Python 从node.js调用Sagemaker Tensorflow Resnet50端点

问题

我想知道node.js中与此Python代码等效的代码：

from keras.preprocessing import image
from PIL import Image
from keras.applications.resnet50 import preprocess_input

raw_img = image.load_img("some/path").resize((224, 224), Image.NEAREST)
img = preprocess_input(image.img_to_array(raw_img))

上下文

我将Keras的ResNet50模型上传到SageMaker端点。我可以使用下面的代码从Python调用它：

import json
import boto3
import numpy as np
import io

client = boto3.client('runtime.sagemaker')

from keras.preprocessing import image
from PIL import Image
from keras.applications.resnet50 import preprocess_input

raw_img = image.load_img("some/path").resize((224, 224), Image.NEAREST)
img = preprocess_input(image.img_to_array(raw_img))

response = client.invoke_endpoint(
  EndpointName="SAGEMAKER_ENDPOINT_NAME",
  Body=json.dumps({ "instances": [ img.tolist() ] }),
  ContentType="application/json"
)

现在我需要在node.js中执行同样的操作。我找到了如何使用aws sdk访问端点的方法：

import * as aws from 'aws-sdk';
const sageMaker = new aws.SageMakerRuntime({
  region: 'ap-northeast-1'
});
sageMaker.invokeEndpoint({
  EndpointName: endpointName,
  Body: input,
  ContentType: "application/json",
}, (error, res) => {
  if (error) { return reject(error); }
  // YEAH
})

但是我不知道如何生成

输入

json，也就是说，相当于这个python片段：

from keras.preprocessing import image
from PIL import Image
from keras.applications.resnet50 import preprocess_input

raw_img = image.load_img("some/path").resize((224, 224), Image.NEAREST)
img = preprocess_input(image.img_to_array(raw_img))

---

是否有任何库可以实现同样的效果，或者我需要重新发明轮子？

答案是：我必须重新发明一半轮子。 以下是到达端点所需的工作（对于ResNet50网络）：

• 将源图像解码为像素
• 转换为3个通道（删除
• 调整大小为224x224
• 将像素规格化为[-1,1]
• 转换为三维阵列（SageMaker中的默认格式）

下面是我最后得到的代码（使用typescript）：

这使用了一些实用函数

getImagePixels

async function getImagePixels(filePath: string) {
  const _getPixels = require('get-pixels');
  return new Promise<IImagePixels>( (resolve, reject) => {
    _getPixels( filePath, (error: Error | null, pixels: ndarray) => {
      if (error) { return reject(error); }

      resolve({
        width: pixels.shape[0],
        height: pixels.shape[1],
        numberOfChannels: pixels.shape[2],
        pixels: pixels
      })
    });
  })
}

异步函数getImagePixels（文件路径：字符串）{ const_getPixels=require（'get-pixels'）； 返回新承诺（（解决、拒绝）=>{ _getPixels（文件路径，（错误：error | null，像素：ndarray）=>{ if（error）{返回拒绝（error）；} 决心({ 宽度：像素。形状[0]， 高度：像素。形状[1]， NumberOfChannel:像素。形状[2]， 像素：像素 }) }); }) } 图像传感器

import ndarray from 'ndarray';

function imageToTensor(img: IImagePixels, o: INormalizationOptions) {
  const rawTensorValues = new Int32Array(img.width * img.height * o.numberOfChannels);
  const rawTensor = tf.tensor3d(rawTensorValues, [ img.width, img.height, o.numberOfChannels ], 'int32');

  // This only uses the first CHANNEL_ND
  for (let row=0; row<img.height; row++) {
    for (let col=0; col<img.width; col++){
      for (let channel =0; channel<o.numberOfChannels; channel++) {
        const pixel = img.pixels.get(row,col,channel);
        if (!isNumeric(pixel)) { throw new Error(`Bad pixel: ${pixel}`) }
        const offset = row * img.width * img.numberOfChannels + col * img.numberOfChannels + channel
        rawTensorValues[offset] = pixel;
      }
    }
  }

  return rawTensor;
}

从“ndarray”导入ndarray；
功能图像传感器（img:IImagePixels，o:INormalizationOptions）{
const rawTensorValues=新的INT32阵列（img.width*img.height*o.numberOfChannels）；
常量rawTensor=tf.tensor3d（rawTensorValues，[img.width，img.height，o.numberOfChannels]，'int32'）；
//这只使用第一个通道
for（设行=0；行
import ndarray from 'ndarray';

function imageToTensor(img: IImagePixels, o: INormalizationOptions) {
  const rawTensorValues = new Int32Array(img.width * img.height * o.numberOfChannels);
  const rawTensor = tf.tensor3d(rawTensorValues, [ img.width, img.height, o.numberOfChannels ], 'int32');

  // This only uses the first CHANNEL_ND
  for (let row=0; row<img.height; row++) {
    for (let col=0; col<img.width; col++){
      for (let channel =0; channel<o.numberOfChannels; channel++) {
        const pixel = img.pixels.get(row,col,channel);
        if (!isNumeric(pixel)) { throw new Error(`Bad pixel: ${pixel}`) }
        const offset = row * img.width * img.numberOfChannels + col * img.numberOfChannels + channel
        rawTensorValues[offset] = pixel;
      }
    }
  }

  return rawTensor;
}

async function tensor3dToArray3d(t: tf.Tensor3D) {
  const dataAs3dArray = new Array<number[][]>();
  const data = await t.data();

  const expectedSizeOfArray = t.shape[0] * t.shape[1] * t.shape[2];


  console.log(`Got vector of size ${t.shape[0]} ${t.shape[1]} ${t.shape[2]}, that is, ${expectedSizeOfArray} data`);
  console.log(`Actual size of data: ${data.length}`);

  for (let i=0; i<t.shape[0]; i++) {
    dataAs3dArray[i] = new Array<number[]>();
    for (let j=0; j<t.shape[1]; j++) {
      dataAs3dArray[i][j] = new Array<number>();
      for (let k=0; k<t.shape[2]; k++ ) {
        const ijk =
            i * t.shape[0] * t.shape[1] * t.shape[2]
          + j * t.shape[1] * t.shape[2]
          + k;

        const datum = Math.random(); // Number( data[ijk] );
        if (!isNumeric(datum)) { throw new Error(`Invalid datum at ${i},${j},${k}: ${datum}`) }
        dataAs3dArray[i][j][k] = datum;
      }
    }
  }
  return dataAs3dArray;
}

function isNumeric(n: any) {
  return !isNaN(parseFloat(n)) && isFinite(n);
}