卷积神经网络（CNN）实战

一、本文基于Tensorflow采用CNN做的手写字体识别，话不多说上代码

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import tensorflow as tf


LEARNING_RATE = 1e-4
TRAINING_ITERATIONS = 2500
DROPOUT = 0.5
BATCH_SIZE = 50
VALIDATION_SIZE = 2000
IMAGINE_TO_DISPLAY = 10

from tensorflow import keras
(x_train,y_train),(x_test,y_test) = keras.datasets.mnist.load_data()
x_train = np.multiply(x_train,1.0/255.0).astype(np.float32)
x_test = np.multiply(x_test,1.0/255.0).astype(np.float32)
def dense_to_one_hot(labels_dense,num_classes):
    num_labels = labels_dense.shape[0]
    index_offset = np.arange(num_labels) * num_classes
    labels_one_hot = np.zeros((num_labels,num_classes))
    labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
    return labels_one_hot
y_train = dense_to_one_hot(y_train,10).astype(np.float32)
y_test = dense_to_one_hot(y_test,10).astype(np.float32)
def weight_variable(shape):
    initial = tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)
def bias_variable(shape):
    initial = tf.constant(0.1,shape=shape)
    return tf.Variable(initial)
def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')


x_train = x_train.reshape([-1,784])
x_test = x_test.reshape([-1,784])

# input and output
x = tf.placeholder('float', shape=[None, 784])
y_ = tf.placeholder('float', shape=[None, 10])
#第一个卷积层计算
#宽5 高5 channel为1 用多少个filter来计算，这里是32
W_conv1 = weight_variable([5, 5, 1, 32])
#执行卷积后得到了32个图，所以需要32个偏置
b_conv1 = bias_variable([32])

# (40000,784) => (40000,28,28,1)
image = tf.reshape(x, [-1,28 , 28,1])
#print (image.get_shape()) # =>(40000,28,28,1)

h_conv1 = tf.nn.relu(conv2d(image, W_conv1) + b_conv1)
#print (h_conv1.get_shape()) # => (40000, 28, 28, 32)
h_pool1 = max_pool_2x2(h_conv1)


W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
#print (h_conv2.get_shape()) # => (40000, 14,14, 64)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

# (40000, 7, 7, 64) => (40000, 3136)
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder('float')
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#print (y.get_shape()) # => (40000, 10)

# cost function
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
# optimisation function
train_step = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(cross_entropy)
# evaluation
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
# prediction function
#[0.1, 0.9, 0.2, 0.1, 0.1 0.3, 0.5, 0.1, 0.2, 0.3] => 1

epochs_completed = 0
index_in_epoch = 0
num_examples = x_train.shape[0]

# serve data by batches
def next_batch(batch_size):

    global x_train
    global y_train
    global index_in_epoch
    global epochs_completed

    start = index_in_epoch
    index_in_epoch += batch_size

    # when all trainig data have been already used, it is reorder randomly
    if index_in_epoch > num_examples:
        # finished epoch
        epochs_completed += 1
        # shuffle the data
        perm = np.arange(num_examples)
        np.random.shuffle(perm)
        x_train = x_train[perm]
        y_train = y_train[perm]
        # start next epoch
        start = 0
        index_in_epoch = batch_size
        assert batch_size <= num_examples
    end = index_in_epoch
    return x_train[start:end], y_train[start:end]

# start TensorFlow session
init = tf.initialize_all_variables()
sess = tf.InteractiveSession()

sess.run(init)

# visualisation variables
train_accuracies = []
validation_accuracies = []
x_range = []

display_step=1

for i in range(TRAINING_ITERATIONS):

    #get new batch
    batch_xs, batch_ys = next_batch(BATCH_SIZE)

    # check progress on every 1st,2nd,...,10th,20th,...,100th... step
    if i%display_step == 0 or (i+1) == TRAINING_ITERATIONS:
        train_accuracy = accuracy.eval(feed_dict={x: batch_xs, y_: batch_ys, keep_prob: 1.0})
        if(VALIDATION_SIZE):
            validation_accuracy = accuracy.eval(feed_dict={ x: x_test[0:BATCH_SIZE],
                                                            y_: y_test[0:BATCH_SIZE],
                                                            keep_prob: 1.0})
            print('training_accuracy / validation_accuracy => %.2f / %.2f for step %d'%(train_accuracy, validation_accuracy, i))

            validation_accuracies.append(validation_accuracy)

        else:
            print('training_accuracy => %.4f for step %d'%(train_accuracy, i))
        train_accuracies.append(train_accuracy)
        x_range.append(i)

        # increase display_step
        if i%(display_step*10) == 0 and i:
            display_step *= 10
    # train on batch
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys, keep_prob: DROPOUT})