函数如下所示
""" Starter code for logistic regression model to solve OCR task with MNIST in TensorFlow MNIST dataset: yann.lecun.com/exdb/mnist/ """ import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import time # Define parameters for the model learning_rate = 0.01 batch_size = 128 n_epochs = 20 # Step 1: Read in data # using TF Learn's built in function to load MNIST data to the folder data/mnist mnist = input_data.read_data_sets('MNIST_data/', one_hot=True) in_units = 784 h1_units = 512 h2_units = 380 out_units = 10 # Step 2: create placeholders for features and labels # each image in the MNIST data is of shape 28*28 = 784 # therefore, each image is represented with a 1x784 tensor # there are 10 classes for each image, corresponding to digits 0 - 09. X = tf.placeholder(tf.float32, [None, in_units], name='X_placeholder') Y = tf.placeholder(tf.float32, [None, out_units], name='Y_placeholder') keep_prob = tf.placeholder(tf.float32, name='keep_prob') # Step 3: create MLP W_h1 = tf.Variable(tf.random_normal([in_units, h1_units]), name='weights_hide_layer_1') h1 = tf.nn.relu(tf.matmul(X, W_h1)) h1_dropout = tf.nn.dropout(h1, keep_prob) W_h2 = tf.Variable(tf.random_normal([h1_units, h2_units]), name='weights_hide_layer_2') h2 = tf.nn.relu(tf.matmul(h1_dropout, W_h2)) W_out = tf.Variable(tf.random_normal([h2_units, out_units]), name='weights_out_layer') y = tf.matmul(h2, W_out) # Step 4: define loss function # use cross entropy loss of the real labels with the softmax of logits # use the method: # tf.nn.softmax_cross_entropy_with_logits(logits, Y) # then use tf.reduce_mean to get the mean loss of the batch loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y, labels=Y, name='loss')) # Step 5: define training op # using gradient descent to minimize loss optimizer = tf.train.AdamOptimizer(learning_rate).minimize(loss) with tf.Session() as sess: # to visualize using TensorBoard writer = tf.summary.FileWriter('./graphs', sess.graph) start_time = time.time() sess.run(tf.global_variables_initializer()) n_batches = int(mnist.train.num_examples / batch_size) for i in range(n_epochs): # train the model n_epochs times total_loss = 0 for _ in range(n_batches): X_batch, Y_batch = mnist.train.next_batch(batch_size) # TO-DO: run optimizer + fetch loss_batch _, loss_batch = sess.run([optimizer, loss], feed_dict={X: X_batch, Y: Y_batch, keep_prob: 0.75}) total_loss += loss_batch print('Average loss epoch {0}: {1}'.format(i, total_loss / n_batches)) print('Total time: {0} seconds'.format(time.time() - start_time)) print('Optimization Finished!') # should be around 0.35 after 25 epochs # test the model n_batches = int(mnist.test.num_examples / batch_size) total_correct_preds = 0 for i in range(n_batches): X_batch, Y_batch = mnist.test.next_batch(batch_size) _, loss_batch, logits_batch = sess.run([optimizer, loss, y], feed_dict={X: X_batch, Y: Y_batch, keep_prob: 1.0}) preds = tf.nn.softmax(logits_batch) correct_preds = tf.equal(tf.argmax(preds, 1), tf.argmax(Y_batch, 1)) accuracy = tf.reduce_sum(tf.cast(correct_preds, tf.float32)) # need numpy.count_nonzero(boolarr) :( total_correct_preds += sess.run(accuracy) print('Accuracy {0}%'.format(100 * total_correct_preds / mnist.test.num_examples)) writer.close()2.TF中的优化方法 tf.train.GradientDescentOptimizer tf.train.AdadeltaOptimizer tf.train.AdagradOptimizer tf.train.AdagradDAOptimizer tf.train.MomentumOptimizer tf.train.AdamOptimizer tf.train.FtrlOptimizer tf.train.ProximalGradientDescentOptimizer tf.train.ProximalAdagradOptimizer tf.train.RMSPropOptimizer
