吴恩达深度学习2-Week3课后作业-Tensorflow

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/Apple_hzc/article/details/83688665

一、deeplearning-assignment

到目前为止，我们一直使用numpy来建立神经网络。这次作业将深入学习框架，可以更容易地建立神经网络。

TensorFlow，PaddlePaddle，Torch，Caffe，Keras等机器学习框架可以显著地加速机器学习开发。这些框架有很多文档，可以随意阅读。在本次任务中，将学习如何在TensorFlow中执行以下操作：

• 初始化变量
• 开始你自己的会话
• 训练算法
• 实现一个神经网络

编程框架不仅可以缩短编码时间，但有时也可以执行优化来加速代码，关于tensorflow相关算法在文章后面已给出。

现在有这样一个问题：对于0-5的手势图片，利用tensorflow框架实现softmax分类器。

训练数据：1080张手势图片代表0-5的数字，每张图片是64 * 64像素大小，每种数字180张图片。

测试数据：120张手势图片代表0-5的数字，每张图片是64 * 64像素大小，每种数字20张图片。

目标是建立一个模型，使得能够以高准确度识别一张图片对应的数字。模型的结构为： LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX。

实验结果：

---

二、相关算法代码

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

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
np.random.seed(1)


# y_hat = tf.constant(36, name='y_hat')
# y = tf.constant(39, name='y')
#
# loss = tf.Variable((y - y_hat) ** 2, name='loss')
# init = tf.global_variables_initializer()
# with tf.Session() as session:
#     session.run(init)
#     print(session.run(loss))

# a = tf.constant(2)
# b = tf.constant(10)
# c = tf.multiply(a, b)
# sess = tf.Session()
# print(sess.run(c))

# x = tf.placeholder(tf.int64, name='x')
# print(sess.run(2 * x, feed_dict={x: 3}))
# sess.close()


def linear_function():
    np.random.seed(1)
    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.add(tf.matmul(W, X), b)

    sess = tf.Session()
    result = sess.run(Y)
    sess.close()

    return result


# print("result = " + str(linear_function()))


def sigmoid(z):
    x = tf.placeholder(tf.float32, name='x')
    sigmoid = tf.sigmoid(x)
    with tf.Session() as session:
        result = session.run(sigmoid, feed_dict={x: z})
    return result


# print("sigmoid(0) = " + str(sigmoid(0)))
# print("sigmoid(12) = " + str(sigmoid(12)))


def cost(logits, labels):
    z = tf.placeholder(tf.float32, name='logits')
    y = tf.placeholder(tf.float32, name='labels')

    cost = tf.nn.sigmoid_cross_entropy_with_logits(logits=z, labels=y)
    session = tf.Session()
    cost = session.run(cost, feed_dict={z: logits, y: labels})
    session.close()

    return cost


# logits = sigmoid(np.array([0.2, 0.4, 0.7, 0.9]))
# cost = cost(logits, np.array([0, 0, 1, 1]))
# print(logits)


def one_hot_matrix(labels, C):
    C = tf.constant(C, name='C')
    one_hot_matrix = tf.one_hot(labels, C, axis=0)

    sess = tf.Session()
    one_hot = sess.run(one_hot_matrix)
    sess.close()

    return one_hot


# labels = np.array([1, 2, 3, 0, 2, 1])
# one_hot = one_hot_matrix(labels, C=4)
# print("one_hot = " + str(one_hot))


def ones(shape):
    ones = tf.ones(shape)
    sess = tf.Session()
    ones = sess.run(ones)
    sess.close()
    return ones


# print("ones = " + str(ones([3])))


X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()
# print(X_train_orig.shape)
# print(Y_train_orig.shape)
# print(X_test_orig.shape)
# print(Y_test_orig.shape)

# index = 0
# plt.imshow(X_train_orig[index])
# plt.show()
# print("y = " + str(np.squeeze(Y_train_orig[:, index])))

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
X_train = X_train_flatten / 255.
X_test = X_test_flatten / 255.
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))


def create_placeholders(n_x, n_y):
    X = tf.placeholder(tf.float32, shape=(n_x, None), name='X')
    Y = tf.placeholder(tf.float32, shape=(n_y, None), name='Y')

    return X, Y


# X, Y = create_placeholders(12288, 6)
# print("X = " + str(X))
# print("Y = " + str(Y))


def initialize_parameters():
    tf.set_random_seed(1)

    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())

    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2,
                  "W3": W3,
                  "b3": b3}

    return parameters


# tf.reset_default_graph()
# with tf.Session() as sess:
#     parameters = initialize_parameters()
#     print("W1 = " + str(parameters["W1"]))
#     print("b1 = " + str(parameters["b1"]))
#     print("W2 = " + str(parameters["W2"]))
#     print("b2 = " + str(parameters["b2"]))


def forward_propagation(X, parameters):
    W1 = parameters['W1']
    b1 = parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']
    W3 = parameters['W3']
    b3 = parameters['b3']

    Z1 = tf.matmul(W1, X) + b1
    A1 = tf.nn.relu(Z1)
    Z2 = tf.matmul(W2, A1) + b2
    A2 = tf.nn.relu(Z2)
    Z3 = tf.matmul(W3, A2) + b3

    return Z3


# 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))


def compute_cost(Z3, Y):
    logits = tf.transpose(Z3)
    labels = tf.transpose(Y)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=labels))
    return cost


# tf.reset_default_graph()
# with tf.Session() as sess:
#     X, Y = create_placeholders(12288, 6)
#     parameters = initialize_parameters()
#     Z3 = forward_propagation(X, parameters)
#     cost = compute_cost(Z3, Y)
#     print("cost = " + str(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.
    ops.reset_default_graph()
    tf.set_random_seed(1)
    seed = 3
    (n_x, m) = X_train.shape
    n_y = Y_train.shape[0]
    costs = []

    X, Y = create_placeholders(n_x, n_y)
    parameters = initialize_parameters()
    Z3 = forward_propagation(X, parameters)
    cost = compute_cost(Z3, Y)

    optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)

    init = tf.global_variables_initializer()

    with tf.Session() as sess:
        sess.run(init)
        for epoch in range(num_epochs):
            epoch_cost = 0.
            num_minibatches = int(m / minibatch_size)
            seed = seed + 1
            minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)

            for minibatch in minibatches:
                (minibatch_X, minibatch_Y) = minibatch
                _, minibatch_cost = sess.run([optimizer, cost], feed_dict={X: minibatch_X, Y: minibatch_Y})

                epoch_cost += minibatch_cost / num_minibatches

            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)

        plt.plot(np.squeeze(costs))
        plt.ylabel('cost')
        plt.xlabel('iterations (per tens)')
        plt.title("Learning rate =" + str(learning_rate))
        plt.show()

        parameters = sess.run(parameters)
        print("Parameters have been trained!")

        correct_prediction = tf.equal(tf.argmax(Z3), tf.argmax(Y))

        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)

---

三、总结

tensorflow是深度学习里的一种框架，可以帮助我们更快地建立模型。

当利用tensorflow进行编码时，主要可分为如下步骤：

1. 创建一个graph，包括张量（Variables，Placeholders...）和操作（tf.matmul，tf.add...）。
2. 创建一个session。
3. 将session初始化。
4. 通过run上述的session来执行graph。

当在optimizer对象中run初始化的session时，反向传播和优化是自动完成的。