%matplotlib inline

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', validation_size=0)

img = mnist.train.images[2]
plt.imshow(img.reshape((28, 28)), cmap='Greys_r')

inputs_ = tf.placeholder(tf.float32, (None, 28, 28, 1), name='inputs')
targets_ = tf.placeholder(tf.float32, (None, 28, 28, 1), name='targets')

### Encoder
conv1 = tf.layers.conv2d(inputs_, 16, (3,3), padding='same', activation=tf.nn.relu)
# Now 28x28x16
maxpool1 = tf.layers.max_pooling2d(conv1, (2,2), (2,2), padding='same')
# Now 14x14x16
conv2 = tf.layers.conv2d(maxpool1, 8, (3,3), padding='same', activation=tf.nn.relu)
# Now 14x14x8
maxpool2 = tf.layers.max_pooling2d(conv2, (2,2), (2,2), padding='same')
# Now 7x7x8
conv3 = tf.layers.conv2d(maxpool2, 8, (3,3), padding='same', activation=tf.nn.relu)
# Now 7x7x8
encoded = tf.layers.max_pooling2d(conv3, (2,2), (2,2), padding='same')
# Now 4x4x8

### Decoder
upsample1 = tf.image.resize_nearest_neighbor(encoded, (7,7))
# Now 7x7x8
conv4 = tf.layers.conv2d(upsample1, 8, (3,3), padding='same', activation=tf.nn.relu)
# Now 7x7x8
upsample2 = tf.image.resize_nearest_neighbor(conv4, (14,14))
# Now 14x14x8
conv5 = tf.layers.conv2d(upsample2, 8, (3,3), padding='same', activation=tf.nn.relu)
# Now 14x14x8
upsample3 = tf.image.resize_nearest_neighbor(conv5, (28,28))
# Now 28x28x8
conv6 = tf.layers.conv2d(upsample3, 16, (3,3), padding='same', activation=tf.nn.relu)
# Now 28x28x16

logits = tf.layers.conv2d(conv6, 1, (3,3), padding='same', activation=None)
#Now 28x28x1

decoded = tf.nn.sigmoid(logits, name='decoded')

loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=targets_, logits=logits)
cost = tf.reduce_mean(loss)
opt = tf.train.AdamOptimizer(0.001).minimize(cost)

sess = tf.Session()

epochs = 20
batch_size = 200
sess.run(tf.global_variables_initializer())
for e in range(epochs):
    for ii in range(mnist.train.num_examples//batch_size):
        batch = mnist.train.next_batch(batch_size)
        imgs = batch[0].reshape((-1, 28, 28, 1))
        batch_cost, _ = sess.run([cost, opt], feed_dict={inputs_: imgs,
                                                         targets_: imgs})

        print("Epoch: {}/{}...".format(e+1, epochs),
              "Training loss: {:.4f}".format(batch_cost))

fig, axes = plt.subplots(nrows=2, ncols=10, sharex=True, sharey=True, figsize=(20,4))
in_imgs = mnist.test.images[:10]
reconstructed = sess.run(decoded, feed_dict={inputs_: in_imgs.reshape((10, 28, 28, 1))})

for images, row in zip([in_imgs, reconstructed], axes):
    for img, ax in zip(images, row):
        ax.imshow(img.reshape((28, 28)), cmap='Greys_r')
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)


fig.tight_layout(pad=0.1)

sess.close()

inputs_ = tf.placeholder(tf.float32, (None, 28, 28, 1), name='inputs')
targets_ = tf.placeholder(tf.float32, (None, 28, 28, 1), name='targets')

### Encoder
conv1 = tf.layers.conv2d(inputs_, 32, (3,3), padding='same', activation=tf.nn.relu)
# Now 28x28x32
maxpool1 = tf.layers.max_pooling2d(conv1, (2,2), (2,2), padding='same')
# Now 14x14x32
conv2 = tf.layers.conv2d(maxpool1, 32, (3,3), padding='same', activation=tf.nn.relu)
# Now 14x14x32
maxpool2 = tf.layers.max_pooling2d(conv2, (2,2), (2,2), padding='same')
# Now 7x7x32
conv3 = tf.layers.conv2d(maxpool2, 16, (3,3), padding='same', activation=tf.nn.relu)
# Now 7x7x16
encoded = tf.layers.max_pooling2d(conv3, (2,2), (2,2), padding='same')
# Now 4x4x16

