吴恩达深度学习第四课第一周

为了方便大家，我将代码上传至git上，训练正确率和测试正确率比coursera上有所提高。

在计算损失函数时，TensorFlow将原来tf.nn.softmax_cross_entropy_with_logits替换为tf.nn.softmax_cross_entropy_with_logits_v2.我查阅了大量资料，未能找到关于二者区别的文章，TensorFlow版本问题可能导致了最终程序结果与Coursera上有所出入，不过不影响大家学习。训练集和测试集以及cnn_utils包都已上传至git。

https://github.com/CrazyKKK/course4_week1-1

import math
import numpy as np
import h5py
import matplotlib.pyplot as plt
import scipy
from PIL import Image
from scipy import ndimage
import tensorflow as tf
from tensorflow.python.framework import ops
from cnn_utils import *

np.random.seed(1)

X_train_orig,Y_train_orig,X_test_orig,Y_test_orig,classes = load_dataset()

X_train = X_train_orig/255
X_test = X_test_orig/255

Y_train = convert_to_one_hot(Y_train_orig,6).T
Y_test = convert_to_one_hot(Y_test_orig,6).T
'''
print ("number of training examples = " + str(X_train.shape[0]))
print ("number of test examples = " + str(X_test.shape[0]))
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))
'''
conv_layers={}

def create_placeholders(n_H0,n_W0,n_C0,n_y):
    """
    Creates the placeholders for the tensorflow session.

    Arguments:
    n_H0 -- scalar, height of an input image
    n_W0 -- scalar, width of an input image
    n_C0 -- scalar, number of channels of the input
    n_y -- scalar, number of classes

    Returns:
    X -- placeholder for the data input, of shape [None, n_H0, n_W0, n_C0] and dtype "float"
    Y -- placeholder for the input labels, of shape [None, n_y] and dtype "float"
    """
    X = tf.placeholder(tf.float32, [None, n_H0, n_W0, n_C0])

    Y = tf.placeholder(tf.float32, [None, n_y])

    return X,Y



def initialize_parameters():
    """
    Initializes weight parameters to build a neural network with tensorflow. The shapes are:
                        W1 : [4, 4, 3, 8]
                        W2 : [2, 2, 8, 16]
    Returns:
    parameters -- a dictionary of tensors containing W1, W2
    """
    tf.set_random_seed(1)       # so that your "random" numbers match ours
    W1 = tf.get_variable('W1', [4 ,4, 3, 8], initializer=tf.contrib.layers.xavier_initializer(seed=0))
    W2 = tf.get_variable('W2', [2, 2, 8, 16], initializer=tf.contrib.layers.xavier_initializer(seed=0))

    parameters = {"W1":W1,
                  "W2":W2}
    return parameters
'''
tf.reset_default_graph()
with tf.Session() as sess_test:
    parameters = initialize_parameters()
    init = tf.global_variables_initializer()
    sess_test.run(init)
    print("W1 = " + str(parameters["W1"].eval()[1,1,1]))
    print("W2 = " + str(parameters["W2"].eval()[1, 1, 1]))
'''

# GRADED FUNCTION: forward_propagation


def forward_propagation(X, parameters):
    """
    Implements the forward propagation for the model:
    CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED

    Arguments:
    X -- input dataset placeholder, of shape (input size, number of examples)
    parameters -- python dictionary containing your parameters "W1", "W2"
                  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']
    W2 = parameters['W2']

    ### START CODE HERE ###
    # CONV2D: stride of 1, padding 'SAME'
    Z1 = tf.nn.conv2d(X,W1,strides=[1,1,1,1],padding='SAME')
    # RELU
    A1 = tf.nn.relu(Z1)
    # MAXPOOL: window 8x8, sride 8, padding 'SAME'
    P1 = tf.nn.max_pool(A1,ksize=[1,8,8,1],strides=[1,8,8,1],padding='SAME')
    # CONV2D: filters W2, stride 1, padding 'SAME'
    Z2 = tf.nn.conv2d(P1,W2,strides=[1,1,1,1],padding='SAME')
    # RELU
    A2 = tf.nn.relu(Z2)
    # MAXPOOL: window 4x4, stride 4, padding 'SAME'
    P2 = tf.nn.max_pool(A2,ksize=[1,4,4,1],strides=[1,4,4,1],padding='SAME')
    # FLATTEN
    P2 = tf.contrib.layers.flatten(P2)
    # FULLY-CONNECTED without non-linear activation function (not not call softmax).
    # 6 neurons in output layer. Hint: one of the arguments should be "activation_fn=None"
    Z3 = tf.contrib.layers.fully_connected(P2,6,activation_fn=None)
    ### END CODE HERE ###

    return Z3

# GRADED FUNCTION: compute_cost
'''
tf.reset_default_graph()
with tf.Session() as sess:
    np.random.seed(1)
    X,Y = create_placeholders(64,64,3,6)
    parameters = initialize_parameters()
    Z3 = forward_propagation(X,parameters)
    init = tf.global_variables_initializer()
    sess.run(init)
    a = sess.run(Z3,{X:np.random.randn(2,64,64,3),Y:np.random.randn(2,6)})
    print("Z3 = "+ str(a))


