吴恩达DeepLearning第四部分作业week1(1) 使用tensorflow搭建CNN

手搓CNN还在尝试中，写了1天还没写完，先把简单的用tensorflow搭建的写出来。

首先处理数据：

import os
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import cnn_utils

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'  # 忽略警告
np.random.seed(1)

# 数据处理
train_set_x, train_set_y, test_set_x, test_set_y, classes = cnn_utils.load_dataset()

train_x = train_set_x / 255  # 归一化操作，原图是RGB图像uint8
test_x = test_set_x / 255


def one_hot(y, c):
    y_onehot = tf.one_hot(y, c.shape[0])
    with tf.Session() as session:
        result = session.run(y_onehot)
        session.close()
    return result


train_y = np.squeeze(one_hot(train_set_y, classes))
test_y = np.squeeze(one_hot(test_set_y, classes))
#print(train_x.shape, train_y.shape, test_x.shape, test_y.shape, classes.shape)

 

 直接建模，绘制损失函数图像，并保存模型：

这边按吴恩达上课演示的模型搭建，2个conv，2个fc，1个softmax

def model(x, y, epoch, batch_size, learning_rate=0.001, beta1=0.9, beta2=0.99):
    X = tf.placeholder(tf.float32, shape=[None, x.shape[1], x.shape[2], x.shape[3]], name='X')
    Y = tf.placeholder(tf.float32, shape=[None, y.shape[1]], name='Y')
    f1 = 5
    nc1 = 8
    f2 = 5
    nc2 = 16
    tf.set_random_seed(1)
    w1 = tf.get_variable("w1", [f1, f1, X.shape[3], nc1], tf.float32,
                         initializer=tf.contrib.layers.xavier_initializer())
    b1 = tf.get_variable("b1", [nc1], tf.float32, initializer=tf.zeros_initializer())
    w2 = tf.get_variable("w2", [f2, f2, nc1, nc2], tf.float32, initializer=tf.contrib.layers.xavier_initializer())
    b2 = tf.get_variable("b2", [nc2], tf.float32, initializer=tf.zeros_initializer())
    w1x = tf.nn.conv2d(X, w1, [1, 1, 1, 1], padding='VALID')
    z1 = tf.nn.bias_add(w1x, b1)  # b:一维的Tensor，数据维度和value的最后一维相同。
    a1 = tf.nn.relu(z1)
    a1_m = tf.nn.max_pool(a1, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')

    w2a1 = tf.nn.conv2d(a1_m, w2, [1, 1, 1, 1], padding='VALID')
    z2 = tf.nn.bias_add(w2a1, b2)
    a2 = tf.nn.relu(z2)
    a2_m = tf.nn.max_pool(a2, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')

    a_f = tf.contrib.layers.flatten(a2_m)
    a3 = tf.contrib.layers.fully_connected(a_f, 120)
    a4 = tf.contrib.layers.fully_connected(a3, 84)
    z5 = tf.contrib.layers.fully_connected(a4, 6, activation_fn=None)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=z5, labels=Y))
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=beta1, beta2=beta2).minimize(cost)
    init = tf.global_variables_initializer()
    saver = tf.train.Saver()
    with tf.Session() as sess:
        sess.run(init)
        costs = []
        for i in range(epoch):
            # 洗牌
            cost_mean = 0
            temp = np.random.permutation(x.shape[0])
            x_shutter = x[temp, :, :, :]
            y_shutter = y[temp, :]
            num = int(x.shape[0] / batch_size)
            for j in range(num):
                x_batch = x_shutter[j * batch_size:(j + 1) * batch_size]
                y_batch = y_shutter[j * batch_size:(j + 1) * batch_size]
                _, cost_ = sess.run([optimizer, cost], feed_dict={X: x_batch, Y: y_batch})
                cost_mean += cost_
            cost_mean = cost_mean / num
            if x.shape[0] % batch_size != 0:
                x_batch = x_shutter[num * batch_size:x.shape[0]]
                y_batch = y_shutter[num * batch_size:y.shape[0]]
                _, cost_ = sess.run([optimizer, cost], feed_dict={X: x_batch, Y: y_batch})
                cost_mean += cost_
            cost_mean = cost_mean / 2
            if i % 1 == 0:
               costs.append(cost_mean)
        saver.save(sess, "./Model/model.ckpt")
        plt.plot(np.squeeze(costs))
        plt.show()

 

 运行：

model(train_x, train_y, 40, 32, 0.001)

读取模型，并评价：

def predict(x, y):
    ops.reset_default_graph()
    X = tf.placeholder(tf.float32, shape=[None, x.shape[1], x.shape[2], x.shape[3]], name='X')
    Y = tf.placeholder(tf.float32, shape=[None, y.shape[1]], name='Y')
    f1 = 5
    nc1 = 8
    f2 = 5
    nc2 = 16
    tf.set_random_seed(1)
    w1 = tf.get_variable("w1", [f1, f1, X.shape[3], nc1])
    b1 = tf.get_variable("b1", [nc1])
    w2 = tf.get_variable("w2", [f2, f2, nc1, nc2])
    b2 = tf.get_variable("b2", [nc2])
    w1x = tf.nn.conv2d(X, w1, [1, 1, 1, 1], padding='VALID')
    z1 = tf.nn.bias_add(w1x, b1)  # b:一维的Tensor，数据维度和value的最后一维相同。
    a1 = tf.nn.relu(z1)
    a1_m = tf.nn.max_pool(a1, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')

    w2a1 = tf.nn.conv2d(a1_m, w2, [1, 1, 1, 1], padding='VALID')
    z2 = tf.nn.bias_add(w2a1, b2)
    a2 = tf.nn.relu(z2)
    a2_m = tf.nn.max_pool(a2, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')

    a_f = tf.contrib.layers.flatten(a2_m)
    a3 = tf.contrib.layers.fully_connected(a_f, 120)
    a4 = tf.contrib.layers.fully_connected(a3, 84)
    z5 = tf.contrib.layers.fully_connected(a4, 6, activation_fn=None)
    saver = tf.train.Saver()
    with tf.Session() as sess:
        saver.restore(sess, "./Model/model.ckpt")
        correct_prediction = tf.equal(tf.argmax(z5, axis=1), tf.argmax(Y, axis=1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
        result = accuracy.eval({X: x, Y: y})
    return result


print("测试集的准确率：", predict(test_x, test_y))
print("训练集的准确率：", predict(train_x, train_y))

结果：

测试集的准确率： 0.941667
训练集的准确率： 1.0

好的过分，有点过拟合