### Decoder
upsample1 = tf.image.resize_nearest_neighbor(encoded, (7,7))
# Now 7x7x16
conv4 = tf.layers.conv2d(upsample1, 16, (3,3), padding='same', activation=tf.nn.relu)
# Now 7x7x16
upsample2 = tf.image.resize_nearest_neighbor(conv4, (14,14))
# Now 14x14x16
conv5 = tf.layers.conv2d(upsample2, 32, (3,3), padding='same', activation=tf.nn.relu)
# Now 14x14x32
upsample3 = tf.image.resize_nearest_neighbor(conv5, (28,28))
# Now 28x28x32
conv6 = tf.layers.conv2d(upsample3, 32, (3,3), padding='same', activation=tf.nn.relu)
# Now 28x28x32

logits = tf.layers.conv2d(conv6, 1, (3,3), padding='same', activation=None)
#Now 28x28x1

decoded = tf.nn.sigmoid(logits, name='decoded')

loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=targets_, logits=logits)
cost = tf.reduce_mean(loss)
opt = tf.train.AdamOptimizer(0.001).minimize(cost)

sess = tf.Session()

epochs = 100
batch_size = 200
# Set's how much noise we're adding to the MNIST images
noise_factor = 0.5
sess.run(tf.global_variables_initializer())
for e in range(epochs):
    for ii in range(mnist.train.num_examples//batch_size):
        batch = mnist.train.next_batch(batch_size)
        # Get images from the batch
        imgs = batch[0].reshape((-1, 28, 28, 1))
        
        # Add random noise to the input images
        noisy_imgs = imgs + noise_factor * np.random.randn(*imgs.shape)
        # Clip the images to be between 0 and 1
        noisy_imgs = np.clip(noisy_imgs, 0., 1.)
        
        # Noisy images as inputs, original images as targets
        batch_cost, _ = sess.run([cost, opt], feed_dict={inputs_: noisy_imgs,
                                                         targets_: imgs})

        print("Epoch: {}/{}...".format(e+1, epochs),
              "Training loss: {:.4f}".format(batch_cost))

fig, axes = plt.subplots(nrows=2, ncols=10, sharex=True, sharey=True, figsize=(20,4))
in_imgs = mnist.test.images[:10]
noisy_imgs = in_imgs + noise_factor * np.random.randn(*in_imgs.shape)
noisy_imgs = np.clip(noisy_imgs, 0., 1.)

reconstructed = sess.run(decoded, feed_dict={inputs_: noisy_imgs.reshape((10, 28, 28, 1))})

for images, row in zip([noisy_imgs, reconstructed], axes):
    for img, ax in zip(images, row):
        ax.imshow(img.reshape((28, 28)), cmap='Greys_r')
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)

fig.tight_layout(pad=0.1)

%matplotlib inline

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', validation_size=0)

img = mnist.train.images[2]
plt.imshow(img.reshape((28, 28)), cmap='Greys_r')

# Size of the encoding layer (the hidden layer)
encoding_dim = 32

image_size = mnist.train.images.shape[1]

inputs_ = tf.placeholder(tf.float32, (None, image_size), name='inputs')
targets_ = tf.placeholder(tf.float32, (None, image_size), name='targets')

# Output of hidden layer
encoded = tf.layers.dense(inputs_, encoding_dim, activation=tf.nn.relu)

# Output layer logits
logits = tf.layers.dense(encoded, image_size, activation=None)
# Sigmoid output from
decoded = tf.nn.sigmoid(logits, name='output')

loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=targets_, logits=logits)
cost = tf.reduce_mean(loss)
opt = tf.train.AdamOptimizer(0.001).minimize(cost)

