LeNet - 5模型實現_MNIST數據

mnist_inference.py

import tensorflow as tf

#配置神經網絡的參數
IMPUT_NODE = 784
OUTPUT_NODE = 10

IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10

# 第一層卷積層的尺寸和深度
CONV1_DEEP = 32
CONV1_SIZE = 5
# 第二層卷積層的尺寸和深度
CONV2_DEEP = 64
CONV2_SIZE = 5
# 全連接層的節點個數
FC_SIZE = 512

# 定義卷積神經網絡的前向傳播過程
def inference(input_tensor, train, regularizer):

    # 實現第一層卷積層的前向傳播過程
    with tf.variable_scope("layer1-conv1"):
        conv1_weights = tf.get_variable("weight", [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_DEEP], initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv1_biases = tf.get_variable("bias", [CONV1_DEEP], initializer=tf.constant_initializer(0.0))

        # 使用邊長爲5，深度爲32的過濾器，過濾器移動步長爲1， 且使用全0填充
        conv1 = tf.nn.conv2d(input_tensor, conv1_weights, strides = [1, 1, 1, 1], padding = "SAME")
        relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))

    # 實現第二層池化層的前向傳播過程
    with tf.name_scope("layer2-pool1"):
        pool1 = tf.nn.max_pool(relu1, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME')

    # 實現第三層卷積層前向傳播過程
    with tf.variable_scope("layer3-conv2"):
        conv2_weights = tf.get_variable('weight', [CONV2_SIZE, CONV2_SIZE, CONV1_DEEP, CONV2_DEEP], initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv2_biases = tf.get_variable('bias', [CONV2_DEEP], initializer = tf.constant_initializer(0.0))

        conv2 = tf.nn.conv2d(pool1, conv2_weights, strides = [1, 1, 1, 1], padding = "SAME")
        relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
    
    # 實現第四層池化層的前向傳播過程
    with tf.name_scope("layer4-pool2"):
        pool2 = tf.nn.max_pool(relu2, ksize = [1, 2, 2, 1], strides= [1, 2, 2, 1], padding = "SAME")
    
    # 將第四層池化層的輸出轉換成第五層全連接層的輸入格式
    pool_shape = pool2.get_shape().as_list()
    nodes = pool_shape[1] * pool_shape[2] * pool_shape[3]

    # 通過tf.reshape函數將第四層的輸出變成一個batch的向量
    reshaped = tf.reshape(pool2, [pool_shape[0], nodes])

    # 聲明第五層全連接的變量並實現前向傳播過程
    with tf.variable_scope("layer5-fc1"):
        fc1_weights = tf.get_variable("weight", [nodes, FC_SIZE], initializer = tf.truncated_normal_initializer(stddev=0.1))
        # 只有全連接層的權重需要加入正則化
        if regularizer != None:
            tf.add_to_collection('losses', regularizer(fc1_weights))
        fc1_biases = tf.get_variable('bias', [FC_SIZE], initializer=tf.constant_initializer(0.1))
        
        fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biases)
        if train:
            fc1 = tf.nn.dropout(fc1, 0.5)

    # 聲明第六層全連接層的變量並實現前向傳播算法
    with tf.variable_scope("layer6-fc2"):
        fc2_weights = tf.get_variable('weight', [FC_SIZE, NUM_LABELS], initializer=tf.truncated_normal_initializer(stddev=0.1))

        if regularizer != None:
            tf.add_to_collection("losses", regularizer(fc2_weights))
        fc2_biases = tf.get_variable("bias", [NUM_LABELS], initializer = tf.constant_initializer(0.1))
        logit = tf.matmul(fc1, fc2_weights) + fc2_biases
    return logit

mnist_train.py

import os
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# 加載mnist_inference.py中定義的常亮和前向傳播函數
import mnist_inference

# 配置神經網絡的參數
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAINING_STEPS = 80000
MOVING_AVERAGE_DECAY = 0.99

# 模型保存的路徑及文件名
MODEL_SAVE_PATH = "D:/Python/"
MODEL_NAME = "model.ckpt"

def train(mnist):
    # 定義輸入輸出placeholder.
    x = tf.placeholder(tf.float32, [BATCH_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS], name="x-input")
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name = "y-input")

    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
    # 直接使用mnist_inference.py中的前向傳播過程
    y = mnist_inference.inference(x, True, regularizer)
    global_step = tf.Variable(0, trainable = False)

    # 定義損失函數，學習率， 滑動平均操作以及訓練過程
    variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)

    variable_average_op = variable_average.apply(tf.trainable_variables())

    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = y, labels = tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection("losses"))

    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY, staircase=True)

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    with tf.control_dependencies([train_step, variable_average_op]):
        train_op = tf.no_op(name = 'train')

    # 初始化TensorFlow持久化類。
    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        
        for i  in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            
            reshaped_xs = np.reshape(xs, (BATCH_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS))
            ### ??????????????????????????????
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict = {x: reshaped_xs, y_: ys})

            # 每1000輪保存一次模型
            if i % 1000 == 0:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)

def main(argv = None):
    mnist = input_data.read_data_sets("F:/AI/MNIST_DATA", one_hot = True)
    train(mnist)

if __name__ == '__main__':
    tf.app.run()

mnist_eval.py

# -*- coding: utf-8 -*-
import time
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#  加載mnist_inference.py和mnist_train.py 中定義的常量和函數
import mnist_inference
import mnist_train

# 每10s加載一次新的模型，並在測試數據上測試新模型的正確性
EAVL_INTERVAL_SECS = 10
def evaluate(mnist):
    with tf.Graph().as_default() as g:
        print(mnist.validation.num_examples)
        x = tf.placeholder(tf.float32, [mnist.validation.num_examples, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS], name="x-input")
        
        y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name = 'y-input')

        x_images = np.reshape(mnist.validation.images, (mnist.validation.num_examples, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS))
        validate_feed = {x: x_images, y_: mnist.validation.labels}

        y = mnist_inference.inference(x, False, None)

        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        # 通過變量重命名的方式來加載模型，這樣在前向傳播的過程中就不需要調用求滑動平均模型來獲取平均值了。
        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                # tf.train.get_checkpoint_state 函數會通過checkpoint文件自動找到目錄中最新模型的文件名
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    # 加載模型：
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    # 通過文件名得到模型保存時迭代的輪數
                    global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                    accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                    print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
                else:
                    print("No checkpoint file found")
                    return 
            time.sleep(EAVL_INTERVAL_SECS)

def main(argv=None):
    mnist = input_data.read_data_sets("F:/AI/MNIST_DATA", one_hot = True)
    evaluate(mnist)

if __name__ == "__main__":
    tf.app.run()