1.mnist_train.py
# -*- coding: utf-8 -*- """ Created on Mon Dec 23 20:01:39 2019 tensorflow實現Lenet-5網絡，mnist_train.py實現lenet-5訓練過程 @author: zhaoy """ ##lenet-5訓練過程 import os import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import numpy as np import mnist_inference ##配置神經網絡的參數 BATCH_SIZE=100 LEARNING_RATE_BASE=0.01 #基礎學習率 LEARNING_RATE_DECAY=0.99 REGULARAZTION_RATE=0.0001 TRAINING_STEPS=30000 MOVING_AVERAGE_DECAY=0.99 ##模型保存的路徑和文件名 MODEL_SAVE_PATH="./model/" MODEL_NAME="model.ckpt" ##定義訓練過程 def train(mnist): #區別與全連接神經網絡的輸入是一個二維[None, mnist_inference.INPUT_NODE]， #卷積神經網絡的輸入x是一個四維數組 x=tf.placeholder(tf.float32,[ BATCH_SIZE, # 第一維表示一個batch中樣例的個數 mnist_inference.IMAGE_SIZE, # 第二維和第三維表示圖片的尺寸28 mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS], #圖像通道數，黑白圖像賦值1，彩色圖像賦值3 name='x-input') y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE] , name='y-input') regularizer=tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE) y=mnist_inference.inference(x,True,regularizer) global_step=tf.Variable(0,trainable=False) #給定滑動平均衰減率和訓練輪數的變量，初始化滑動平均類 variable_averages=tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step) #在所有代表神經網絡參數的變量上使用滑動平均。 variables_averages_op=variable_averages.apply(tf.trainable_variables()) #計算交叉熵作為刻畫預測值和真實值之間差距的損失函數 cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_,1)) #計算在當前batch中所有樣例的交叉熵平均值 cross_entropy_mean=tf.reduce_mean(cross_entropy) #計算L2正則化損失函數 #regularizer=tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE) #計算模型的正則化損失 #regularization=regularizer(weights1)+regularizer(weights2) #總損失等於交叉熵損失和正則化損失的和 loss=cross_entropy_mean+tf.add_n(tf.get_collection('losses')) #regularization #設置指數衰減的學習率 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,variables_averages_op]):train_op=tf.no_op(name='train') train_op=tf.group(train_step, variables_averages_op) #初始化tensorflow持久化類 saver=tf.train.Saver() ##初始化會話並開始訓練過程 with tf.Session() as sess: tf.global_variables_initializer().run() print("****************開始訓練************************") # validate_feed={x:mnist.validation.images,y_:mnist.validation.labels} #准備測試數據. #test_feed={x:mnist.test.images,y_:mnist.test.labels} #迭代地訓練神經網絡 for i in range(TRAINING_STEPS): xs,ys=mnist.train.next_batch(BATCH_SIZE) #區別於全連接神經網絡，卷積神經網絡的輸入為四維數組 reshaped_xs = np.reshape(xs, (BATCH_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS)) train_op_renew,loss_value, step=sess.run([train_op,loss,global_step], feed_dict={x:reshaped_xs,y_:ys}) 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("MNIST_data/",one_hot=True) train(mnist) if __name__=='__main__': tf.app.run()
2.mnist_inference.py
# -*- coding: utf-8 -*- """ Created on Mon Dec 23 19:44:19 2019 Tensorflow實現LeNet-5模型,mnist_inference.py實現神經卷積網絡前向傳播過程 @author: zhaoy """ ##實現神經卷積網絡的前向傳播過程 import tensorflow as tf INPUT_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_SISE=512 tf.reset_default_graph() #定義卷積神經網絡的前向傳播過程，這里添加了一個新的參數train用以區分訓練過程和測試過程；train為布爾量： #采用dropout機制防止過擬合，在全連接層layer5-fc1中包含dropout機制， def inference(input_tensor,train,regularizer): ##聲明第一層卷積層的變量並實現前向傳播過程，這一層的輸入為28*28*1的矩陣，由於采取全0填充，所以輸出層為28*28*32的矩陣 with tf.variable_scope('layer1-conv1'): conv1_weights=tf.get_variable("weights",[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)) #使用邊長為5，深度為32的過濾器，過濾器移動的步長為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），這里選用最大池化層，池化層的過濾器的邊長為2，所以輸出為14*14*32 with tf.name_scope('layer2-poll'): pool1=tf.nn.max_pool(relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME') ##聲明第三層卷積層的變量並實現前向傳播過程，這一層的輸入為14*14*32的矩陣，輸出為14*14*64 with tf.variable_scope('layer3-conv2'): conv2_weights=tf.get_variable("weights",[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)) #使用邊長為5，深度為64的過濾器，過濾器移動的步長為1，且使用全0填充. 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,輸入為14*14*64的矩陣，輸出為7*7*64的矩陣 with tf.name_scope('layer4-pool2'): pool2=tf.nn.max_pool(relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME') #第四層的輸出為7*7*64，然而第五層全連接層需要的輸入格式為向量，所以這里需要將7*7*64拉伸為一個向量。 #pool2.get_shape。