# Create the session
sess = tf.Session()

epochs = 20
batch_size = 200
sess.run(tf.global_variables_initializer())
for e in range(epochs):
    for ii in range(mnist.train.num_examples//batch_size):
        batch = mnist.train.next_batch(batch_size)
        feed = {inputs_: batch[0], targets_: batch[0]}
        batch_cost, _ = sess.run([cost, opt], feed_dict=feed)

        print("Epoch: {}/{}...".format(e+1, epochs),
              "Training loss: {:.4f}".format(batch_cost))

fig, axes = plt.subplots(nrows=2, ncols=10, sharex=True, sharey=True, figsize=(20,4))
in_imgs = mnist.test.images[:10]
reconstructed, compressed = sess.run([decoded, encoded], feed_dict={inputs_: in_imgs})

for images, row in zip([in_imgs, reconstructed], axes):
    for img, ax in zip(images, row):
        ax.imshow(img.reshape((28, 28)), cmap='Greys_r')
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)

fig.tight_layout(pad=0.1)

sess.close()

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True, reshape=False)

"""
DO NOT MODIFY THIS CELL
"""
def fully_connected(prev_layer, num_units):
    """
    Create a fully connectd layer with the given layer as input and the given number of neurons.
    
    :param prev_layer: Tensor
        The Tensor that acts as input into this layer
    :param num_units: int
        The size of the layer. That is, the number of units, nodes, or neurons.
    :returns Tensor
        A new fully connected layer
    """
    layer = tf.layers.dense(prev_layer, num_units, activation=tf.nn.relu)
    return layer

"""
DO NOT MODIFY THIS CELL
"""
def conv_layer(prev_layer, layer_depth):
    """
    Create a convolutional layer with the given layer as input.
    
    :param prev_layer: Tensor
        The Tensor that acts as input into this layer
    :param layer_depth: int
        We'll set the strides and number of feature maps based on the layer's depth in the network.
        This is *not* a good way to make a CNN, but it helps us create this example with very little code.
    :returns Tensor
        A new convolutional layer
    """
    strides = 2 if layer_depth % 3 == 0 else 1
    conv_layer = tf.layers.conv2d(prev_layer, layer_depth*4, 3, strides, 'same', activation=tf.nn.relu)
    return conv_layer

"""
DO NOT MODIFY THIS CELL
"""
def train(num_batches, batch_size, learning_rate):
    # Build placeholders for the input samples and labels 
    inputs = tf.placeholder(tf.float32, [None, 28, 28, 1])
    labels = tf.placeholder(tf.float32, [None, 10])
    
    # Feed the inputs into a series of 20 convolutional layers 
    layer = inputs
    for layer_i in range(1, 20):
        layer = conv_layer(layer, layer_i)

    # Flatten the output from the convolutional layers 
    orig_shape = layer.get_shape().as_list()
    layer = tf.reshape(layer, shape=[-1, orig_shape[1] * orig_shape[2] * orig_shape[3]])

    # Add one fully connected layer
    layer = fully_connected(layer, 100)

    # Create the output layer with 1 node for each 
    logits = tf.layers.dense(layer, 10)
    
    # Define loss and training operations
    model_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=logits, labels=labels))
    train_opt = tf.train.AdamOptimizer(learning_rate).minimize(model_loss)
    
    # Create operations to test accuracy
    correct_prediction = tf.equal(tf.argmax(logits,1), tf.argmax(labels,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    
    # Train and test the network
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for batch_i in range(num_batches):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            # train this batch
            sess.run(train_opt, {inputs: batch_xs, labels: batch_ys})
            
            # Periodically check the validation or training loss and accuracy
            if batch_i % 100 == 0:
                loss, acc = sess.run([model_loss, accuracy], {inputs: mnist.validation.images,
                                                              labels: mnist.validation.labels})
                print('Batch: {:>2}: Validation loss: {:>3.5f}, Validation accuracy: {:>3.5f}'.format(batch_i, loss, acc))
            elif batch_i % 25 == 0:
                loss, acc = sess.run([model_loss, accuracy], {inputs: batch_xs, labels: batch_ys})
                print('Batch: {:>2}: Training loss: {:>3.5f}, Training accuracy: {:>3.5f}'.format(batch_i, loss, acc))

