代码:
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data #载入数据集 #当前路径 mnist = input_data.read_data_sets("MNISt_data", one_hot=True)
运行结果:
Extracting MNISt_data/train-images-idx3-ubyte.gz Extracting MNISt_data/train-labels-idx1-ubyte.gz Extracting MNISt_data/t10k-images-idx3-ubyte.gz Extracting MNISt_data/t10k-labels-idx1-ubyte.gz
代码:
#每个批次的大小 #以矩阵的形式放进去 batch_size = 100 #计算一共有多少个批次 n_batch = mnist.train.num_examples // batch_size #定义三个placeholder #28 x 28 = 784 x = tf.placeholder(tf.float32, [None, 784]) y = tf.placeholder(tf.float32, [None, 10]) keep_prob = tf.placeholder(tf.float32) #创建一个的神经网络 #输入层784,隐藏层一1000,隐藏层二1000,隐藏层三1000,输出层10个神经元 #隐藏层 W1 = tf.Variable(tf.truncated_normal([784, 1000], stddev=0.1)) b1 = tf.Variable(tf.zeros([1000]) + 0.1) L1 = tf.nn.tanh(tf.matmul(x, W1) + b1) L1_drop = tf.nn.dropout(L1,keep_prob) W2 = tf.Variable(tf.truncated_normal([1000, 1000], stddev=0.1)) b2 = tf.Variable(tf.zeros([1000]) + 0.1) L2 = tf.nn.tanh(tf.matmul(L1_drop, W2) + b2) L2_drop = tf.nn.dropout(L2,keep_prob) W3 = tf.Variable(tf.truncated_normal([1000, 1000], stddev=0.1)) b3 = tf.Variable(tf.zeros([1000]) + 0.1) L3 = tf.nn.tanh(tf.matmul(L2_drop, W3) + b3) L3_drop = tf.nn.dropout(L3,keep_prob) W4 = tf.Variable(tf.truncated_normal([1000, 10], stddev=0.1)) b4 = tf.Variable(tf.zeros([10]) + 0.1) prediction = tf.nn.softmax(tf.matmul(L3_drop, W4) + b4) #交叉熵 loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction)) #使用梯度下降法 train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss) #初始化变量 init = tf.global_variables_initializer() #结果存放在一个布尔型列表中 #tf.argmax(y, 1)与tf.argmax(prediction, 1)相同返回True,不同则返回False #argmax返回一维张量中最大的值所在的位置 correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1)) #求准确率 #tf.cast(correct_prediction, tf.float32) 将布尔型转换为浮点型 accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) with tf.Session() as sess: sess.run(init) #总共10个周期 for epoch in range(10): #总共n_batch个批次 for batch in range(n_batch): #获得一个批次 batch_xs, batch_ys = mnist.train.next_batch(batch_size) sess.run(train_step, feed_dict={x:batch_xs, y:batch_ys, keep_prob:0.7}) #训练完一个周期后测试数据准确率 test_acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0}) #训练完一个周期后训练数据准确率 train_acc = sess.run(accuracy, feed_dict={x:mnist.train.images, y:mnist.train.labels, keep_prob:1.0}) print("Iter" + str(epoch) + ", Testing Accuracy" + str(test_acc)+ ", Testing Accuracy" + str(train_acc))
运行结果:
#没有使用Droupout Iter0, Testing Accuracy0.9408, Testing Accuracy0.946473 Iter1, Testing Accuracy0.9566, Testing Accuracy0.968982 Iter2, Testing Accuracy0.963, Testing Accuracy0.976364 Iter3, Testing Accuracy0.9651, Testing Accuracy0.982218 Iter4, Testing Accuracy0.9706, Testing Accuracy0.985836 Iter5, Testing Accuracy0.9707, Testing Accuracy0.987618 Iter6, Testing Accuracy0.9719, Testing Accuracy0.989018 Iter7, Testing Accuracy0.9742, Testing Accuracy0.990255 Iter8, Testing Accuracy0.9737, Testing Accuracy0.991036 Iter9, Testing Accuracy0.9738, Testing Accuracy0.9916
运行结果:
#使用Droupout #过拟合情况很小 Iter0, Testing Accuracy0.9175, Testing Accuracy0.9134 Iter1, Testing Accuracy0.9291, Testing Accuracy0.926327 Iter2, Testing Accuracy0.9362, Testing Accuracy0.935982 Iter3, Testing Accuracy0.9399, Testing Accuracy0.940564 Iter4, Testing Accuracy0.9433, Testing Accuracy0.9454 Iter5, Testing Accuracy0.9465, Testing Accuracy0.949091 Iter6, Testing Accuracy0.9479, Testing Accuracy0.952145 Iter7, Testing Accuracy0.9504, Testing Accuracy0.956018 Iter8, Testing Accuracy0.9523, Testing Accuracy0.956855 Iter9, Testing Accuracy0.9542, Testing Accuracy0.9586