'''
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
    """
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=Z3,labels=Y))

    return cost

# GRADED FUNCTION: model
'''
tf.reset_default_graph()
with tf.Session() as sess:
    np.random.seed(1)
    X,Y = create_placeholders(64,64,3,6)
    parameters = initialize_parameters()
    Z3 = forward_propagation(X,parameters)
    cost = compute_cost(Z3,Y)
    init = tf.global_variables_initializer()
    sess.run(init)
    a = sess.run(cost,{X:np.random.randn(4,64,64,3),Y:np.random.randn(4,6)})

    print("cost=" + str(a))
'''
'''

'''
# GRADED FUNCTION: model

def model(X_train, Y_train, X_test, Y_test, learning_rate = 0.0009,
          num_epochs = 300, minibatch_size = 64, print_cost = True):
    """
    Implements a three-layer ConvNet in Tensorflow:
    CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED

    Arguments:
    X_train -- training set, of shape (None, 64, 64, 3)
    Y_train -- test set, of shape (None, n_y = 6)
    X_test -- training set, of shape (None, 64, 64, 3)
    Y_test -- test set, of shape (None, n_y = 6)
    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:
    train_accuracy -- real number, accuracy on the train set (X_train)
    test_accuracy -- real number, testing accuracy on the test set (X_test)
    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 results consistent (tensorflow seed)
    seed = 3                                          # to keep results consistent (numpy seed)
    (m, n_H0, n_W0, n_C0) = X_train.shape
    n_y = Y_train.shape[1]
    costs = []                                        # To keep track of the cost

    # Create Placeholders of the correct shape
    ### START CODE HERE ### (1 line)
    X, Y = create_placeholders(n_H0,n_W0,n_C0,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 that minimizes the cost.
    ### START CODE HERE ### (1 line)
    optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)
    ### END CODE HERE ###

    # Initialize all the variables globally
    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):

            minibatch_cost = 0.
            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)
                _ , temp_cost = sess.run([optimizer,cost],feed_dict={X:minibatch_X,Y:minibatch_Y})
                ### END CODE HERE ###

                minibatch_cost += temp_cost / num_minibatches


            # Print the cost every epoch
            if print_cost == True and epoch % 5 == 0:
                print ("Cost after epoch %i: %f" % (epoch, minibatch_cost))
            if print_cost == True and epoch % 1 == 0:
                costs.append(minibatch_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()

        # Calculate the correct predictions
        predict_op = tf.argmax(Z3, 1)
        correct_prediction = tf.equal(predict_op, tf.argmax(Y, 1))

        # Calculate accuracy on the test set
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
        print(accuracy)
        train_accuracy = accuracy.eval({X: X_train, Y: Y_train})
        test_accuracy = accuracy.eval({X: X_test, Y: Y_test})
        print("Train Accuracy:", train_accuracy)
        print("Test Accuracy:", test_accuracy)

        return train_accuracy, test_accuracy, parameters

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

程序运行结果：
Cost after epoch 0: 1.976589
Cost after epoch 5: 1.895094
Cost after epoch 10: 1.884952
Cost after epoch 15: 1.862152
Cost after epoch 20: 1.792553
Cost after epoch 25: 1.659748
Cost after epoch 30: 1.439652
Cost after epoch 35: 1.210028
Cost after epoch 40: 1.059912
Cost after epoch 45: 0.950599
Cost after epoch 50: 0.864589
Cost after epoch 55: 0.779795
Cost after epoch 60: 0.721491
Cost after epoch 65: 0.659299
Cost after epoch 70: 0.622481
Cost after epoch 75: 0.587786
Cost after epoch 80: 0.553721
Cost after epoch 85: 0.515339
Cost after epoch 90: 0.481323
Cost after epoch 95: 0.464154
Cost after epoch 100: 0.450780
Cost after epoch 105: 0.419089
Cost after epoch 110: 0.393920
Cost after epoch 115: 0.381122
Cost after epoch 120: 0.375946
Cost after epoch 125: 0.361885
Cost after epoch 130: 0.344810
Cost after epoch 135: 0.328714
Cost after epoch 140: 0.321064
Cost after epoch 145: 0.299867
Cost after epoch 150: 0.298625
Cost after epoch 155: 0.284655
Cost after epoch 160: 0.269399
Cost after epoch 165: 0.264294
Cost after epoch 170: 0.269712
Cost after epoch 175: 0.267915
Cost after epoch 180: 0.242613
Cost after epoch 185: 0.228068
Cost after epoch 190: 0.218832
Cost after epoch 195: 0.213510
Cost after epoch 200: 0.205735
Cost after epoch 205: 0.200092
Cost after epoch 210: 0.196989
Cost after epoch 215: 0.187289
Cost after epoch 220: 0.181605
Cost after epoch 225: 0.186336
Cost after epoch 230: 0.177865
Cost after epoch 235: 0.174295
Cost after epoch 240: 0.165915
Cost after epoch 245: 0.168665
Cost after epoch 250: 0.151124
Cost after epoch 255: 0.157855
Cost after epoch 260: 0.157312
Cost after epoch 265: 0.150373
Cost after epoch 270: 0.148940
Cost after epoch 275: 0.139157
Cost after epoch 280: 0.136293
Cost after epoch 285: 0.127223
Cost after epoch 290: 0.132367
Cost after epoch 295: 0.118375
Tensor("Mean_1:0", shape=(), dtype=float32)
Train Accuracy: 0.9759259
Test Accuracy: 0.89166665

Process finished with exit code 0