MeanTeacher in a custom TF estimator

mean_estimator.py

#!/usr/bin/env python
#  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.
"""An Example of a custom Estimator for the Iris dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import tensorflow as tf

import iris_data

parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=100, type=int, help='batch size')
parser.add_argument('--train_steps', default=1000, type=int,
                    help='number of training steps')


def my_net(inputs, params, ema=None, scope='net'):
    ''' build network, optionally get exponential moving average of params '''
    if ema is None:
        reuse = tf.AUTO_REUSE
        getter = None
    else:
        reuse = True
        def getter(getter, name, *args, **kwargs):  # noqa
            var = getter(name, *args, **kwargs)
            ema_var = ema.average(var)
            return ema_var if ema_var else var
    with tf.variable_scope(scope, reuse=reuse, custom_getter=getter):
        net = tf.identity(inputs)
        for units in params['hidden_units']:
            net = tf.layers.dense(net, units=units, activation=tf.nn.relu)
        logits = tf.layers.dense(net, params['n_classes'], activation=None)
    return logits


def my_model(features, labels, mode, params):
    """DNN with three hidden layers, and dropout of 0.1 probability."""
    # Create three fully connected layers each layer having a dropout
    # probability of 0.1.
    inputs = tf.feature_column.input_layer(features, params['feature_columns'])
    logits = my_net(inputs, params)
    # exponential moving average
    with tf.variable_scope('ema'):
        ema = tf.train.ExponentialMovingAverage(decay=0.999)
    ema_op = ema.apply(tf.trainable_variables())
    tf.add_to_collection(tf.GraphKeys.UPDATE_OPS, ema_op)
    teacher = tf.stop_gradient(my_net(inputs, params, ema=ema))

    # Compute predictions.
    predicted_classes = tf.argmax(logits, 1)
    if mode == tf.estimator.ModeKeys.PREDICT:
        predictions = {
            'class_ids': predicted_classes[:, tf.newaxis],
            'probabilities': tf.nn.softmax(logits),
            'logits': logits,
            'teacher': teacher,
        }
        return tf.estimator.EstimatorSpec(mode, predictions=predictions)

    # Compute loss.
    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
    loss += tf.losses.mean_squared_error(teacher, logits)

    # Compute evaluation metrics.
    accuracy = tf.metrics.accuracy(labels=labels,
                                   predictions=predicted_classes,
                                   name='acc_op')
    metrics = {'accuracy': accuracy}
    tf.summary.scalar('accuracy', accuracy[1])

    if mode == tf.estimator.ModeKeys.EVAL:
        return tf.estimator.EstimatorSpec(
            mode, loss=loss, eval_metric_ops=metrics)

    # Create training op.
    assert mode == tf.estimator.ModeKeys.TRAIN

    optimizer = tf.train.AdagradOptimizer(learning_rate=0.1)
    with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
        train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)


def main(argv):
    args = parser.parse_args(argv[1:])

    # Fetch the data
    (train_x, train_y), (test_x, test_y) = iris_data.load_data()

    # Feature columns describe how to use the input.
    my_feature_columns = []
    for key in train_x.keys():
        my_feature_columns.append(tf.feature_column.numeric_column(key=key))

    # Build 2 hidden layer DNN with 10, 10 units respectively.
    classifier = tf.estimator.Estimator(
        model_fn=my_model,
        params={
            'feature_columns': my_feature_columns,
            # Two hidden layers of 10 nodes each.
            'hidden_units': [10, 10],
            # The model must choose between 3 classes.
            'n_classes': 3,
        })

    # Train the Model.
    classifier.train(
        input_fn=lambda:iris_data.train_input_fn(train_x, train_y, args.batch_size),
        steps=args.train_steps)

    # Evaluate the model.
    eval_result = classifier.evaluate(
        input_fn=lambda:iris_data.eval_input_fn(test_x, test_y, args.batch_size))

    print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))

    # Generate predictions from the model
    expected = ['Setosa', 'Versicolor', 'Virginica']
    predict_x = {
        'SepalLength': [5.1, 5.9, 6.9],
        'SepalWidth': [3.3, 3.0, 3.1],
        'PetalLength': [1.7, 4.2, 5.4],
        'PetalWidth': [0.5, 1.5, 2.1],
    }

    predictions = classifier.predict(
        input_fn=lambda:iris_data.eval_input_fn(predict_x,
                                                labels=None,
                                                batch_size=args.batch_size))

    for pred_dict, expec in zip(predictions, expected):
        template = ('\nPrediction is "{}" ({:.1f}%), expected "{}"')

        class_id = pred_dict['class_ids'][0]
        probability = pred_dict['probabilities'][class_id]

        print(template.format(iris_data.SPECIES[class_id],
                              100 * probability, expec))


if __name__ == '__main__':
    tf.logging.set_verbosity(tf.logging.INFO)
    tf.app.run(main)