def autoencoder():
# building dataset, batch_size and preprocessor
data = Mnist(train_valid_test_ratio=[8, 1, 1], batch_size=100, preprocessor=GCN())
# for AutoEncoder, the inputs and outputs must be the same
train = data.get_train()
data.set_train(train.X, train.X)
valid = data.get_valid()
data.set_valid(valid.X, valid.X)
test = data.get_test()
data.set_test(test.X, test.X)
# building autoencoder
ae = AutoEncoder(input_dim=data.feature_size(), rand_seed=123)
h1_layer = Tanh(dim=500, name="h1_layer", W=None, b=None)
# adding encoding layer
ae.add_encode_layer(h1_layer)
# mirror layer has W = h1_layer.W.T
h1_mirror = Tanh(dim=ae.input_dim, name="h1_mirror", W=h1_layer.W.T, b=None)
# adding decoding mirror layer
ae.add_decode_layer(h1_mirror)
# build learning method
learning_method = AdaGrad(learning_rate=0.1, momentum=0.9)
# set the learning rules
learning_rule = LearningRule(
max_col_norm=10,
L1_lambda=None,
L2_lambda=None,
training_cost=Cost(type="mse"),
learning_rate_decay_factor=None,
stopping_criteria={
"max_epoch": 300,
"epoch_look_back": 10,
"cost": Cost(type="error"),
"percent_decrease": 0.01,
},
)
# put all the components into a TrainObject
train_object = TrainObject(model=ae, dataset=data, learning_rule=learning_rule, learning_method=learning_method)
# finally run the training
train_object.run()
def build_dataset(self):
dataset = None
preprocessor = None if self.state.dataset.preprocessor.type is None else \
getattr(preproc, self.state.dataset.preprocessor.type)()
noise = None if self.state.dataset.dataset_noise.type is None else \
getattr(data_noise, self.state.dataset.dataset_noise.type)()
if self.state.dataset.dataset_noise.type == 'Gaussian':
noise.std = self.state.dataset.dataset_noise.std
if self.state.dataset.preprocessor.type == 'Scale':
preprocessor.max = self.state.dataset.preprocessor.global_max
preprocessor.min = self.state.dataset.preprocessor.global_min
preprocessor.buffer = self.state.dataset.preprocessor.buffer
preprocessor.scale_range = self.state.dataset.preprocessor.scale_range
if self.state.dataset.type == 'Mnist':
dataset = Mnist(train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.y, train.y)
valid = dataset.get_valid()
dataset.set_valid(valid.y, valid.y)
test = dataset.get_test()
dataset.set_test(test.y, test.y)
elif self.state.dataset.type[:12] == 'Mnist_Blocks':
dataset = getattr(mnist, self.state.dataset.type)(
feature_size=self.state.dataset.feature_size,
target_size=self.state.dataset.feature_size,
train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
elif self.state.dataset.type[:4] == 'P276':
dataset = getattr(spec, self.state.dataset.type)(
train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
elif self.state.dataset.type[:5] == 'Laura':
dataset = getattr(spec, self.state.dataset.type)(
feature_size=self.state.dataset.feature_size,
target_size=self.state.dataset.feature_size,
train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
num_blocks=self.state.dataset.num_blocks,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
elif self.state.dataset.type[:18] == 'TransFactor_Blocks':
dataset = getattr(tf, self.state.dataset.type)(
feature_size=self.state.dataset.feature_size,
target_size=self.state.dataset.feature_size,
one_hot=self.state.dataset.one_hot,
num_blocks=self.state.dataset.num_blocks,
train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
elif self.state.dataset.type[:11] == 'TransFactor':
dataset = getattr(tf, self.state.dataset.type)(
# feature_size = self.state.dataset.feature_size,
# target_size = self.state.dataset.feature_size,
train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
elif self.state.dataset.type[:13] == 'I2R_Posterior':
dataset = getattr(i2r, self.state.dataset.type)(
train_valid_test_ratio=self.state.dataset.
