TensorFlow搭建神經網路最佳實務，tensorflow最佳實務

TensorFlow搭建神經網路最佳實務，tensorflow最佳實務

一、TensorFLow完整範例

在MNIST資料集上，搭建一個簡單神經網路結構，一個包含ReLU單元的非線性化處理的兩層神經網路。在訓練神經網路的時候，使用帶指數衰減的學習率設定、使用正則化來避免過擬合、使用滑動平均模型來使得最終的模型更加健壯。

程式將計算神經網路前向傳播的部分單獨定義一個函數inference，訓練部分定義一個train函數，再定義一個主函數main。

完整程式：

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Thu May 25 08:56:30 2017  @author: marsjhao """  import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data  INPUT_NODE = 784 # 輸入節點數 OUTPUT_NODE = 10 # 輸出節點數 LAYER1_NODE = 500 # 隱含層節點數 BATCH_SIZE = 100 LEARNING_RETE_BASE = 0.8 # 基學習率 LEARNING_RETE_DECAY = 0.99 # 學習率的衰減率 REGULARIZATION_RATE = 0.0001 # 正則化項的權重係數 TRAINING_STEPS = 10000 # 迭代訓練次數 MOVING_AVERAGE_DECAY = 0.99 # 滑動平均的衰減係數  # 傳入神經網路的權重和偏置，計算神經網路前向傳播的結果 def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):   # 判斷是否傳入ExponentialMovingAverage類對象   if avg_class == None:     layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)     return tf.matmul(layer1, weights2) + biases2   else:     layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1))                    + avg_class.average(biases1))     return tf.matmul(layer1, avg_class.average(weights2))\              + avg_class.average(biases2)  # 神經網路模型的訓練過程 def train(mnist):   x = tf.placeholder(tf.float32, [None,INPUT_NODE], name='x-input')   y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')    # 定義神經網路結構的參數   weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE],                         stddev=0.1))   biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))   weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE],                         stddev=0.1))   biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))    # 計算非滑動平均模型下的參數的前向傳播的結果   y = inference(x, None, weights1, biases1, weights2, biases2)      global_step = tf.Variable(0, trainable=False) # 定義儲存當前迭代訓練輪數的變數    # 定義ExponentialMovingAverage類對象   variable_averages = tf.train.ExponentialMovingAverage(             MOVING_AVERAGE_DECAY, global_step) # 傳入當前迭代輪數參數   # 定義對所有可訓練變數trainable_variables進行更新滑動平均值的操作op   variables_averages_op = variable_averages.apply(tf.trainable_variables())    # 計算滑動模型下的參數的前向傳播的結果   average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)    # 定義交叉熵損失值   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)   # 定義L2正則化器並對weights1和weights2正則化   regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)   regularization = regularizer(weights1) + regularizer(weights2)   loss = cross_entropy_mean + regularization # 總損失值    # 定義指數衰減學習率   learning_rate = tf.train.exponential_decay(LEARNING_RETE_BASE, global_step,           mnist.train.num_examples / BATCH_SIZE, LEARNING_RETE_DECAY)   # 定義梯度下降操作op，global_step參數可實現自加1運算   train_step = tf.train.GradientDescentOptimizer(learning_rate)\              .minimize(loss, global_step=global_step)   # 組合兩個操作op   train_op = tf.group(train_step, variables_averages_op)   '''''   # 與tf.group()等價的語句   with tf.control_dependencies([train_step, variables_averages_op]):     train_op = tf.no_op(name='train')   '''   # 定義準確率   # 在最終預測的時候，神經網路的輸出採用的是經過滑動平均的前向傳播計算結果   correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))   accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))    # 初始化回話sess並開始迭代訓練   with tf.Session() as sess:     sess.run(tf.global_variables_initializer())     # 驗證集待喂入資料     validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}     # 測試集待喂入資料     test_feed = {x: mnist.test.images, y_: mnist.test.labels}     for i in range(TRAINING_STEPS):       if i % 1000 == 0:         validate_acc = sess.run(accuracy, feed_dict=validate_feed)         print('After %d training steps, validation accuracy'            ' using average model is %f' % (i, validate_acc))       xs, ys = mnist.train.next_batch(BATCH_SIZE)       sess.run(train_op, feed_dict={x: xs, y_:ys})      test_acc = sess.run(accuracy, feed_dict=test_feed)     print('After %d training steps, test accuracy'        ' using average model is %f' % (TRAINING_STEPS, test_acc))  # 主函數 def main(argv=None):   mnist = input_data.read_data_sets("MNIST_data", one_hot=True)   train(mnist)  # 當前的python檔案是shell檔案執行的入口檔案，而非當做import的python module。 if __name__ == '__main__': # 在模組內部執行   tf.app.run() # 調用main函數並傳入所需的參數list 

二、分析與改進設計

1. 程式分析改進

第一，計算前向傳播的函數inference中需要將所有的變數以參數的形式傳入函數，當神經網路結構變得更加複雜、參數更多的時候，程式的可讀性將變得非常差。

第二，在程式退出時，訓練好的模型就無法再利用，且大型神經網路的訓練時間都比較長，在訓練過程中需要每隔一段時間儲存一次模型訓練的中間結果，這樣如果在訓練過程中程式死機，死機前的最新的模型參數仍能保留，杜絕了時間和資源的浪費。

