def test_mnist(self):
config = agents.tools.AttrDict(default_config())
model = benchmark_model.build_tf_one_hot_model(config.batch_size)
from keras.utils.np_utils import to_categorical
from keras.datasets.mnist import load_data
(x_train, y_train), (x_test, y_test) = load_data('/tmp/mnist')
x_train = x_train.reshape((-1, 784)).astype(np.float64) / 255.
y_train = to_categorical(y_train, 10).astype(np.float64)
assert x_train.shape == (60000, 784)
assert y_train.shape == (60000, 10)
optimizer = optimizers.NMFOptimizer()
train_op = optimizer.minimize(model.frob_norm)
losses = []
init = tf.global_variables_initializer()
with self.test_session() as sess:
sess.run(init)
pprint(optimizer._layers)
for i in range(2):
x, y = benchmark_model.batch(x_train, y_train, config.batch_size)
_, new_loss, acc = sess.run([train_op, model.cross_entropy, model.accuracy], feed_dict={
model.inputs: x,
model.labels: y,
})
losses.append(new_loss)
print('\nloss {}, accuracy {}'.format(new_loss, acc), end='', flush=True)
def test_autoencoder(self):
print()
config = agents.tools.AttrDict(default_config())
model = benchmark_model.build_tf_one_hot_model(batch_size=config.batch_size)
optimizer = optimizers.NMFOptimizer(config)
train_op = optimizer.minimize(model.frob_norm)
self.assertEqual(model.inputs.shape, optimizer.decoder.shape)
def test_get_placeholder_ops(self):
print()
model = benchmark_model.build_tf_one_hot_model(False)
import time
start_time = time.time()
inputs, labels = utility.get_placeholder_ops(model.frob_norm)
duration = time.time() - start_time
print('duration', duration)
self.assertEqual(model.inputs, inputs)
self.assertEqual(model.labels, labels)
def test_factorize(self):
config = agents.tools.AttrDict(default_config())
model = benchmark_model.build_tf_one_hot_model(config.batch_size)
optimizer = optimizers.NMFOptimizer(config)
train_op = optimizer.minimize(model.frob_norm)
init = tf.global_variables_initializer()
with self.test_session() as sess:
sess.run(init)
pprint(optimizer._layers)
def main(_):
# Set configuration
config = AttrDict(default_config())
# Build one hot mnist model.
model = benchmark_model.build_tf_one_hot_model(batch_size=config.batch_size,
use_bias=config.use_bias,
activation=config.activation)
# Load one hot mnist data.
(x_train, y_train), (x_test, y_test) = benchmark_model.load_one_hot_data(dataset=config.dataset)
# Testing whether the dataset have correct shape.
assert x_train.shape == (60000, 784)
assert y_train.shape == (60000, 10)
# Minimize model's loss with NMF optimizer.
# optimizer = NMFOptimizer(config)
optimizer = NMFOptimizer(config=config)
train_op = optimizer.minimize(model.frob_norm)
# Minimize model's loss with Adam optimizer.
bp_optimizer = tf.train.AdamOptimizer(config.learning_rate)
bp_train_op = bp_optimizer.minimize(model.cross_entropy)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for i in range(1000):
x, y = benchmark_model.batch(x_train, y_train, batch_size=config.batch_size)
loss, _ = sess.run([optimizer.autoencoder_loss, optimizer.autoencoder_train_op],
feed_dict={model.inputs: x})
print('\rloss {}'.format(loss), end='', flush=True)
print()
_train_and_test = functools.partial(train_and_test,
sess=sess, model=model,
x_train=x_train, y_train=y_train,
x_test=x_test, y_test=y_test,
batch_size=config.batch_size)
print('NMF-optimizer')
# Train with NMF optimizer.
_train_and_test(train_op, num_iters=config.num_mf_iters)
print('Adam-optimizer')
# Train with Adam optimizer.
_train_and_test(bp_train_op, num_iters=config.num_bp_iters)
def main(_):
# Set configuration
config = agents.tools.AttrDict(default_config())
# Build one hot mnist model.
model = benchmark_model.build_tf_one_hot_model(
3072, use_bias=config.use_bias, activation=config.activation)
# Load one hot mnist data.
(x_train,
y_train), (x_test,
y_test) = benchmark_model.load_one_hot_data(dataset='cifar10')
# Testing whether the dataset have correct shape.
assert x_train.shape == (50000, 3072)
assert y_train.shape == (50000, 10)
# Minimize model's loss with NMF optimizer.
# optimizer = NMFOptimizer(config)
optimizer = NMFOptimizer()
train_op = optimizer.minimize(model.frob_norm)
# Minimize model's loss with Adam optimizer.
bp_optimizer = tf.train.AdamOptimizer(config.learning_rate)
bp_train_op = bp_optimizer.minimize(model.cross_entropy)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
_train_and_test = functools.partial(train_and_test,
sess=sess,
model=model,
x_train=x_train,
y_train=y_train,
x_test=x_test,
y_test=y_test,
batch_size=config.batch_size)
print('NMF-optimizer')
# Train with NMF optimizer.
_train_and_test(train_op, num_iters=config.num_mf_iters)
print('Adam-optimizer')
# Train with Adam optimizer.
_train_and_test(bp_train_op, num_iters=config.num_bp_iters)