试将 base64 中的图像文件发送到 Lambda 函数(用 Python 编写)，以调用 Sagemaker Endpoint，这是我的 Lambda 函数:

I have the next problem, I try send image file in base64 to Lambda function(write in Python), for invoke Sagemaker Endpoint, this is my Lambda Function:

import os
import io
import boto3
import json
import base64

# grab environment variables
ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    print("Received event: " + json.dumps(event, indent=2))
    
    data = json.loads(json.dumps(event))
    payload = data['foto']
    img = base64.b64decode(payload)
    #body = json.dumps({"instances": img})

    try:
        response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,
                                            Body=img)
        print(response)
    except Exception as e:
        print("Inference Error:")
        print(e)

    return { "img":"ok" }

在 Jupyter 中调用 sagemaker 端点可以很好地使用此代码，

And sagemaker endpoint invoke in Jupyter works fine with this code,

from tensorflow.keras.preprocessing.image import ImageDataGenerator

test_datagen = ImageDataGenerator(rescale=1./255)
test_generator = test_datagen.flow_from_directory('./data/val', target_size=(224,224))

instance = test_generator[1][0]
print(instance.shape)
array = instance.reshape((1,) + instance.shape)
payload = { 'instances': array.tolist() }

resp = tf_predictor.predict(payload)['predictions']
print(resp)

Lambda 中的错误表示数据类型未知，以及维度中的 CloudWatch 错误.

The error in Lambda says that the data type is unknown, and CloudWatch error in dimensions.

我认为，错误出在 invoke_endpoint 方法的主体中，但我没有找到如何将字节类型转换为包含图像数据的列表.我需要带有 numpy 或其他库的自定义 Lambda 函数?或者没有必要

I think, that the error is in Body of invoke_endpoint method, but i not found how convert bytes type to list with image data. I need custom Lambda Function with numpy, or other library? or isn't necesary

推荐答案

解决方案很简单使用 bytes(img) 将 base64 转换为字节并将 ContentType='image/jpeg' 添加到调用端点.

Solution it simple Convert base64 to bytes with bytes(img) and add ContentType='image/jpeg' to the invoke endpoint.

经过两次小的更改后，您的 Lambda 函数现在应该是这样的:

After two small changes, This is how your Lambda function should look now:

import os
import io
import boto3
import json
import base64

# grab environment variables
ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    print("Received event: " + json.dumps(event, indent=2))

    data = json.loads(json.dumps(event))
    payload = data['foto']
    img = base64.b64decode(payload)
    
    payload = bytes(img) # convert base64 to bytes 

    try:
        response = runtime.invoke_endpoint
        (
            EndpointName=ENDPOINT_NAME,
            ContentType='image/jpeg' ,
            Body=payload
        )
        print(response)
    except Exception as e:
        print("Inference Error:")
        print(e)

    return {"img": "ok"}

这篇关于AWS Lambda 将图像文件发送到 Amazon Sagemaker的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！