第三，將訓練和測試分成兩個獨立的程式，將訓練和測試都會用到的前向傳播的過程抽象成單獨的庫函數。這樣就保證了在訓練和預測兩個過程中所調用的前向傳播計算程式是一致的。

2. 改進後程式設計

mnist_inference.py

該檔案中定義了神經網路的前向傳播過程，其中的多次用到的weights定義過程又單獨定義成函數。

通過tf.get_variable函數來擷取變數，在神經網路訓練時建立這些變數，在測試時會通過儲存的模型載入這些變數的取值，而且可以在變數載入時將滑動平均值重新命名。所以可以直接通過同樣的名字在訓練時使用變數自身，在測試時使用變數的滑動平均值。

mnist_train.py

該程式給出了神經網路的完整訓練過程。

mnist_eval.py

在滑動平均模型上做測試。

通過tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)擷取最新模型的檔案名稱，實際是擷取checkpoint檔案的所有內容。

三、TensorFlow最佳實務範例

mnist_inference.py

import tensorflow as tf  INPUT_NODE = 784 OUTPUT_NODE = 10 LAYER1_NODE = 500  def get_weight_variable(shape, regularizer):   weights = tf.get_variable("weights", shape,          initializer=tf.truncated_normal_initializer(stddev=0.1))   if regularizer != None:     # 將權重參數的正則化項加入至損失集合     tf.add_to_collection('losses', regularizer(weights))   return weights  def inference(input_tensor, regularizer):   with tf.variable_scope('layer1'):     weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)     biases = tf.get_variable("biases", [LAYER1_NODE],                  initializer=tf.constant_initializer(0.0))     layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)    with tf.variable_scope('layer2'):     weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)     biases = tf.get_variable("biases", [OUTPUT_NODE],                  initializer=tf.constant_initializer(0.0))     layer2 = tf.matmul(layer1, weights) + biases    return layer2 

mnist_train.py

import os import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import mnist_inference  BATCH_SIZE = 100 LEARNING_RATE_BASE = 0.8 LEARNING_RATE_DECAY = 0.99 REGULARIZATION_RATE = 0.0001 TRAINING_STEPS = 10000 MOVING_AVERAGE_DECAY = 0.99  MODEL_SAVE_PATH = "Model_Folder/" MODEL_NAME = "model.ckpt"  def train(mnist):   # 定義輸入placeholder   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')   # 定義正則化器及計算前向過程輸出   regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)   y = mnist_inference.inference(x, regularizer)   # 定義當前訓練輪數及滑動平均模型   global_step = tf.Variable(0, trainable=False)   variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,                              global_step)   variables_averages_op = variable_averages.apply(tf.trainable_variables())   # 定義損失函數   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'))   # 定義指數衰減學習率   learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step,           mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)   # 定義訓練操作，包括模型訓練及滑動模型操作   train_step = tf.train.GradientDescentOptimizer(learning_rate)\           .minimize(loss, global_step=global_step)   train_op = tf.group(train_step, variables_averages_op)   # 定義Saver類對象，儲存模型，TensorFlow持久化類   saver = tf.train.Saver()    # 定義會話，啟動訓練過程   with tf.Session() as sess:     tf.global_variables_initializer().run()      for i in range(TRAINING_STEPS):       xs, ys = mnist.train.next_batch(BATCH_SIZE)       _, loss_value, step = sess.run([train_op, loss, global_step],                       feed_dict={x: xs, y_: ys})       if i % 1000 == 0:         print("After %d training step(s), loss on training batch is %g."\             % (step, loss_value))         # save方法的global_step參數可以讓每個被儲存的模型的檔案名稱末尾加上當前訓練輪數         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() 

mnist_eval.py

import time import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import mnist_inference import mnist_train  EVAL_INTERVAL_SECS = 10  def evaluate(mnist):   with tf.Graph().as_default() as g:     # 定義輸入placeholder     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')     # 定義feed字典     validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}     # 測試時不加參數正則化損失     y = mnist_inference.inference(x, None)     # 計算正確率     correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))     accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))     # 載入滑動平均模型下的參數值     variable_averages = tf.train.ExponentialMovingAverage(                    mnist_train.MOVING_AVERAGE_DECAY)     saver = tf.train.Saver(variable_averages.variables_to_restore())      # 每隔EVAL_INTERVAL_SECS秒啟動一次會話     while True:       with tf.Session() as sess:         ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)         if ckpt and ckpt.model_checkpoint_path:           saver.restore(sess, ckpt.model_checkpoint_path)           # 取checkpoint檔案中的當前迭代輪數global_step           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(EVAL_INTERVAL_SECS)  def main(argv=None):   mnist = input_data.read_data_sets("MNIST_data", one_hot=True)   evaluate(mnist)  if __name__ == '__main__':   tf.app.run() 

以上就是本文的全部內容，希望對大家的學習有所協助，也希望大家多多支援幫客之家。