多层感知机（multi-layer perceptron）实现手写体分类（TensorFlow）

#multi_layer  Perceptron by ffzhangimport numpy as npimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport timeimport osos.environ["CUDA_VISIBLE_DEVICES"]='2'mnist = input_data.read_data_sets('data/mnist',one_hot=True)mnist.train.images.shapemnist.train.labels.shape#define placeholder to save the training dataX = tf.placeholder(tf.float32,[None,784],name='X_placeholder')Y = tf.placeholder(tf.float32,[None,10],name='Y_placeholder')#define parametersn_hidden_1 =256n_hidden_2 =256n_input =784n_classes =10weights ={    'h1': tf.Variable(tf.random_normal([n_input,n_hidden_1]),name='W1'),    'h2': tf.Variable(tf.random_normal([n_hidden_1,n_hidden_2]),name='W2'),    'out': tf.Variable(tf.random_normal([n_hidden_2,n_classes]),name='W')}biases ={    'b1': tf.Variable(tf.random_normal([n_hidden_1]),name='b1'),    'b2': tf.Variable(tf.random_normal([n_hidden_2]),name='b2'),    'out': tf.Variable(tf.random_normal([n_classes]),name='bias')}#define graph for this networkdef multilayer_perceptron(x,weights,biases):     layer_1 = tf.add(tf.matmul(x,weights['h1']),biases['b1'],name='fc_1')     layer_1 = tf.nn.relu(layer_1,name='relu_1')     layer_2 = tf.add(tf.matmul(layer_1,weights['h2']),biases['b2'],name='fc_2')     layer_2 = tf.nn.relu(layer_2,name='relu_2')     out_layer = tf.add(tf.matmul(layer_2,weights['out']),biases['out'],name='fc_3')     return out_layerpred = multilayer_perceptron(X, weights, biases)learning_rate = 0.001loss_all = tf.nn.softmax_cross_entropy_with_logits(labels=Y,logits=pred,name='cross_entropy')loss = tf.reduce_mean(loss_all,name='avg_loss')optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)init =tf.global_variables_initializer()training_epochs=15batch_size=128display_step =1with tf.Session() as sess:    sess.run(init)    writer =tf.summary.FileWriter('./graphs/MLP_dnn',sess.graph)    for epoch in range(training_epochs):        avg_loss =0        total_batch = int(mnist.train.num_examples/batch_size)        for i in range(total_batch):            batch_x, batch_y =mnist.train.next_batch(batch_size)            _, l =sess.run([optimizer,loss],feed_dict={X: batch_x, Y: batch_y})            avg_loss += l/total_batch        if epoch%display_step==0:            print ('Epoch:', '%04d'% (epoch+1),'cost=', "{:.9f}".format(avg_loss))    print ('optimizer finished')    correct_prediction = tf.equal(tf.argmax(pred,1),tf.argmax(Y,1))    accuracy = tf.reduce_mean(tf.cast(correct_prediction,'float'))    print ('accuracy:',accuracy.eval({X:mnist.test.images, Y:mnist.test.labels}))    writer.close()