Permalink
Fetching contributors…
Cannot retrieve contributors at this time
94 lines (81 sloc) 3.79 KB
import time
import tensorflow as tf
import tensorlayer as tl
tf.logging.set_verbosity(tf.logging.DEBUG)
tl.logging.set_verbosity(tl.logging.DEBUG)
sess = tf.InteractiveSession()
# prepare data
X_train, y_train, X_val, y_val, X_test, y_test = tl.files.load_mnist_dataset(shape=(-1, 784))
# define placeholder
x = tf.placeholder(tf.float32, shape=[None, 784], name='x')
y_ = tf.placeholder(tf.int64, shape=[None], name='y_')
# define the network
network = tl.layers.InputLayer(x, name='input')
network = tl.layers.DropoutLayer(network, keep=0.8, name='drop1')
network = tl.layers.DenseLayer(network, n_units=800, act=tf.nn.relu, name='relu1')
network = tl.layers.DropoutLayer(network, keep=0.5, name='drop2')
network = tl.layers.DenseLayer(network, n_units=800, act=tf.nn.relu, name='relu2')
network = tl.layers.DropoutLayer(network, keep=0.5, name='drop3')
# the softmax is implemented internally in tl.cost.cross_entropy(y, y_) to
# speed up computation, so we use identity here.
# see tf.nn.sparse_softmax_cross_entropy_with_logits()
network = tl.layers.DenseLayer(network, n_units=10, act=None, name='output')
# define cost function and metric.
y = network.outputs
cost = tl.cost.cross_entropy(y, y_, name='xentropy')
correct_prediction = tf.equal(tf.argmax(y, 1), y_)
acc = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
y_op = tf.argmax(tf.nn.softmax(y), 1)
# define the optimizer
train_params = network.all_params
train_op = tf.train.AdamOptimizer(learning_rate=0.0001).minimize(cost, var_list=train_params)
# initialize all variables in the session
tl.layers.initialize_global_variables(sess)
# print network information
network.print_params()
network.print_layers()
n_epoch = 500
batch_size = 500
print_freq = 5
for epoch in range(n_epoch):
start_time = time.time()
for X_train_a, y_train_a in tl.iterate.minibatches(X_train, y_train, batch_size, shuffle=True):
feed_dict = {x: X_train_a, y_: y_train_a}
feed_dict.update(network.all_drop) # enable noise layers
sess.run(train_op, feed_dict=feed_dict)
if epoch + 1 == 1 or (epoch + 1) % print_freq == 0:
print("Epoch %d of %d took %fs" % (epoch + 1, n_epoch, time.time() - start_time))
train_loss, train_acc, n_batch = 0, 0, 0
for X_train_a, y_train_a in tl.iterate.minibatches(X_train, y_train, batch_size, shuffle=True):
dp_dict = tl.utils.dict_to_one(network.all_drop) # disable noise layers
feed_dict = {x: X_train_a, y_: y_train_a}
feed_dict.update(dp_dict)
err, ac = sess.run([cost, acc], feed_dict=feed_dict)
train_loss += err
train_acc += ac
n_batch += 1
print(" train loss: %f" % (train_loss / n_batch))
print(" train acc: %f" % (train_acc / n_batch))
val_loss, val_acc, n_batch = 0, 0, 0
for X_val_a, y_val_a in tl.iterate.minibatches(X_val, y_val, batch_size, shuffle=True):
dp_dict = tl.utils.dict_to_one(network.all_drop) # disable noise layers
feed_dict = {x: X_val_a, y_: y_val_a}
feed_dict.update(dp_dict)
err, ac = sess.run([cost, acc], feed_dict=feed_dict)
val_loss += err
val_acc += ac
n_batch += 1
print(" val loss: %f" % (val_loss / n_batch))
print(" val acc: %f" % (val_acc / n_batch))
print('Evaluation')
test_loss, test_acc, n_batch = 0, 0, 0
for X_test_a, y_test_a in tl.iterate.minibatches(X_test, y_test, batch_size, shuffle=True):
dp_dict = tl.utils.dict_to_one(network.all_drop) # disable noise layers
feed_dict = {x: X_test_a, y_: y_test_a}
feed_dict.update(dp_dict)
err, ac = sess.run([cost, acc], feed_dict=feed_dict)
test_loss += err
test_acc += ac
n_batch += 1
print(" test loss: %f" % (test_loss / n_batch))
print(" test acc: %f" % (test_acc / n_batch))