mnist.js

/**
 * @license
 * Copyright 2018 Google LLC. All Rights Reserved.
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 * =============================================================================
 */

import * as tf from '@tensorflow/tfjs';

import {MnistData} from './data';

const model = tf.sequential();

model.add(tf.layers.conv2d({
  inputShape: [28, 28, 1],
  kernelSize: 5,
  filters: 8,
  strides: 1,
  activation: 'relu',
  kernelInitializer: 'varianceScaling'
}));
model.add(tf.layers.maxPooling2d({poolSize: [2, 2], strides: [2, 2]}));
model.add(tf.layers.conv2d({
  kernelSize: 5,
  filters: 16,
  strides: 1,
  activation: 'relu',
  kernelInitializer: 'varianceScaling'
}));
model.add(tf.layers.maxPooling2d({poolSize: [2, 2], strides: [2, 2]}));
model.add(tf.layers.flatten());
model.add(tf.layers.dense(
    {units: 10, kernelInitializer: 'varianceScaling', activation: 'softmax'}));

const LEARNING_RATE = 0.15;
const optimizer = tf.train.sgd(LEARNING_RATE);
model.compile({
  optimizer: optimizer,
  loss: 'categoricalCrossentropy',
  metrics: ['accuracy'],
});

const BATCH_SIZE = 64;
const TRAIN_BATCHES = 150;

// Every few batches, test accuracy over many examples. Ideally, we'd compute
// accuracy over the whole test set, but for performance we'll use a subset.
const TEST_BATCH_SIZE = 1000;
const TEST_ITERATION_FREQUENCY = 5;

async function train() {
  //ui.isTraining();

  const lossValues = [];
  const accuracyValues = [];

  for (let i = 0; i < TRAIN_BATCHES; i++) {
    const batch = data.nextTrainBatch(BATCH_SIZE);

    let testBatch;
    let validationData;
    // Every few batches test the accuracy of the mode.
    if (i % TEST_ITERATION_FREQUENCY === 0) {
      testBatch = data.nextTestBatch(TEST_BATCH_SIZE);
      validationData = [
        testBatch.xs.reshape([TEST_BATCH_SIZE, 28, 28, 1]), testBatch.labels
      ];
    }

    // The entire dataset doesn't fit into memory so we call fit repeatedly
    // with batches.
    const history = await model.fit(
        batch.xs.reshape([BATCH_SIZE, 28, 28, 1]), batch.labels,
        {batchSize: BATCH_SIZE, validationData, epochs: 1});

    const loss = history.history.loss[0];
    const accuracy = history.history.acc[0];

    // Plot loss / accuracy.
    lossValues.push({'batch': i, 'loss': loss, 'set': 'train'});
    //ui.plotLosses(lossValues);

    if (testBatch != null) {
      accuracyValues.push({'batch': i, 'accuracy': accuracy, 'set': 'train'});
      //ui.plotAccuracies(accuracyValues);
    }

    batch.xs.dispose();
    batch.labels.dispose();
    if (testBatch != null) {
      testBatch.xs.dispose();
      testBatch.labels.dispose();
    }

    await tf.nextFrame();
  }
}

function showTestResults(batch, predictions, labels) {
  const testExamples = batch.xs.shape[0];
  let totalCorrect = 0;

  for (let i = 0; i < testExamples; i++) {
    const prediction = predictions[i];
    const label = labels[i];
    const correct = prediction === label;
    if (correct) totalCorrect++;

    console.log(`pred: ${prediction} - ${correct}`);
  }

  console.log(`${totalCorrect}/${testExamples} => ${(totalCorrect/testExamples) * 100.0}% correct`);
}

async function showPredictions() {
  const testExamples = 100;
  const batch = data.nextTestBatch(testExamples);

  tf.tidy(() => {
    const output = model.predict(batch.xs.reshape([-1, 28, 28, 1]));

    const axis = 1;
    const labels = Array.from(batch.labels.argMax(axis).dataSync());
    const predictions = Array.from(output.argMax(axis).dataSync());

    showTestResults(batch, predictions, labels);
  });
}

let data;
async function load() {
  data = new MnistData();
  await data.load();
}

export async function mnist() {
  await load();
  await train();
  showPredictions();
}

mnist.py

#  Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
#  limitations under the License.
"""Convolutional Neural Network Estimator for MNIST, built with tf.layers."""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import tensorflow as tf

tf.logging.set_verbosity(tf.logging.INFO)


def cnn_model_fn(features, labels, mode):
  """Model function for CNN."""
  # Input Layer
  # Reshape X to 4-D tensor: [batch_size, width, height, channels]
  # MNIST images are 28x28 pixels, and have one color channel
  input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