train_valid_test_ratio,
preprocessor=preprocessor,
noise=noise,
batch_size=self.state.dataset.batch_size,
num_batches=self.state.dataset.num_batches,
iter_class=self.state.dataset.iter_class,
rng=self.state.dataset.rng)
return dataset
def build_dataset(self):
dataset = None
preprocessor = None if self.state.dataset.preprocessor.type is None else \
getattr(preproc, self.state.dataset.preprocessor.type)()
noise = None if self.state.dataset.dataset_noise.type is None else \
getattr(data_noise, self.state.dataset.dataset_noise.type)()
if self.state.dataset.dataset_noise.type == 'Gaussian':
noise.std = self.state.dataset.dataset_noise.std
if self.state.dataset.preprocessor.type == 'Scale':
preprocessor.max = self.state.dataset.preprocessor.global_max
preprocessor.min = self.state.dataset.preprocessor.global_min
preprocessor.buffer = self.state.dataset.preprocessor.buffer
preprocessor.scale_range = self.state.dataset.preprocessor.scale_range
if self.state.dataset.type == 'Mnist':
dataset = Mnist(train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.y, train.y)
valid = dataset.get_valid()
dataset.set_valid(valid.y, valid.y)
test = dataset.get_test()
dataset.set_test(test.y, test.y)
elif self.state.dataset.type[:12] == 'Mnist_Blocks':
dataset = getattr(mnist, self.state.dataset.type)(
feature_size = self.state.dataset.feature_size,
target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
elif self.state.dataset.type[:4] == 'P276':
dataset = getattr(spec, self.state.dataset.type)(
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
elif self.state.dataset.type[:5] == 'Laura':
dataset = getattr(spec, self.state.dataset.type)(
feature_size = self.state.dataset.feature_size,
target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
num_blocks = self.state.dataset.num_blocks,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
elif self.state.dataset.type[:18] == 'TransFactor_Blocks':
dataset = getattr(tf, self.state.dataset.type)(
feature_size = self.state.dataset.feature_size,
target_size = self.state.dataset.feature_size,
one_hot = self.state.dataset.one_hot,
num_blocks = self.state.dataset.num_blocks,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
elif self.state.dataset.type[:11] == 'TransFactor':
dataset = getattr(tf, self.state.dataset.type)(
# feature_size = self.state.dataset.feature_size,
# target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
elif self.state.dataset.type[:13] == 'I2R_Posterior':
dataset = getattr(i2r, self.state.dataset.type)(
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
return dataset
def build_dataset(self):
dataset = None
preprocessor = None if self.state.dataset.preprocessor.type is None else \
getattr(preproc, self.state.dataset.preprocessor.type)()
# if self.state.dataset.noise.type == 'BlackOut' or self.state.dataset.noise.type == 'MaskOut':
# noise = None if self.state.dataset.noise.type is None else \
# getattr(noisy, self.state.dataset.noise.type)(ratio=self.state.dataset.noise.ratio)
# else:
# noise = getattr(noisy, self.state.dataset.noise.type)()
noise = None if self.state.dataset.dataset_noise.type is None else \
getattr(noisy, self.state.dataset.dataset_noise.type)()
if self.state.dataset.preprocessor.type == 'Scale':
preprocessor.max = self.state.dataset.preprocessor.global_max
preprocessor.min = self.state.dataset.preprocessor.global_min
preprocessor.buffer = self.state.dataset.preprocessor.buffer
preprocessor.scale_range = self.state.dataset.preprocessor.scale_range
if self.state.dataset.type == 'Mnist':
dataset = Mnist(train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
elif self.state.dataset.type[:12] == 'Mnist_Blocks':
dataset = getattr(mnist, self.state.dataset.type)(
feature_size = self.state.dataset.feature_size,
target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
elif self.state.dataset.type[:4] == 'P276':
dataset = getattr(spec, self.state.dataset.type)(
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
