Modelos do TensorFlow


TesorFlow.js

Uma biblioteca JavaScript para

Treinamento e implantação de
modelos de aprendizado de máquina
no navegador


Modelos de Tensorflow

Modelos e camadas são blocos de construção importantes no Machine Learning .

Para diferentes tarefas de Machine Learning, você deve combinar diferentes tipos de camadas em um modelo que pode ser treinado com dados para prever valores futuros.

O TensorFlow.js oferece suporte a diferentes tipos de modelos e diferentes tipos de camadas.

Um modelo do TensorFlow é uma rede neural com uma ou mais camadas .


Um projeto Tensorflow

Um projeto do Tensorflow tem este fluxo de trabalho típico:

  • Coletando dados
  • Criando um modelo
  • Adicionando camadas ao modelo
  • Compilando o modelo
  • Treinando o Modelo
  • Usando o modelo

Exemplo

Suppose you knew a function that defined a strait line:

Y = 1.2X + 5

Then you could calculate any y value with the JavaScript formula:

y = 1.2 * x + 5;

To demonstrate Tensorflow.js, we could train a Tensorflow.js model to predict Y values based on X inputs.

The TensorFlow model does not know the function.

// Create Training Data
const xs = tf.tensor([0, 1, 2, 3, 4]);
const ys = xs.mul(1.2).add(5);

// Define a Linear Regression Model
const model = tf.sequential();
model.add(tf.layers.dense({units:1, inputShape:[1]}));

// Specify Loss and Optimizer
model.compile({loss:'meanSquaredError', optimizer:'sgd'});

// Train the Model
model.fit(xs, ys, {epochs:500}).then(() => {myFunction()});

// Use the Model
function myFunction() {
  const xArr = [];
  const yArr = [];
  for (let x = 0; x <= 10; x++) {
    xArr.push(x);
    let result = model.predict(tf.tensor([Number(x)]));
    result.data().then(y => {
      yArr.push(Number(y));
      if (x == 10) {plot(xArr, yArr)};
    });
  }
}

The example is explained below:


Collecting Data

Create a tensor (xs) with 5 x values:

const xs = tf.tensor([0, 1, 2, 3, 4]);

Create a tensor (ys) with 5 correct y answers (multiply xs with 1.2 and add 5):

const ys = xs.mul(1.2).add(5);

Creating a Model

Create a sequential mode:.

const model = tf.sequential();

In a sequential model, the output from one layer is the input to the next layer.


Adding Layers

Add one dense layer to the model.

The layer is only one unit (tensor) and the shape is 1 (one dimentional):

model.add(tf.layers.dense({units:1, inputShape:[1]}));

in a dense the layer, every node is connected to every node in the preceding layer.


Compiling the Model

Compile the model using meanSquaredError as loss function and sgd (stochastic gradient descent) as optimizer function:

model.compile({loss:'meanSquaredError', optimizer:'sgd'});

Tensorflow Optimizers

  • Adadelta -Implements the Adadelta algorithm.
  • Adagrad - Implements the Adagrad algorithm.
  • Adam - Implements the Adam algorithm.
  • Adamax - Implements the Adamax algorithm.
  • Ftrl - Implements the FTRL algorithm.
  • Nadam - Implements the NAdam algorithm.
  • Optimizer - Base class for Keras optimizers.
  • RMSprop - Implements the RMSprop algorithm.
  • SGD - Stochastic Gradient Descent Optimizer.

Training the Model

Train the model (using xs and ys) with 500 repeats (epochs):

model.fit(xs, ys, {epochs:500}).then(() => {myFunction()});

Using the Model

After the model is trained, you can use it for many different purposes.

This example predicts 10 y values, given 10 x values, and calls a function to plot the predictions in a graph:

function myFunction() {
  const xArr = [];
  const yArr = [];
  for (let x = 0; x <= 10; x++) {
    let result = model.predict(tf.tensor([Number(x)]));
    result.data().then(y => {
      xArr.push(x);
      yArr.push(Number(y));
      if (x == 10) {display(xArr, yArr)};
    });
  }
}

This example predicts 10 y values, given 10 x values, and calls a function to display the values:

function myFunction() {
  const xArr = [];
  const yArr = [];
  for (let x = 0; x <= 10; x++) {
    let result = model.predict(tf.tensor([Number(x)]));
    result.data().then(y => {
      xArr.push(x);
      yArr.push(Number(y));
      if (x == 10) {display(xArr, yArr)};
    });
  }
}