add dnn

DNN/keras_dnn.py

@@ -0,0 +1,31 @@
+#由于不能链接到官方的已经处理好的数据，所以这里通过tensorflow导入mnist数据
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+#from _future_ import print_function
+import numpy as np
+#from keras.dataseets import mnist
+from keras.models import Sequential
+from keras.layers import Dense
+from keras.utils import np_utils
+
+batch_size = 128 #梯度下降一个批（batch）的数据量
+nb_classes =10 #类别
+nb_epoch =10 #梯度下降epoch循环训练次数，每次循环包含全部的样本
+image_size = 28*28 #输入图片的大小，由于是灰度图片，因此只有一个颜色通道
+
+#加载数据
+mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
+x_train,y_train= mnist.train.images, mnist.train.labels
+#print(x_train.shape,y_train.shape) #(55000, 784) (55000, 10)
+x_test,y_test= mnist.test.images, mnist.test.labels
+#print(x_test.shape,y_test.shape) #(10000, 784) (10000, 10)
+#如果y_train\y_test不是one_hot编码，需要进行转换
+
+#创建模型，逻辑分类相当于一层全链接的神经网络（Dense是Keras中定义的DNN模型）
+model = Sequential([Dense(128,input_shape=(image_size,),activation= 'relu'),Dense(10,input_shape=(128,),activation= 'softmax')])
+#配置优化器，损失函数
+model.compile(optimizer = 'rmsprop',loss = 'categorical_crossentropy',metrics= ['accuracy'])
+model.fit(x_train,y_train,batch_size = batch_size,nb_epoch = nb_epoch,verbose = 1,validation_data = (x_test,y_test))
+#score分数包含两部分，一部分是val_loss,一部分是val_acc。取score[1]来进行模型的得分评价
+score = model.evaluate(x_test,y_test,verbose = 0)
+print('Accuracy:{}'.format(score[1]))

DNN/tensorflow_DNN.py

@@ -0,0 +1,75 @@
+#coding:utf-8
+
+#下载mnist数据集
+from tensorflow.examples.tutorials.mnist import input_data
+mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
+
+import tensorflow as tf
+
+#定义一些参数
+learning_rate = 0.001
+train_epochs = 20
+batch_size = 64
+
+#定义3层感知机的神经单元个数
+n_input = 784
+n_hidden1 = 100
+n_hidden2 = 100
+n_classes = 10
+
+#定义网络输入参数占位符
+x = tf.placeholder(tf.float32, shape=[None, n_input])
+y = tf.placeholder(tf.float32, shape=[None, n_classes])
+
+#定义权重与偏置
+weights = {'h1': tf.Variable(tf.random_normal([n_input, n_hidden1])),
+                  'h2': tf.Variable(tf.random_normal([n_hidden1, n_hidden2])),
+                  'out': tf.Variable(tf.random_normal([n_hidden2, n_classes]))}
+
+biases = {'b1': tf.Variable(tf.random_normal([n_hidden1])),
+                'b2': tf.Variable(tf.random_normal([n_hidden2])),
+                'out': tf.Variable(tf.random_normal([n_classes]))}
+
+
+#定义推断过程
+def inference(input_x):
+    layer_1 = tf.nn.relu(tf.matmul(x, weights['h1']) + biases['b1'])
+    layer_2 = tf.nn.relu(tf.matmul(layer_1, weights['h2']) + biases['b2'])
+    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
+    return out_layer
+
+#构建网络
+logits = inference(x)
+prediction = tf.nn.softmax(logits)
+
+#定义损失函数与优化器
+loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))
+optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
+train_op = optimizer.minimize(loss)
+
+#定义评价指标(准确度)
+pre_correct = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1))
+accuracy = tf.reduce_mean(tf.cast(pre_correct, tf.float32))
+
+#初始化所有变量
+init = tf.global_variables_initializer()
+
+#开始训练
+with tf.Session() as sess:
+    sess.run(init)
+    total_batch = int(mnist.train.num_examples / batch_size)
+
+    for epoch in range(train_epochs):
+        for batch in range(total_batch):
+            batch_x, batch_y = mnist.train.next_batch(batch_size)
+            sess.run(train_op, feed_dict={x:batch_x, y:batch_y})
+
+        if epoch % 10 == 0:
+            loss_, acc = sess.run([loss, accuracy], feed_dict={x:batch_x, y:batch_y})
+            print("epoch {},  loss {:.4f}, acc {:.3f}".format(epoch, loss_, acc))
+
+    print("optimizer finished!")
+
+    #计算测试集的准确度 
+    test_acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels})
+    print('test accuracy', test_acc)