model.py

#!/usr/bin/env python
"""This file contains all the model information: the training steps, the batch size and the model iself."""

import tensorflow as tf


def get_training_steps():
    """Returns the number of batches that will be used to train your solution.
    It is recommended to change this value."""
    return 50


def get_batch_size():
    """Returns the batch size that will be used by your solution.
    It is recommended to change this value."""
    return 20

def solution(features, labels, mode):
    """Returns an EstimatorSpec that is constructed using the solution that you have to write below."""
    # Input Layer (a batch of images that have 64x64 pixels and are RGB colored (3)
    input_layer = tf.reshape(features["x"], [-1, 64, 64, 3])

    # TODO: Code of your solution
    # Convolutional Layer #1
    conv1 = tf.layers.conv2d(
        inputs=input_layer,
        filters=32,
        kernel_size=[5, 5],
        padding="same",
        activation=tf.nn.relu)

    # Pooling Layer #1
    pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

    # Convolutional Layer #2 and Pooling Layer #2
    conv2 = tf.layers.conv2d(
        inputs=pool1,
        filters=64,
        kernel_size=[5, 5],
        padding="same",
        activation=tf.nn.relu)
    pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

    # Dense Layer
    pool2_flat = tf.reshape(pool2, [-1, 8 * 8 * 64])
    dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
    dropout = tf.layers.dropout(
        inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

    # Logits Layer
    logits = tf.layers.dense(inputs=dropout, units=4)

    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:
        # TODO: return tf.estimator.EstimatorSpec with prediction values of all classes
        return tf.estimator.EstimatorSpec(mode, predictions=predictions)

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

    if mode == tf.estimator.ModeKeys.TRAIN:
        # TODO: Let the model train here
        # TODO: return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
        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)

    if mode == tf.estimator.ModeKeys.EVAL:
        # The classes variable below exists of an tensor that contains all the predicted classes in a batch
        # TODO: eval_metric_ops = {"accuracy": tf.metrics.accuracy(labels=labels, predictions=classes)}
        # TODO: return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
        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)