因為每層網絡的輸入輸出都是一batch，矩陣所以這里的維度也包含batch中數據的個數 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編程一個batch的向量 reshaped=tf.reshape(pool2,[pool_shape[0],nodes]) #聲明第五層全連接層的變量並實現前向傳播過程，這一層是一個拉直后的一組向量，向量長度為3136，輸出為為一組長度為512的向量 #引入dropout機制，droupout在訓練時會隨機將部分節點輸出為0，即使部分節點“死掉” with tf.variable_scope('layer5-fc1'): fc1_weights=tf.get_variable("weight",[nodes,FC_SISE], initializer=tf.truncated_normal_initializer(stddev=0.1)) if regularizer!=None: tf.add_to_collection('losses',regularizer(fc1_weights)) fc1_biases=tf.get_variable("bias",[FC_SISE],initializer=tf.constant_initializer(0.1)) fc1=tf.nn.relu(tf.matmul(reshaped,fc1_weights)+fc1_biases) #duopout系數為0.5 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過程，這一層輸入為長度為512的向量，輸出為一組長度10的向量 with tf.variable_scope('layer6-fc2'): fc2_weights=tf.get_variable("weight",[FC_SISE,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 ##返回第六層的輸出 return logit
3.mnist_test.py
# -*- coding: utf-8 -*- """ Created on Mon Dec 23 17:28:07 2019 tensorflow實現神經網絡對mnist手寫字的識別，mnist_test.py評估訓練的神經網絡在mnist測試集的正確率 @author: zhaoy """ 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 def evaluate(mnist): with tf.Graph().as_default() as g: # 定義輸入輸出的格式。 x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input') y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input') test_feed = {x: mnist.test.images, y_: mnist.test.labels} # 直接通過調用封裝好的函數來計算前向傳播的結果。因為測試時不關注ze正則化損失的值 # 所以這里用於計算正則化損失的函數被設置為None。 y = mnist_inference.inference(x, None) # 使用前向傳播的結果計算正確率。如果需要對未知的樣例進行分類，那么使用 # tf.argmax(y,1)就可以得到輸入樣例的預測類別了。 correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # 同訓練模型一樣，定義一個滑動平均類 variable_averages = tf.train.ExponentialMovingAverage( mnist_train.MOVING_AVERAGE_DECAY ) #在使用滑動平均進行模型訓練時，模型除了保存網絡參數以外，還會保存相應的滑動平均參數， #此時加載模型參數需要聯通滑動參數一起加載模型時，需要用到.variables_to_restore variables_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variables_to_restore) 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。 #split函數：拆分字符串。通過指定分隔符對字符串進行切片，並返回分割后的字符串列表（list）。 #split函數返回值為：分割后的字符串列表。 #list[n]：即表示選取第n個分片,n為-1即為末尾倒數第一個分片（分片即為在返回值列表中元素） global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] accuracy_score = sess.run(accuracy, feed_dict=test_feed) print("After %s training step(s), test " "accuracy = %g" % (global_step, accuracy_score)) else: print("No checkpoint file found") return def main(argv=None): mnist = input_data.read_data_sets("C:/Users/zhaoy/Desktop/Tensorflow/sample/data/MNIST", one_hot=True) #one_hot表示0-1編碼 evaluate(mnist) if __name__ == "__main__": tf.app.run()
4.predict.py
# -*- coding: utf-8 -*- """ Created on Fri Dec 27 17:35:39 2019 @author: zhaoy """ import tensorflow as tf # 加載mnist_inference.py 和mnist_train.py中定義的常量和函數。 import mnist_inference import mnist_train import cv2 def imageprepare(file_name): im = cv2.imread(file_name,0) print(file_name) pixels = [] h, w = im.shape #normalize pixels to 0 and 1. 0 is pure white, 1 is pure black. for i in range(h): for j in range(w): #如果是白底黑字則為：pixels.append((255-im[i,j])*1.0/255.0) pixels.append(im[i, j]*1.0/255.0) #print(pixels) return pixels # ============================================================================= # def imageprepare(file_name): # image = tf.gfile.FastGFile(file_name, 'rb').read() # print(file_name) # pixels = [] # image_data = tf.image.decode_jpeg(image) # image_data = tf.image.convert_image_dtype(image_data, dtype=tf.float32) # # pixels.append(image_data) # return pixels # ============================================================================= x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input') y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input') y = mnist_inference.inference(x, None) 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) prediction = tf.argmax(y, 1) probability = tf.nn.softmax(y) with tf.Session() as sess: result = imageprepare('4.jpg') tf.global_variables_initializer().run() 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) pre, prob = sess.run([prediction, probability], feed_dict={x:[result]}) #pre = prediction.eval(feed_dict={x:[result]}, session=sess) #global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] #accuracy_score = sess.run(accuracy, feed_dict=test_feed) print( "recognize result = %d," "the probability is %g " % (pre[0],prob[0][pre])) else: print("No checkpoint file found")