        # At the end, score the final accuracy for both the validation and test sets
        acc = sess.run(accuracy, {inputs: mnist.validation.images,
                                  labels: mnist.validation.labels})
        print('Final validation accuracy: {:>3.5f}'.format(acc))
        acc = sess.run(accuracy, {inputs: mnist.test.images,
                                  labels: mnist.test.labels})
        print('Final test accuracy: {:>3.5f}'.format(acc))
        
        # Score the first 100 test images individually. This won't work if batch normalization isn't implemented correctly.
        correct = 0
        for i in range(100):
            correct += sess.run(accuracy,feed_dict={inputs: [mnist.test.images[i]],
                                                    labels: [mnist.test.labels[i]]})

        print("Accuracy on 100 samples:", correct/100)


num_batches = 800
batch_size = 64
learning_rate = 0.002

tf.reset_default_graph()
with tf.Graph().as_default():
    train(num_batches, batch_size, learning_rate)

def fully_connected(prev_layer, num_units, is_training):
    """
    Create a fully connectd layer with the given layer as input and the given number of neurons.
    
    :param prev_layer: Tensor
        The Tensor that acts as input into this layer
    :param num_units: int
        The size of the layer. That is, the number of units, nodes, or neurons.
    :returns Tensor
        A new fully connected layer
    """
    layer = tf.layers.dense(prev_layer, num_units, use_bias=False, activation=None)
    layer = tf.layers.batch_normalization(layer, training=is_training) #归一化
    layer = tf.nn.relu(layer)
    return layer

def conv_layer(prev_layer, layer_depth, is_training):
    """
    Create a convolutional layer with the given layer as input.
    
    :param prev_layer: Tensor
        The Tensor that acts as input into this layer
    :param layer_depth: int
        We'll set the strides and number of feature maps based on the layer's depth in the network.
        This is *not* a good way to make a CNN, but it helps us create this example with very little code.
    :returns Tensor
        A new convolutional layer
    """
    strides = 2 if layer_depth % 3 == 0 else 1
    conv_layer = tf.layers.conv2d(prev_layer, layer_depth*4, 3, strides, 'same', use_bias=False, activation=None)
    conv_layer = tf.layers.batch_normalization(conv_layer, training=is_training)#归一化
    conv_layer = tf.nn.relu(conv_layer)
    return conv_layer

def train(num_batches, batch_size, learning_rate):
    # Build placeholders for the input samples and labels 
    inputs = tf.placeholder(tf.float32, [None, 28, 28, 1])
    labels = tf.placeholder(tf.float32, [None, 10])
    
    is_training = tf.placeholder(tf.bool)
    # Feed the inputs into a series of 20 convolutional layers 
    layer = inputs
    for layer_i in range(1, 20):
        layer = conv_layer(layer, layer_i, is_training)

    # Flatten the output from the convolutional layers 
    orig_shape = layer.get_shape().as_list()
    layer = tf.reshape(layer, shape=[-1, orig_shape[1] * orig_shape[2] * orig_shape[3]])

    # Add one fully connected layer
    layer = fully_connected(layer, 100,is_training)

    # Create the output layer with 1 node for each 
    logits = tf.layers.dense(layer, 10)
    
    # Define loss and training operations
    model_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=logits, labels=labels))
    
    # Tell TensorFlow to update the population statistics while training
    with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
        train_opt = tf.train.AdamOptimizer(learning_rate).minimize(model_loss)
 
    
    # Create operations to test accuracy
    correct_prediction = tf.equal(tf.argmax(logits,1), tf.argmax(labels,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    
    # Train and test the network
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for batch_i in range(num_batches):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            # train this batch
            sess.run(train_opt, {inputs: batch_xs, labels: batch_ys, is_training: True})
            
            # Periodically check the validation or training loss and accuracy
            if batch_i % 100 == 0:
                loss, acc = sess.run([model_loss, accuracy], {inputs: mnist.validation.images,
                                                              labels: mnist.validation.labels,
                                                              is_training: False})
                print('Batch: {:>2}: Validation loss: {:>3.5f}, Validation accuracy: {:>3.5f}'.format(batch_i, loss, acc))
            elif batch_i % 25 == 0:
                loss, acc = sess.run([model_loss, accuracy], {inputs: batch_xs, labels: batch_ys, is_training: False})
                print('Batch: {:>2}: Training loss: {:>3.5f}, Training accuracy: {:>3.5f}'.format(batch_i, loss, acc))

