02.改善深层神经网络：超参数调试、正则化以及优化 W3. 超参数调试、Batch Norm和程序框架（作业：TensorFlow教程+数字手势预测）

import math
import numpy as np
import h5py
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
from tf_utils import load_dataset, random_mini_batches, convert_to_one_hot, predict

%matplotlib inline
np.random.seed(1)

import sys
sys.path.append(r"/path/file")

y_hat = tf.constant(36, name='y_hat')            
# Define y_hat constant. Set to 36.

y = tf.constant(39, name='y')                    
# Define y. Set to 39

loss = tf.Variable((y - y_hat)**2, name='loss')  
# Create a variable for the loss

init = tf.global_variables_initializer()         
# When init is run later (session.run(init)),
# the loss variable will be initialized and ready to be computed

with tf.Session() as session:                    
# Create a session and print the output
    session.run(init)                            
    # Initializes the variables
    print(session.run(loss))                     
    # Prints the loss

9

a = tf.constant(2)
b = tf.constant(10)
c = tf.multiply(a,b)
print(c)

Tensor("Mul:0", shape=(), dtype=int32)

sess = tf.Session()
print(sess.run(c))

# Change the value of x in the feed_dict

x = tf.placeholder(tf.int64, name = 'xa')
# 定义变量x，稍后才能赋值
print(sess.run(2 * x, feed_dict = {x: 3}))
# 运行（计算图，给placeholder变量喂数据）
sess.close()

# GRADED FUNCTION: linear_function

def linear_function():
    """
    Implements a linear function: 
            Initializes W to be a random tensor of shape (4,3)
            Initializes X to be a random tensor of shape (3,1)
            Initializes b to be a random tensor of shape (4,1)
    Returns: 
    result -- runs the session for Y = WX + b 
    """
    
    np.random.seed(1)
    
    ### START CODE HERE ### (4 lines of code)
    X = tf.constant(np.random.randn(3,1), name='X')
    W = tf.constant(np.random.randn(4,3), name='W')
    b = tf.constant(np.random.randn(4,1), name='b')
    Y = tf.matmul(W,X)+b
    # Y = tf.add(tf.matmul(W,X), b) # 也可以
    # Y = W*X+b # 错误写法！！！！！！！！！！
    ### END CODE HERE ### 
    
    # Create the session using tf.Session() and run it with sess.run(...) on the variable you want to calculate
    
    ### START CODE HERE ###
    sess = tf.Session()
    result = sess.run(Y)
    ### END CODE HERE ### 
    
    # close the session 
    sess.close()

    return result

sess = tf.Session()
# Run the variables initialization (if needed), run the operations
result = sess.run(..., feed_dict = {...})
sess.close() # Close the session

with tf.Session() as sess: 
    # run the variables initialization (if needed), run the operations
    result = sess.run(..., feed_dict = {...})
    # This takes care of closing the session for you :)

# GRADED FUNCTION: sigmoid

def sigmoid(z):
    """
    Computes the sigmoid of z
    
    Arguments:
    z -- input value, scalar or vector
    
    Returns: 
    results -- the sigmoid of z
    """
    
    ### START CODE HERE ### ( approx. 4 lines of code)
    # Create a placeholder for x. Name it 'x'.
    x = tf.placeholder(tf.float32, name='x')

    # compute sigmoid(x)
    sigmoid = tf.sigmoid(x)

    # Create a session, and run it. 
    # Please use the method 2 explained above. 
    # You should use a feed_dict to pass z's value to x. 
    with tf.Session() as sess:
        # Run session and call the output "result"
        result = sess.run(sigmoid,feed_dict={x:z})
    
    ### END CODE HERE ###
    
    return result

# GRADED FUNCTION: cost

def cost(logits, labels):
    """
    Computes the cost using the sigmoid cross entropy
    
    Arguments:
    logits -- vector containing z, output of the last linear unit 
    			(before the final sigmoid activation)
    labels -- vector of labels y (1 or 0) 
    
    Note: What we've been calling "z" and "y" in this class are 
    		respectively called "logits" and "labels" 
    in the TensorFlow documentation. 
    So logits will feed into z, and labels into y. 
    
    Returns:
    cost -- runs the session of the cost (formula (2))
    """
    
    ### START CODE HERE ### 
    
    # Create the placeholders for "logits" (z) and "labels" (y) (approx. 2 lines)
    z = tf.placeholder(tf.float32, name='z')
    y = tf.placeholder(tf.float32, name='y')
    
    # Use the loss function (approx. 1 line)
    cost = tf.nn.sigmoid_cross_entropy_with_logits(logits=z, labels=y)
    
    # Create a session (approx. 1 line). See method 1 above.
    sess = tf.Session()
    
    # Run the session (approx. 1 line).
    cost = sess.run(cost, feed_dict={z:logits, y:labels})
    
    # Close the session (approx. 1 line). See method 1 above.
    sess.close()
    
    ### END CODE HERE ###
    
    return cost

# GRADED FUNCTION: one_hot_matrix

def one_hot_matrix(labels, C):
    """
    Creates a matrix where the i-th row corresponds to the ith class number and the jth column
                     corresponds to the jth training example. So if example j had a label i. Then entry (i,j) 
                     will be 1. 
                     
