关于深度学习的实践
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('./data/',one_hot=True) # print("train data size:",mnist.train.num_examples) # print("validation data size:",mnist.validation.num_examples) # print("test data size:",mnist.test.num_examples) # # print(mnist.train.labels[0].shape) # print(mnist.train.images[0].shape) # BATCH_SIZE = 128 # xs,ys = mnist.train.next_batch(BATCH_SIZE) # print("xs shape：",xs.shape) # tf.get_collection("") 从集合里取出全部的变量，生成一个列表 # tf.add_n([]) 把列表里面所有的元素相加 # tf.cast(x,dtype) 把x转换为dtype类型 # tf.argmax(x,axis) 返回最大值所在的索引号 # os.path.join("data","mnist") data/mnist BATCH_SIZE = 128 # 设置每一轮的batch大小 LEARNING_RATE = 0.1 # 初始学习率 LEARNING_RATE_DECAY = 0.99 # 学习率的衰减 REGULARIZER = 0.0001 # 正则化参数 STEP = 50000 # 最大训练步数 MODEL_SAVE_PATH = './model/' MODEL_NAME = 'mnist_model' def hidden_layer(input_tensor,weights1,biases1,weight2,biases2,layer_name): layer1 = tf.nn.relu(tf.matmul(input_tensor,weights1)+biases1) return tf.matmul(layer1,weight2)+biases2 x = tf.placeholder(tf.float32,[None,784],name="x-input") y_ = tf.placeholder(tf.float32,[None,10],name="y-input") # 生成隐藏层参数 weights1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1)) biases1 = tf.Variable(tf.constant(0,1,shape=[500])) # 生成输出层参数 weights2 = tf.Variable(tf.truncated_normal([500,10],stddev=0.1)) biases2 = tf.Variable(tf.constant(0,1,shape=[10])) # 计算经过神经网络前向传播后得到的y y = hidden_layer(x,weights1,biases1,weights2,biases2,'y') # 初始化一个滑动平均类，衰减率为0.99 # 为了使模型在训练的前期可以更新的更快，这里使用num_updates参数 averages_class = tf.train.ExponentialMovingAverage(0.99,STEP) # 定义一个更新变量滑动平均值的草祖宗需要向滑动平均类的apply()函数提供一个参数列表 averages_op = averages_class.apply(tf.trainable_variables()) average_y = hidden_layer(x,averages_class.average(weights1), averages_class.average(biases1), averages_class.average(weights2), averages_class.average(biases2), 'average_y') # 随机梯度下降优化器，学习率指数衰减 cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1)) regularizer = tf.contrib.layers.l2_regularizer(REGULARIZER) regularization = regularizer(weights1)+regularizer(weights2) loss = tf.reduce_mean(cross_entropy)+regularization # 用指数衰减法设置学习率，另学习率连续衰减 learning_rate = tf.train.exponential_decay(LEARNING_RATE,STEP,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY) train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss) train_op = tf.group(train_step,averages_op) correct_predicition = tf.equal(tf.argmax(average_y,1),tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_predicition,tf.float32)) with tf.Session() as sess: tf.global_variables_initializer().run() validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels} test_feed = {x: mnist.test.images, y_: mnist.test.labels} for i in range(STEP): if i % 1000 == 0: validate_accuracy = sess.run(accuracy,feed_dict=validate_feed) print("after %d training steps,validation accuracy=%g%%"%(i,validate_accuracy*100)) xs,ys = mnist.train.next_batch(batch_size=BATCH_SIZE) sess.run(train_op,feed_dict={x:xs,y_:ys}) test_accuracy = sess.run(accuracy,feed_dict=test_feed) print("after %d training steps,validation accuracy=%g%%" % (STEP, test_accuracy * 100))
总结的经验：初期就是背代码，理解代码，理解思路，我现在就是初期，感觉在深度学习上需要下很大的功夫，才能入门。
另外公文流转基本完成了，但有很多需要优化的部分。
下周优化公文流转，继续深度学习。
遇到的问题：现在就是深度学习基础的代码框架还有要做什么都明白了，就是语法记不清，而且如果换一个问题就没有自己的思路，感觉还是没有入门。