  # Convolutional Layer #1
  # Computes 32 features using a 5x5 filter with ReLU activation.
  # Padding is added to preserve width and height.
  # Input Tensor Shape: [batch_size, 28, 28, 1]
  # Output Tensor Shape: [batch_size, 28, 28, 32]
  conv1 = tf.layers.conv2d(
      inputs=input_layer,
      filters=32,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #1
  # First max pooling layer with a 2x2 filter and stride of 2
  # Input Tensor Shape: [batch_size, 28, 28, 32]
  # Output Tensor Shape: [batch_size, 14, 14, 32]
  pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

  # Convolutional Layer #2
  # Computes 64 features using a 5x5 filter.
  # Padding is added to preserve width and height.
  # Input Tensor Shape: [batch_size, 14, 14, 32]
  # Output Tensor Shape: [batch_size, 14, 14, 64]
  conv2 = tf.layers.conv2d(
      inputs=pool1,
      filters=64,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #2
  # Second max pooling layer with a 2x2 filter and stride of 2
  # Input Tensor Shape: [batch_size, 14, 14, 64]
  # Output Tensor Shape: [batch_size, 7, 7, 64]
  pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

  # Flatten tensor into a batch of vectors
  # Input Tensor Shape: [batch_size, 7, 7, 64]
  # Output Tensor Shape: [batch_size, 7 * 7 * 64]
  pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])

  # Dense Layer
  # Densely connected layer with 1024 neurons
  # Input Tensor Shape: [batch_size, 7 * 7 * 64]
  # Output Tensor Shape: [batch_size, 1024]
  dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)

  # Add dropout operation; 0.6 probability that element will be kept
  dropout = tf.layers.dropout(
      inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

  # Logits layer
  # Input Tensor Shape: [batch_size, 1024]
  # Output Tensor Shape: [batch_size, 10]
  logits = tf.layers.dense(inputs=dropout, units=10)

  predictions = {
      # Generate predictions (for PREDICT and EVAL mode)
      "classes": tf.argmax(input=logits, axis=1),
      # Add `softmax_tensor` to the graph. It is used for PREDICT and by the
      # `logging_hook`.
      "probabilities": tf.nn.softmax(logits, name="softmax_tensor")
  }
  if mode == tf.estimator.ModeKeys.PREDICT:
    return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

  # Calculate Loss (for both TRAIN and EVAL modes)
  loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

  # Configure the Training Op (for TRAIN mode)
  if mode == tf.estimator.ModeKeys.TRAIN:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
    train_op = optimizer.minimize(
        loss=loss,
        global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)

  # Add evaluation metrics (for EVAL mode)
  eval_metric_ops = {
      "accuracy": tf.metrics.accuracy(
          labels=labels, predictions=predictions["classes"])}
  return tf.estimator.EstimatorSpec(
      mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)


def main(unused_argv):
  # Load training and eval data
  mnist = tf.contrib.learn.datasets.load_dataset("mnist")
  train_data = mnist.train.images  # Returns np.array
  train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
  eval_data = mnist.test.images  # Returns np.array
  eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)

  # Create the Estimator
  mnist_classifier = tf.estimator.Estimator(
      model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")

  # Set up logging for predictions
  # Log the values in the "Softmax" tensor with label "probabilities"
  tensors_to_log = {"probabilities": "softmax_tensor"}
  logging_hook = tf.train.LoggingTensorHook(
      tensors=tensors_to_log, every_n_iter=50)

  # Train the model
  train_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      batch_size=100,
      num_epochs=None,
      shuffle=True)
  mnist_classifier.train(
      input_fn=train_input_fn,
      steps=20000,
      hooks=[logging_hook])

  # Evaluate the model and print results
  eval_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": eval_data},
      y=eval_labels,
      num_epochs=1,
      shuffle=False)
  eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
  print(eval_results)


if __name__ == "__main__":
  tf.app.run()