        # At the end, score the final accuracy for both the validation and test sets
        acc = sess.run(accuracy, {inputs: mnist.validation.images,
                                  labels: mnist.validation.labels,
                                  is_training: False})
        print('Final validation accuracy: {:>3.5f}'.format(acc))
        acc = sess.run(accuracy, {inputs: mnist.test.images,
                                  labels: mnist.test.labels,
                                  is_training: False})
        print('Final test accuracy: {:>3.5f}'.format(acc))
        
        # Score the first 100 test images individually. This won't work if batch normalization isn't implemented correctly.
        correct = 0
        for i in range(100):
            correct += sess.run(accuracy,feed_dict={inputs: [mnist.test.images[i]],
                                                    labels: [mnist.test.labels[i]],
                                                    is_training: False})

        print("Accuracy on 100 samples:", correct/100)


num_batches = 800
batch_size = 64
learning_rate = 0.002

tf.reset_default_graph()
with tf.Graph().as_default():
    train(num_batches, batch_size, learning_rate)

def fully_connected(prev_layer, num_units, is_training):
    """
    Create a fully connectd layer with the given layer as input and the given number of neurons.
    
    :param prev_layer: Tensor
        The Tensor that acts as input into this layer
    :param num_units: int
        The size of the layer. That is, the number of units, nodes, or neurons.
    :returns Tensor
        A new fully connected layer
    """
    layer = tf.layers.dense(prev_layer, num_units, use_bias=False, activation=None)
    
    gamma = tf.Variable(tf.ones([num_units]))#归一化参数，会进行训练
    beta = tf.Variable(tf.zeros([num_units]))#归一化参数，会进行训练
                        
    pop_mean = tf.Variable(tf.zeros([num_units]), trainable=False)                    
    pop_variance = tf.Variable(tf.ones([num_units]), trainable=False)                    
    epsilon = 1e-3
                        
    #训练阶段的函数
    def batch_normal_training():
        batch_mean, batch_variance = tf.nn.moments(layer, [0])    
          
        decay = 0.99
        train_mean = tf.assign(pop_mean, pop_mean * decay + batch_mean * (1 - decay))#计算均值，测试阶段使用         
        train_variance = tf.assign(pop_variance, pop_variance * decay + batch_variance * (1 - decay))  #计算偏差，测试阶段使用       
          
        with tf.control_dependencies([train_mean, train_variance]):
            return tf.nn.batch_normalization(layer, batch_mean, batch_variance, beta, gamma, epsilon)
     
    #测试阶段使用的函数
    def batch_normal_inference():
        return tf.nn.batch_normalization(layer, pop_mean, pop_variance, beta, gamma,  epsilon)
    
    batch_normalized_output = tf.cond(is_training, batch_normal_training, batch_normal_inference)   
                        
    return tf.nn.relu(batch_normalized_output)

def conv_layer(prev_layer, layer_depth, is_training):
    """
    Create a convolutional layer with the given layer as input.
    
    :param prev_layer: Tensor
        The Tensor that acts as input into this layer
    :param layer_depth: int
        We'll set the strides and number of feature maps based on the layer's depth in the network.
        This is *not* a good way to make a CNN, but it helps us create this example with very little code.
    :returns Tensor
        A new convolutional layer
    """
    strides = 2 if layer_depth % 3 == 0 else 1

    in_channels = prev_layer.get_shape().as_list()[3]
    out_channels = layer_depth*4
    
    weights = tf.Variable(
        tf.truncated_normal([3, 3, in_channels, out_channels], stddev=0.05))
    
    bias = tf.Variable(tf.zeros(out_channels))

    layer = tf.nn.conv2d(prev_layer, weights, strides=[1,strides, strides, 1], padding='SAME')
    
    gamma = tf.Variable(tf.ones([out_channels]))
    beta = tf.Variable(tf.zeros([out_channels]))

    pop_mean = tf.Variable(tf.zeros([out_channels]), trainable=False)
    pop_variance = tf.Variable(tf.ones([out_channels]), trainable=False)

