Home
Back
Tensorflow.JS Console
// Define a model for linear regression. const model = tf.sequential(); model.add(tf.layers.dense({units: 1, inputShape: [1]})); // First layer (input) model.add(tf.layers.dense({units: 20, inputShape: [1]})); // Second layer (hidden) model.add(tf.layers.dense({units: 1, inputShape: [10]})); // Last layer (output) // Prepare the model for training: Specify the loss and the optimizer. model.compile({loss: 'meanSquaredError', optimizer: 'sgd'}); // Generate some synthetic data for training. const xs = tf.tensor2d([1, 2, 3, 4], [4, 1]); const ys = tf.tensor2d([1, 3, 5, 7], [4, 1]); // Train the model using the data. model.fit(xs, ys, {epochs: 50}).then(() => { // Use the model to do inference on a data point the model hasn't seen before: print(model.predict(tf.tensor2d([5], [1, 1]))); });
Pre-defined functions:
print(x): to print an input string x
max(a,b): to return the largest one
Array2d(r,c): return a 2D array of size [r,c]
dump2d(array): dump a 2D array
Peizhi Yan, All rights reserved.
2018