    Arguments:
    labels -- vector containing the labels 
    C -- number of classes, the depth of the one hot dimension
    
    Returns: 
    one_hot -- one hot matrix
    """
    
    ### START CODE HERE ###
    
    # Create a tf.constant equal to C (depth), name it 'C'. (approx. 1 line)
    C = tf.constant(C, name='C')
    
    # Use tf.one_hot, be careful with the axis (approx. 1 line)
    one_hot_matrix = tf.one_hot(labels, C, axis=0) 
    # 不写 axis默认为 1， 0 是列向
    
    # Create the session (approx. 1 line)
    sess = tf.Session()
    
    # Run the session (approx. 1 line)
    one_hot = sess.run(one_hot_matrix)
    
    # Close the session (approx. 1 line). See method 1 above.
    sess.close()
    
    ### END CODE HERE ###
    
    return one_hot

# GRADED FUNCTION: ones

def ones(shape):
    """
    Creates an array of ones of dimension shape
    
    Arguments:
    shape -- shape of the array you want to create
        
    Returns: 
    ones -- array containing only ones
    """
    
    ### START CODE HERE ###
    
    # Create "ones" tensor using tf.ones(...). (approx. 1 line)
    ones = tf.ones(shape)
    
    # Create the session (approx. 1 line)
    sess = tf.Session()
    
    # Run the session to compute 'ones' (approx. 1 line)
    ones = sess.run(ones)
    
    # Close the session (approx. 1 line). See method 1 above.
    sess.close()
    
    ### END CODE HERE ###
    return ones

# Loading the dataset
X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()

# Example of a picture
index = 1
plt.imshow(X_train_orig[index])
print ("y = " + str(np.squeeze(Y_train_orig[:, index])))

# Flatten the training and test images
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 image vectors
X_train = X_train_flatten/255.
X_test = X_test_flatten/255.
# Convert training and test labels to one hot matrices
Y_train = convert_to_one_hot(Y_train_orig, 6)
Y_test = convert_to_one_hot(Y_test_orig, 6)

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))

number of training examples = 1080
number of test examples = 120
X_train shape: (12288, 1080) # 64*64*3 = 12288
Y_train shape: (6, 1080)
X_test shape: (12288, 120)
Y_test shape: (6, 120)

# 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(tf.float32, shape=(n_x, None), name='X')
    Y = tf.placeholder(tf.float32, shape=(n_y, None), name='Y')
    ### END CODE HERE ###
    
    return X, Y

# 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

# 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.matmul(W1, X) + b1                 # Z1 = np.dot(W1, X) + b1
    A1 = tf.nn.relu(Z1)                       # A1 = relu(Z1)
    Z2 = tf.matmul(W2, A1) + b2               # Z2 = np.dot(W2, a1) + b2
    A2 = tf.nn.relu(Z2)                       # A2 = relu(Z2)
    Z3 = tf.matmul(W3, A2) + b3               # Z3 = np.dot(W3,Z2) + b3
    ### END CODE HERE ###
    
    return Z3

# 测试
tf.reset_default_graph()

with tf.Session() as sess:
    X, Y = create_placeholders(12288, 6)
    parameters = initialize_parameters()
    Z3 = forward_propagation(X, parameters)
    print("Z3 = " + str(Z3))
   
# Z3 = Tensor("add_2:0", shape=(6, ?), dtype=float32)

# 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) # 形状不对，先转置
    labels = tf.transpose(Y)
    
    ### START CODE HERE ### (1 line of code)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=labels))
    ### END CODE HERE ###
    
    return cost

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 ###
    
    # 初始化所有变量
    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) 
            # 多少个minibatch子集
            
            seed = seed + 1
            minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)

            for minibatch in minibatches:#对每个随机的子集

                # 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

parameters = model(X_train, Y_train, X_test, Y_test)

Cost after epoch 0: 1.855702
Cost after epoch 100: 1.017255
Cost after epoch 200: 0.733184
Cost after epoch 300: 0.573071
Cost after epoch 400: 0.468573
Cost after epoch 500: 0.381228
Cost after epoch 600: 0.313815
Cost after epoch 700: 0.253708
Cost after epoch 800: 0.203900
Cost after epoch 900: 0.166453
Cost after epoch 1000: 0.146636
Cost after epoch 1100: 0.107279
Cost after epoch 1200: 0.086699
Cost after epoch 1300: 0.059341
Cost after epoch 1400: 0.052289

Parameters have been trained!
Train Accuracy: 0.9990741
Test Accuracy: 0.725

import scipy
from PIL import Image
from scipy import ndimage

## START CODE HERE ## (PUT YOUR IMAGE NAME) 
my_image = "thumbs_up.jpg"
## END CODE HERE ##

# We preprocess your image to fit your algorithm.
fname = "images/" + my_image
image = np.array(ndimage.imread(fname, flatten=False))
my_image = scipy.misc.imresize(image, size=(64,64)).reshape((1, 64*64*3)).T
my_image_prediction = predict(my_image, parameters)

plt.imshow(image)
print("Your algorithm predicts: y = " + str(np.squeeze(my_image_prediction)))

Your algorithm predicts: y = 3

Your algorithm predicts: y = 5