👨‍💻 Tensorflow Kod Notları

👨‍🔧 Verileri Düzenleme

Verileri Tek Boyuta Alma
Normalize Etme
OneShot Yapısı
Boyutları Bastırma
Verileri Tek Boyuta Alma
X_train_flatten = X_train_orig.reshape(X_train_orig.shape[0], -1).T
X_test_flatten = X_test_orig.reshape(X_test_orig.shape[0], -1).T
Normalize Etme
# . olma sebebi float olmasını sağlamak
X_train = X_train_flatten/255.
X_test = X_test_flatten/255.
OneShot Yapısı
Y_train = convert_to_one_hot(Y_train_orig, 6)
Y_test = convert_to_one_hot(Y_test_orig, 6)
Boyutları Bastırma
print ("number of training examples = " + str(X_train.shape[1]))
print ("number of test examples = " + str(X_test.shape[1]))
print ("X_train shape: " + str(X_train.shape))
print ("Y_train shape: " + str(Y_train.shape))
print ("X_test shape: " + str(X_test.shape))
print ("Y_test shape: " + str(Y_test.shape))

✨ Tensorflow Ortamı Tanımlama

Placeholder
Parametre Tanımlama
Forward Propagation
Cost
Model Oluşturma
Placeholder
# GRADED FUNCTION: create_placeholders
def create_placeholders(n_x, n_y):
"""
Creates the placeholders for the tensorflow session.
Arguments:
n_x -- scalar, size of an image vector (num_px * num_px = 64 * 64 * 3 = 12288)
n_y -- scalar, number of classes (from 0 to 5, so -> 6)
Returns:
X -- placeholder for the data input, of shape [n_x, None] and dtype "float"
Y -- placeholder for the input labels, of shape [n_y, None] and dtype "float"
Tips:
- You will use None because it let's us be flexible on the number of examples you will for the placeholders.
In fact, the number of examples during test/train is different.
"""
### START CODE HERE ### (approx. 2 lines)
X = tf.placeholder(dtype=tf.float32, shape=[n_x, None])
Y = tf.placeholder(dtype=tf.float32, shape=[n_y, None])
### END CODE HERE ###
return X, Y
Parametre Tanımlama
# GRADED FUNCTION: initialize_parameters
def initialize_parameters():
"""
Initializes parameters to build a neural network with tensorflow. The shapes are:
W1 : [25, 12288]
b1 : [25, 1]
W2 : [12, 25]
b2 : [12, 1]
W3 : [6, 12]
b3 : [6, 1]
Returns:
parameters -- a dictionary of tensors containing W1, b1, W2, b2, W3, b3
"""
tf.set_random_seed(1) # so that your "random" numbers match ours
### START CODE HERE ### (approx. 6 lines of code)
W1 = tf.get_variable("W1", [25, 12288], initializer = tf.contrib.layers.xavier_initializer(seed = 1))
b1 = tf.get_variable("b1", [25, 1], initializer = tf.zeros_initializer())
W2 = tf.get_variable("W2", [12, 25], initializer = tf.contrib.layers.xavier_initializer(seed = 1))
b2 = tf.get_variable("b2", [12, 1], initializer = tf.zeros_initializer())
W3 = tf.get_variable("W3", [6, 12], initializer = tf.contrib.layers.xavier_initializer(seed = 1))
b3 = tf.get_variable("b3", [6, 1], initializer = tf.zeros_initializer())
### END CODE HERE ###
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2,
"W3": W3,
"b3": b3}
return parameters
Forward Propagation
# GRADED FUNCTION: forward_propagation
def forward_propagation(X, parameters):
"""
Implements the forward propagation for the model: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX
Arguments:
X -- input dataset placeholder, of shape (input size, number of examples)
parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3"
the shapes are given in initialize_parameters
Returns:
Z3 -- the output of the last LINEAR unit
"""
# Retrieve the parameters from the dictionary "parameters"
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
W3 = parameters['W3']
b3 = parameters['b3']
### START CODE HERE ### (approx. 5 lines) # Numpy Equivalents:
Z1 = tf.add(tf.matmul(W1, X), b1) # Z1 = np.dot(W1, X) + b1
A1 = tf.nn.relu(Z1) # A1 = relu(Z1)
Z2 = tf.add(tf.matmul(W2, A1), b2) # Z2 = np.dot(W2, a1) + b2
A2 = tf.nn.relu(Z2) # A2 = relu(Z2)
Z3 = tf.add(tf.matmul(W3, A2), b3) # Z3 = np.dot(W3,Z2) + b3
### END CODE HERE ###
return Z3
Cost
# GRADED FUNCTION: compute_cost
def compute_cost(Z3, Y):
"""
Computes the cost
Arguments:
Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (6, number of examples)
Y -- "true" labels vector placeholder, same shape as Z3
Returns:
cost - Tensor of the cost function
"""
# to fit the tensorflow requirement for tf.nn.softmax_cross_entropy_with_logits(...,...)
logits = tf.transpose(Z3)
labels = tf.transpose(Y)
### START CODE HERE ### (1 line of code)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = labels, logits = logits))
### END CODE HERE ###
return cost
Model Oluşturma
def model(X_train, Y_train, X_test, Y_test, learning_rate = 0.0001,
num_epochs = 1500, minibatch_size = 32, print_cost = True):
"""
Implements a three-layer tensorflow neural network: LINEAR->RELU->LINEAR->RELU->LINEAR->SOFTMAX.
Arguments:
X_train -- training set, of shape (input size = 12288, number of training examples = 1080)
Y_train -- test set, of shape (output size = 6, number of training examples = 1080)
X_test -- training set, of shape (input size = 12288, number of training examples = 120)
Y_test -- test set, of shape (output size = 6, number of test examples = 120)
learning_rate -- learning rate of the optimization
num_epochs -- number of epochs of the optimization loop
minibatch_size -- size of a minibatch
print_cost -- True to print the cost every 100 epochs
Returns:
parameters -- parameters learnt by the model. They can then be used to predict.
"""
ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables
tf.set_random_seed(1) # to keep consistent results
seed = 3 # to keep consistent results
(n_x, m) = X_train.shape # (n_x: input size, m : number of examples in the train set)
n_y = Y_train.shape[0] # n_y : output size
costs = [] # To keep track of the cost
# Create Placeholders of shape (n_x, n_y)
### START CODE HERE ### (1 line)
X, Y = create_placeholders(n_x, n_y)
### END CODE HERE ###
# Initialize parameters
### START CODE HERE ### (1 line)
parameters = initialize_parameters()
### END CODE HERE ###
# Forward propagation: Build the forward propagation in the tensorflow graph
### START CODE HERE ### (1 line)
Z3 = forward_propagation(X, parameters)
### END CODE HERE ###
# Cost function: Add cost function to tensorflow graph
### START CODE HERE ### (1 line)
cost = compute_cost(Z3, Y)
### END CODE HERE ###
# Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer.
### START CODE HERE ### (1 line)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
### END CODE HERE ###
# Initialize all the variables
init = tf.global_variables_initializer()
# Start the session to compute the tensorflow graph
with tf.Session() as sess:
# Run the initialization
sess.run(init)
# Do the training loop
for epoch in range(num_epochs):
epoch_cost = 0. # Defines a cost related to an epoch
num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train set
seed = seed + 1
minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# IMPORTANT: The line that runs the graph on a minibatch.
# Run the session to execute the "optimizer" and the "cost", the feedict should contain a minibatch for (X,Y).
### START CODE HERE ### (1 line)
_ , minibatch_cost = sess.run([optimizer, cost], feed_dict={X: minibatch_X, Y: minibatch_Y})
### END CODE HERE ###
epoch_cost += minibatch_cost / num_minibatches
# Print the cost every epoch
if print_cost == True and epoch % 100 == 0:
print ("Cost after epoch %i: %f" % (epoch, epoch_cost))
if print_cost == True and epoch % 5 == 0:
costs.append(epoch_cost)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
# lets save the parameters in a variable
parameters = sess.run(parameters)
print ("Parameters have been trained!")
# Calculate the correct predictions
correct_prediction = tf.equal(tf.argmax(Z3), tf.argmax(Y))
# Calculate accuracy on the test set
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print ("Train Accuracy:", accuracy.eval({X: X_train, Y: Y_train}))
print ("Test Accuracy:", accuracy.eval({X: X_test, Y: Y_test}))
return parameters