elif self.state.dataset.type[:5] == 'Laura':
dataset = getattr(spec, self.state.dataset.type)(
feature_size = self.state.dataset.feature_size,
target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
elif self.state.dataset.type[:18] == 'TransFactor_Blocks':
dataset = getattr(tf, self.state.dataset.type)(
feature_size = self.state.dataset.feature_size,
target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
elif self.state.dataset.type[:11] == 'TransFactor':
dataset = getattr(tf, self.state.dataset.type)(
# feature_size = self.state.dataset.feature_size,
# target_size = self.state.dataset.feature_size,
train_valid_test_ratio = self.state.dataset.train_valid_test_ratio,
preprocessor = preprocessor,
noise = noise,
batch_size = self.state.dataset.batch_size,
num_batches = self.state.dataset.num_batches,
iter_class = self.state.dataset.iter_class,
rng = self.state.dataset.rng)
train = dataset.get_train()
dataset.set_train(train.X, train.X)
valid = dataset.get_valid()
dataset.set_valid(valid.X, valid.X)
test = dataset.get_test()
dataset.set_test(test.X, test.X)
return dataset
def stacked_autoencoder():
name = "Stacked_AE"
# =====[ Train First layer of stack autoencoder ]=====#
print("Start training First Layer of AutoEncoder")
# building dataset, batch_size and preprocessor
data = Mnist(train_valid_test_ratio=[8, 1, 1], batch_size=100)
# for AutoEncoder, the inputs and outputs must be the same
train = data.get_train()
data.set_train(train.X, train.X)
valid = data.get_valid()
data.set_valid(valid.X, valid.X)
test = data.get_test()
data.set_test(test.X, test.X)
# building autoencoder
ae = AutoEncoder(input_dim=data.feature_size(), rand_seed=123)
h1_layer = RELU(dim=500, name="h1_layer", W=None, b=None)
# adding encoding layer
ae.add_encode_layer(h1_layer)
# mirror layer has W = h1_layer.W.T
h1_mirror = RELU(dim=ae.input_dim, name="h1_mirror", W=h1_layer.W.T, b=None)
# adding decoding mirror layer
ae.add_decode_layer(h1_mirror)
# build learning method
learning_method = SGD(learning_rate=0.001, momentum=0.9)
# set the learning rules
learning_rule = LearningRule(
max_col_norm=10,
L1_lambda=None,
L2_lambda=None,
training_cost=Cost(type="mse"),
learning_rate_decay_factor=None,
stopping_criteria={"max_epoch": 3, "epoch_look_back": 1, "cost": Cost(type="error"), "percent_decrease": 0.01},
)
# put all the components into a TrainObject
train_object = TrainObject(model=ae, dataset=data, learning_rule=learning_rule, learning_method=learning_method)
# finally run the training
train_object.run()
# =====[ Train Second Layer of autoencoder ]=====#
print("Start training Second Layer of AutoEncoder")
# fprop == forward propagation
reduced_train_X = ae.encode(train.X)
reduced_valid_X = ae.encode(valid.X)
reduced_test_X = ae.encode(test.X)
data.set_train(X=reduced_train_X, y=reduced_train_X)
data.set_valid(X=reduced_valid_X, y=reduced_valid_X)
data.set_test(X=reduced_test_X, y=reduced_test_X)
# create a new mlp taking inputs from the encoded outputs of first autoencoder
ae2 = AutoEncoder(input_dim=data.feature_size(), rand_seed=None)
h2_layer = RELU(dim=100, name="h2_layer", W=None, b=None)
ae2.add_encode_layer(h2_layer)
h2_mirror = RELU(dim=h1_layer.dim, name="h2_mirror", W=h2_layer.W.T, b=None)
ae2.add_decode_layer(h2_mirror)
train_object = TrainObject(model=ae2, dataset=data, learning_rule=learning_rule, learning_method=learning_method)
train_object.run()
# =====[ Fine Tuning ]=====#
print("Fine Tuning")
data = Mnist()
train = data.get_train()
data.set_train(train.X, train.X)
valid = data.get_valid()
data.set_valid(valid.X, valid.X)
test = data.get_test()
data.set_test(test.X, test.X)
ae3 = AutoEncoder(input_dim=data.feature_size(), rand_seed=None)
ae3.add_encode_layer(h1_layer)
ae3.add_encode_layer(h2_layer)
ae3.add_decode_layer(h2_mirror)
ae3.add_decode_layer(h1_mirror)
train_object = TrainObject(model=ae3, dataset=data, learning_rule=learning_rule, learning_method=learning_method)
train_object.run()
print("Training Done")
