MNIST数据集下载：
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #one_hot 独热编码，也叫一位有效编码。在任意时候只有一位为1，其他位都是0
1 使用逻辑回归：
import tensorflow as tf # 导入数据集 #from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # 变量 batch_size = 50 #训练的x(image),y(label) # x = tf.Variable() # y = tf.Variable() x = tf.placeholder(tf.float32, [None, 784]) y = tf.placeholder(tf.float32, [None, 10]) # 模型权重 #[55000,784] * W = [55000,10] W = tf.Variable(tf.zeros([784, 10])) b = tf.Variable(tf.zeros([10])) # 用softmax构建逻辑回归模型 pred = tf.nn.softmax(tf.matmul(x, W) + b) # 损失函数(交叉熵) cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), 1)) # 低度下降 optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(cost) # 初始化所有变量 init = tf.global_variables_initializer() # 加载session图 with tf.Session() as sess: sess.run(init) # 开始训练 for epoch in range(25): avg_cost = 0. total_batch = int(mnist.train.num_examples/batch_size) for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) sess.run(optimizer, {x: batch_xs,y: batch_ys}) #计算损失平均值 avg_cost += sess.run(cost,{x: batch_xs,y: batch_ys}) / total_batch if (epoch+1) % 5 == 0: print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost)) print("运行完成") # 测试求正确率 correct = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct, tf.float32)) print("正确率:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
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 Epoch: 0005 cost= 0.394426425 Epoch: 0010 cost= 0.344705163 Epoch: 0015 cost= 0.323814137 Epoch: 0020 cost= 0.311426675 Epoch: 0025 cost= 0.302971779 运行完成 正确率: 0.9188
2 使用神经网络：
import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data def init_weights(shape): return tf.Variable(tf.random_normal(shape, stddev=0.01)) def model(X, w_h, w_o): h = tf.nn.sigmoid(tf.matmul(X, w_h)) # this is a basic mlp, think 2 stacked logistic regressions return tf.matmul(h, w_o) # note that we dont take the softmax at the end because our cost fn does that for us mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels X = tf.placeholder("float", [None, 784]) Y = tf.placeholder("float", [None, 10]) w_h = init_weights([784, 625]) # create symbolic variables w_o = init_weights([625, 10]) py_x = model(X, w_h, w_o) cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # compute costs train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct an optimizer predict_op = tf.argmax(py_x, 1) # Launch the graph in a session with tf.Session() as sess: # you need to initialize all variables tf.global_variables_initializer().run() for i in range(100): for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)): sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]}) print(i, np.mean(np.argmax(teY, axis=1) == sess.run(predict_op, feed_dict={X: teX})))
结果：
0 0.6898 1 0.8244 2 0.8635 3 0.881 4 0.8881 5 0.8931 6 0.8972 7 0.9005 8 0.9042 9 0.9062
3 使用卷积神经网络：
import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data batch_size = 128 test_size = 256 def init_weights(shape): return tf.Variable(tf.random_normal(shape, stddev=0.01)) def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden): l1a = tf.nn.relu(tf.nn.conv2d(X, w, # l1a shape=(?, 28, 28, 32) strides=[1, 1, 1, 1], padding='SAME')) l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1], # l1 shape=(?, 14, 14, 32) strides=[1, 2, 2, 1], padding='SAME') l1 = tf.nn.dropout(l1, p_keep_conv) l2a = tf.nn.relu(tf.nn.conv2d(l1, w2, # l2a shape=(?, 14, 14, 64) strides=[1, 1, 1, 1], padding='SAME')) l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1], # l2 shape=(?, 7, 7, 64) strides=[1, 2, 2, 1], padding='SAME') l2 = tf.nn.dropout(l2, p_keep_conv) l3a = tf.nn.relu(tf.nn.conv2d(l2, w3, # l3a shape=(?, 7, 7, 128) strides=[1, 1, 1, 1], padding='SAME')) l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1], # l3 shape=(?, 4, 4, 128) strides=[1, 2, 2, 1], padding='SAME') l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]]) # reshape to (?, 2048) l3 = tf.nn.dropout(l3, p_keep_conv) l4 = tf.nn.relu(tf.matmul(l3, w4)) l4 = tf.nn.dropout(l4, p_keep_hidden) pyx = tf.matmul(l4, w_o) return pyx mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels trX = trX.reshape(-1, 28, 28, 1) # 28x28x1 input img teX = teX.reshape(-1, 28, 28, 1) # 28x28x1 input img X = tf.placeholder("float", [None, 28, 28, 1]) Y = tf.placeholder("float", [None, 10]) w = init_weights([3, 3, 1, 32]) # 3x3x1 conv, 32 outputs w2 = init_weights([3, 3, 32, 64]) # 3x3x32 conv, 64 outputs w3 = init_weights([3, 3, 64, 128]) # 3x3x32 conv, 128 outputs w4 = init_weights([128 * 4 * 4, 625]) # FC 128 * 4 * 4 inputs, 625 outputs w_o = init_weights([625, 10]) # FC 625 inputs, 10 outputs (labels) p_keep_conv = tf.placeholder("float") p_keep_hidden = tf.placeholder("float") py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden) cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost) predict_op = tf.argmax(py_x, 1) # Launch the graph in a session with tf.Session() as sess: # you need to initialize all variables tf.global_variables_initializer().run() for i in range(10): training_batch = zip(range(0, len(trX), batch_size), range(batch_size, len(trX)+1, batch_size)) for start, end in training_batch: sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end], p_keep_conv: 0.8, p_keep_hidden: 0.5}) test_indices = np.arange(len(teX)) # Get A Test Batch np.random.shuffle(test_indices) test_indices = test_indices[0:test_size] print(i, np.mean(np.argmax(teY[test_indices], axis=1) == sess.run(predict_op, feed_dict={X: teX[test_indices], Y: teY[test_indices], p_keep_conv: 1.0, p_keep_hidden: 1.0})))
结果：
0 0.9453125 1 0.9765625 2 0.9921875 3 0.98828125 4 0.984375 5 0.9921875 6 0.984375 7 0.9921875 8 0.98828125 9 0.99609375