We need to define model and architecture and choose cost function and optmizer.
import tensorflow as tf
class ConvolutionalNeuralNetworkTensorflow:
def __init__(
self,
X_train,
Y_train,
X_test,
Y_test,
n_filters=10,
n_neurons_connected=50,
n_categories=10,
receptive_field=3,
stride=1,
padding=1,
epochs=10,
batch_size=100,
eta=0.1,
lmbd=0.0):
self.global_step = tf.Variable(0, dtype=tf.int32, trainable=False, name='global_step')
self.X_train = X_train
self.Y_train = Y_train
self.X_test = X_test
self.Y_test = Y_test
self.n_inputs, self.input_width, self.input_height, self.depth = X_train.shape
self.n_filters = n_filters
self.n_downsampled = int(self.input_width*self.input_height*n_filters / 4)
self.n_neurons_connected = n_neurons_connected
self.n_categories = n_categories
self.receptive_field = receptive_field
self.stride = stride
self.strides = [stride, stride, stride, stride]
self.padding = padding
self.epochs = epochs
self.batch_size = batch_size
self.iterations = self.n_inputs // self.batch_size
self.eta = eta
self.lmbd = lmbd
self.create_placeholders()
self.create_CNN()
self.create_loss()
self.create_optimiser()
self.create_accuracy()
def create_placeholders(self):
with tf.name_scope('data'):
self.X = tf.placeholder(tf.float32, shape=(None, self.input_width, self.input_height, self.depth), name='X_data')
self.Y = tf.placeholder(tf.float32, shape=(None, self.n_categories), name='Y_data')
def create_CNN(self):
with tf.name_scope('CNN'):
# Convolutional layer
self.W_conv = self.weight_variable([self.receptive_field, self.receptive_field, self.depth, self.n_filters], name='conv', dtype=tf.float32)
b_conv = self.weight_variable([self.n_filters], name='conv', dtype=tf.float32)
z_conv = tf.nn.conv2d(self.X, self.W_conv, self.strides, padding='SAME', name='conv') + b_conv
a_conv = tf.nn.relu(z_conv)
# 2x2 max pooling
a_pool = tf.nn.max_pool(a_conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME', name='pool')
# Fully connected layer
a_pool_flat = tf.reshape(a_pool, [-1, self.n_downsampled])
self.W_fc = self.weight_variable([self.n_downsampled, self.n_neurons_connected], name='fc', dtype=tf.float32)
b_fc = self.bias_variable([self.n_neurons_connected], name='fc', dtype=tf.float32)
a_fc = tf.nn.relu(tf.matmul(a_pool_flat, self.W_fc) + b_fc)
# Output layer
self.W_out = self.weight_variable([self.n_neurons_connected, self.n_categories], name='out', dtype=tf.float32)
b_out = self.bias_variable([self.n_categories], name='out', dtype=tf.float32)
self.z_out = tf.matmul(a_fc, self.W_out) + b_out
def create_loss(self):
with tf.name_scope('loss'):
softmax_loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=self.Y, logits=self.z_out))
regularizer_loss_conv = tf.nn.l2_loss(self.W_conv)
regularizer_loss_fc = tf.nn.l2_loss(self.W_fc)
regularizer_loss_out = tf.nn.l2_loss(self.W_out)
regularizer_loss = self.lmbd*(regularizer_loss_conv + regularizer_loss_fc + regularizer_loss_out)
self.loss = softmax_loss + regularizer_loss
def create_accuracy(self):
with tf.name_scope('accuracy'):
probabilities = tf.nn.softmax(self.z_out)
predictions = tf.argmax(probabilities, 1)
labels = tf.argmax(self.Y, 1)
correct_predictions = tf.equal(predictions, labels)
correct_predictions = tf.cast(correct_predictions, tf.float32)
self.accuracy = tf.reduce_mean(correct_predictions)
def create_optimiser(self):
with tf.name_scope('optimizer'):
self.optimizer = tf.train.GradientDescentOptimizer(learning_rate=self.eta).minimize(self.loss, global_step=self.global_step)
def weight_variable(self, shape, name='', dtype=tf.float32):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial, name=name, dtype=dtype)
def bias_variable(self, shape, name='', dtype=tf.float32):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial, name=name, dtype=dtype)
def fit(self):
data_indices = np.arange(self.n_inputs)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(self.epochs):
for j in range(self.iterations):
chosen_datapoints = np.random.choice(data_indices, size=self.batch_size, replace=False)
batch_X, batch_Y = self.X_train[chosen_datapoints], self.Y_train[chosen_datapoints]
sess.run([CNN.loss, CNN.optimizer],
feed_dict={CNN.X: batch_X,
CNN.Y: batch_Y})
accuracy = sess.run(CNN.accuracy,
feed_dict={CNN.X: batch_X,
CNN.Y: batch_Y})
step = sess.run(CNN.global_step)
self.train_loss, self.train_accuracy = sess.run([CNN.loss, CNN.accuracy],
feed_dict={CNN.X: self.X_train,
CNN.Y: self.Y_train})
self.test_loss, self.test_accuracy = sess.run([CNN.loss, CNN.accuracy],
feed_dict={CNN.X: self.X_test,
CNN.Y: self.Y_test})