机器学习模型中的无效元素类型

Question

我使用的是 @tensorflow/tfjs 的简单模型，它只显示准确性。相同的代码在代码沙箱中运行时不会给出任何错误，而在运行中它在 visual studio 代码中会发生不变类型错误。我的代码附在下面。还指导有关代码中使用的输入形状和单位术语以及如何在 React Native 中实现此代码。

import '@tensorflow/tfjs-react-native'
import * as tf from "@tensorflow/tfjs";
import * as ft from '@tensorflow/tfjs-backend-webgpu';
//import { writeFileSync, readFileSync } from 'fs';

(async() => {
  await ft.ready 
 // then do all operations on the backend
})()


const model = tf.sequential({
  layers: [
    tf.layers.dense({ inputShape: [784], units: 32, activation: "relu" }),
    tf.layers.dense({ units: 10, activation: "softmax" })
  ]
});
model.weights.forEach(w => {
  console.log(w.name, w.shape);
});
model.weights.forEach(w => {
  const newVals = tf.randomNormal(w.shape);
  // w.val is an instance of tf.Variable
  w.val.assign(newVals);
});
model.compile({
  optimizer: "sgd",
  loss: "categoricalCrossentropy",
  metrics: ["accuracy"]
});
const data = tf.randomNormal([100, 784]);
const labels = tf.randomUniform([100, 10]);

function onBatchEnd(batch, logs) {
  console.log("Accuracy", logs.acc);
}

// Train for 5 epochs with batch size of 32.
model
  .fit(data, labels, {
    epochs: 5,
    batchSize: 32,
    callbacks: { onBatchEnd }
  })
  .then(info => {
    console.log("Final accuracy", info.history.acc);
  });

错误

Answer 1

您需要导入 @tensorflow/tfjs-react-native 包。此外，如果后端是异步的，则应使用 tf.ready() 这是您的 React 应用程序的示例

import * as tf from '@tensorflow/tfjs';
import '@tensorflow/tfjs-react-native';

export class App extends React.Component {
  constructor(props) {
    super(props);
    this.state = {
      isTfReady: false,
    };
  }

  init() {
    const model = tf.sequential({
        layers: [
            tf.layers.dense({
                inputShape: [784],
                units: 32,
                activation: "relu"
            }),
            tf.layers.dense({
                units: 10,
                activation: "softmax"
            })
        ]
    });
    model.weights.forEach(w => {
        console.log(w.name, w.shape);
    });
    model.weights.forEach(w => {
        const newVals = tf.randomNormal(w.shape);
        // w.val is an instance of tf.Variable
        w.val.assign(newVals);
    });
    model.compile({
        optimizer: "sgd",
        loss: "categoricalCrossentropy",
        metrics: ["accuracy"]
    });
    const data = tf.randomNormal([100, 784]);
    const labels = tf.randomUniform([100, 10]);

    function onBatchEnd(batch, logs) {
        console.log("Accuracy", logs.acc);
    }

    // Train for 5 epochs with batch size of 32.
    model
        .fit(data, labels, {
            epochs: 5,
            batchSize: 32,
            callbacks: {
                onBatchEnd
            }
        })
        .then(info => {
            console.log("Final accuracy", info.history.acc);
        });
  }

  async componentDidMount() {
    // Wait for tf to be ready.
    await tf.ready();
    // Signal to the app that tensorflow.js can now be used.
    this.setState({
      isTfReady: true,
    });
  }


  render() {
    init()
    //
  }
}

机器学习模型中的无效元素类型

inavalid element type in machine learning model

javascript

react-native

machine-learning

tensorflow.js