🧱 Temel Tanımlamalar

✨ Değişken Tanımlamaları
🏃‍♂️ Çalıştırma İşlemleri
🧮 Matematiksel İşlemler
✨ Değişken Tanımlamaları
# Değişken değerleri tanımlama
w = tf.Variable(0, dtype=tf.float32)
loss = tf.Variable((y - y_hat)**2, name='loss')
# Sabit değerleri tanımlama
a = tf.constant(2)
b = tf.constant(10)
X = tf.constant(np.random.randn(3, 1), name = "X")
W = tf.constant(np.random.randn(4, 3), name = "W")
# Sonradan atancak değerlerin tipi ve boyutu
x = tf.placeholder(tf.float32, (3, 1))
train = tf.train.GradientDescentOptimizer(0.01).minimize(cost)
init = tf.global_variables_initializer() # When init is run later (session.run(init)),
# Z ve Y değerlerine göre cost tanımlama
cost = x[0][0] * w**2 + x[1][0] * w + x[2][0]
cost = tf.nn.sigmoid_cross_entropy_with_logits(logits = z, labels = y)
# mean, toplayıp ortalama almak demektir
cost = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(
labels = labels, logits = logits
)
)
# Cost değerini minimum yapmayı amaçlayan değişkenler
optimizer = tf.train.GradientDescentOptimizer(learning_rate = learning_rate).minimize(cost)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# y = [1, 2, 3, 4] -> [[0,1,0,0], [0, 0, 1, 0], ...] gösterimi
one_hot_matrix = tf.one_hot(indices=labels, depth=C, axis=0)
🏃‍♂️ Çalıştırma İşlemleri
sess = tf.Session()
result = sess.run(Y)
sess.close()
# Context manager ile kullanılırsa hatalar da kontrol edilir (?)
with tf.Session() as session:
session.run(init)
session.run(w)
session.run(train, feed_dict={x:coefficients})
session.run(w)
sess.close()
# Tekrarlı çalıştırma
for i in range(100000):
# session.run(train)
session.run(train, feed_dict={x:coefficients}) # X verilerine değer atama
session.run(w)
sess.close()
_ , c = sess.run([optimizer, cost], feed_dict={X: minibatch_X, Y: minibatch_Y})
🧮 Matematiksel İşlemler
# Y = W.X + b
Y = tf.add(tf.matmul(W, X), b)
Y = tf.matmul(W, X)
A = tf.nn.relu()