    epsilon = 1e-3
    
    def batch_norm_training():
        # Important to use the correct dimensions here to ensure the mean and variance are calculated 
        # per feature map instead of for the entire layer
        batch_mean, batch_variance = tf.nn.moments(layer, [0,1,2], keep_dims=False)

        decay = 0.99
        train_mean = tf.assign(pop_mean, pop_mean * decay + batch_mean * (1 - decay))
        train_variance = tf.assign(pop_variance, pop_variance * decay + batch_variance * (1 - decay))

        with tf.control_dependencies([train_mean, train_variance]):
            return tf.nn.batch_normalization(layer, batch_mean, batch_variance, beta, gamma, epsilon)
 
    def batch_norm_inference():
        return tf.nn.batch_normalization(layer, pop_mean, pop_variance, beta, gamma, epsilon)

    batch_normalized_output = tf.cond(is_training, batch_norm_training, batch_norm_inference)
    return tf.nn.relu(batch_normalized_output)
    return conv_layer

def train(num_batches, batch_size, learning_rate):
    # Build placeholders for the input samples and labels 
    inputs = tf.placeholder(tf.float32, [None, 28, 28, 1])
    labels = tf.placeholder(tf.float32, [None, 10])
    is_training = tf.placeholder(tf.bool)
    # Feed the inputs into a series of 20 convolutional layers 
    layer = inputs
    for layer_i in range(1, 20):
        layer = conv_layer(layer, layer_i, is_training)

    # Flatten the output from the convolutional layers 
    orig_shape = layer.get_shape().as_list()
    layer = tf.reshape(layer, shape=[-1, orig_shape[1] * orig_shape[2] * orig_shape[3]])

    # Add one fully connected layer
    layer = fully_connected(layer, 100, is_training)

    # Create the output layer with 1 node for each 
    logits = tf.layers.dense(layer, 10)
    
    # Define loss and training operations
    model_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=logits, labels=labels))
    train_opt = tf.train.AdamOptimizer(learning_rate).minimize(model_loss)
    
    # Create operations to test accuracy
    correct_prediction = tf.equal(tf.argmax(logits,1), tf.argmax(labels,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    
    # Train and test the network
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for batch_i in range(num_batches):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            # train this batch
            sess.run(train_opt, {inputs: batch_xs, labels: batch_ys, is_training: True})
            
            # Periodically check the validation or training loss and accuracy
            if batch_i % 100 == 0:
                loss, acc = sess.run([model_loss, accuracy], {inputs: mnist.validation.images,
                                                              labels: mnist.validation.labels,
                                                              is_training: False})
                print('Batch: {:>2}: Validation loss: {:>3.5f}, Validation accuracy: {:>3.5f}'.format(batch_i, loss, acc))
            elif batch_i % 25 == 0:
                loss, acc = sess.run([model_loss, accuracy], {inputs: batch_xs, labels: batch_ys, is_training: False})
                print('Batch: {:>2}: Training loss: {:>3.5f}, Training accuracy: {:>3.5f}'.format(batch_i, loss, acc))

        # At the end, score the final accuracy for both the validation and test sets
        acc = sess.run(accuracy, {inputs: mnist.validation.images,
                                  labels: mnist.validation.labels,
                                  is_training: False})
        print('Final validation accuracy: {:>3.5f}'.format(acc))
        acc = sess.run(accuracy, {inputs: mnist.test.images,
                                  labels: mnist.test.labels,
                                  is_training: False})
        print('Final test accuracy: {:>3.5f}'.format(acc))
        
        # Score the first 100 test images individually. This won't work if batch normalization isn't implemented correctly.
        correct = 0
        for i in range(100):
            correct += sess.run(accuracy,feed_dict={inputs: [mnist.test.images[i]],
                                                    labels: [mnist.test.labels[i]],
                                                    is_training: False})

        print("Accuracy on 100 samples:", correct/100)


num_batches = 800
batch_size = 64
learning_rate = 0.002

tf.reset_default_graph()
with tf.Graph().as_default():
    train(num_batches, batch_size, learning_rate)