rnd=rnd)
validation_data = BatchProcessor(
X_dirpath=C['X_valid_dirpath'], y_dirpath=C['y_dirpath'],
batchsize=C['batchsize'], border=C['border'],
limit=C['limit'], random=False,
dtype=theano.config.floatX, rnd=rnd)
pretrain_data = BatchProcessor(
X_dirpath=C['X_pretrain_dirpath'],
y_dirpath=C['y_dirpath'],
batchsize=500000, border=C['border'], limit=None,
random=True, random_mode='fully', rnd=rnd,
dtype=theano.config.floatX)
C['training_size'] = training_data.size()
C['validation_size'] = validation_data.size()
C['pretrain_size'] = pretrain_data.size()
print "Training size: %d" % C['training_size']
print "Validation size: %d" % C['validation_size']
print "Pretrain size: %d" % C['pretrain_size']
mr.add_experiment_metainfo(constants=C)
mr.start()
save_dir = "./models/%s_%d_" % (mr.experiment_name, mr.job_id)
pretrain_save_dir = save_dir + "pretrain_"
n_in = (2*C['border']+1)**2
net = Network([
AutoencoderLayer(n_in=n_in, n_hidden=C['hidden_1'], rnd=rnd,
def train(job_id, params):
print "Job ID: %d" % job_id
border = 2
n_hidden_layer = params['hidden']
metric_recorder = MetricRecorder(config_dir_path='./config.json',
job_id=job_id)
C = {
'X_dirpath' : '../../../data/onetext_train_small/*',
'X_valid_dirpath' : '../../../data/onetext_valid_small/*',
'y_dirpath' : '../../../data/train_cleaned/',
'batchsize' : 2000000,
'limit' : None,
'epochs' : 15,
'patience' : 70000,
'patience_increase' : 2,
'improvement_threshold' : 0.995,
'validation_frequency' : 2,
'lmbda' : 0.0,
'dropout' : 0.0,
'training_size' : None,
'validation_size' : None,
'algorithm' : 'RMSProp',
'eta' : float(params['eta'][0]),
'eta_min': float(params['eta_min'][0]),
'eta_pre' : float(params['eta_pre'][0]),
'corruption_level' : float(params['corruption_level'][0]),
'border' : 2,
'hidden' : int(params['hidden'][0]),
'mini_batch_size': 500
}
training_data = BatchProcessor(
X_dirpath=C['X_dirpath'],
y_dirpath=C['y_dirpath'],
batchsize=C['batchsize'],
border=C['border'],
limit=C['limit'],
random=True,
random_mode='fully',
dtype=theano.config.floatX,
rnd=rnd)
validation_data = BatchProcessor(
X_dirpath=C['X_valid_dirpath'],
y_dirpath=C['y_dirpath'],
batchsize=C['batchsize'],
border=C['border'],
limit=C['limit'],
random=False,
dtype=theano.config.floatX,
rnd=rnd)
pretrain_data = BatchProcessor(
X_dirpath='../../../data/onetext_pretrain_small/*',
y_dirpath='../../../data/train_cleaned/',
batchsize=50000, border=border, limit=None,
random=True, random_mode='fully', rnd=rnd,
dtype=theano.config.floatX)
C['training_size'] = training_data.size()
C['validation_size'] = validation_data.size()
print "Training size: %d" % C['training_size']
print "Validation size: %d" % C['validation_size']
metric_recorder.add_experiment_metainfo(constants=C)
metric_recorder.start()
n_in = (2*border+1)**2
net = Network([
AutoencoderLayer(n_in=n_in, n_hidden=C['hidden'], rnd=rnd,
corruption_level=C['corruption_level']),
FullyConnectedLayer(n_in=C['hidden'], n_out=1, rnd=rnd)],
C['mini_batch_size'])
print '...start pretraining'
net.pretrain_autoencoders(training_data=pretrain_data,
mbs=C['mini_batch_size'], eta=C['eta_pre'], epochs=15, metric_recorder=metric_recorder)
result = net.train(tdata=training_data, epochs=C['epochs'],
mbs=C['mini_batch_size'], eta=C['eta'],
eta_min=C['eta_min'],
vdata=validation_data, lmbda=C['lmbda'],
momentum=None,
patience_increase=C['patience_increase'],
improvement_threshold=C['improvement_threshold'],
validation_frequency=C['validation_frequency'],
metric_recorder=metric_recorder,
save_dir='./models/%d_' % metric_recorder.job_id,
early_stoping=False)
print 'Time = %f' % metric_recorder.stop()
print 'Result = %f' % result
return float(result)
def train(job_id, mbs):
#print "Job ID: %d" % job_id
eta = 0.01 # 1-7 0.01
border = 2
n_hidden_layer = 80
metric_recorder = MetricRecorder(config_dir_path='.', job_id=job_id)
C = {
'X_dirpath' : '../../../data/train_all/*',
'y_dirpath' : '../../../data/train_cleaned/',
'batchsize' : 500000,
'limit' : 20,
'epochs' : 4,
'patience' : 70000,
'patience_increase' : 2,
'improvement_threshold' : 0.995,
'validation_frequency' : 20,
'lmbda' : 0.0,
'training_size' : None,
'validation_size' : None,
'algorithm' : 'RMSProp',
'mini_batch_size': mbs
}
training_data = BatchProcessor(
X_dirpath='../../../data/train_all/*',
y_dirpath='../../../data/train_cleaned/',
batchsize=C['batchsize'],
border=border,
limit=C['limit'],
random=True,
random_mode='fully',
dtype=theano.config.floatX,
rnd=rnd)
validation_data = BatchProcessor(
X_dirpath='../../../data/train/*',
y_dirpath='../../../data/train_cleaned/',
batchsize=C['batchsize'],
random=False,
border=border,
limit=C['limit'],
dtype=theano.config.floatX,
rnd=rnd)
C['training_size'] = training_data.size()
C['validation_size'] = validation_data.size()
print "Training size: %d" % C['training_size']
print "Validation size: %d" % C['validation_size']
metric_recorder.add_experiment_metainfo(constants=C)
metric_recorder.start()
n_in = (2*border+1)**2
net = Network([FullyConnectedLayer(n_in=n_in, n_out=n_hidden_layer,
rnd=rnd),
FullyConnectedLayer(n_in=n_hidden_layer, n_out=1,
rnd=rnd)],
C['mini_batch_size'])
result = net.train(tdata=training_data, epochs=C['epochs'],
mbs=C['mini_batch_size'], eta=eta,
vdata=validation_data, lmbda=C['lmbda'],
momentum=None, patience_increase=C['patience_increase'],
improvement_threshold=C['improvement_threshold'],
validation_frequency=C['validation_frequency'],
metric_recorder=metric_recorder,
save_dir='./model/%d_' % metric_recorder.job_id,
early_stoping=False)
print 'Time = %f' % metric_recorder.stop()
print 'Result = %f' % result
return float(result)
def train(job_id, params):
print "Job ID: %d" % job_id
eta = params["eta"]
border = 2
n_hidden_layer = params["hidden"]
metric_recorder = MetricRecorder(config_dir_path="./config.json", job_id=job_id)
C = {
"X_dirpath": "../../../data/onetext_train_small/*",
"X_valid_dirpath": "../../../data/onetext_valid_small/*",
"y_dirpath": "../../../data/train_cleaned/",
"batchsize": 500000,
"limit": None,
"epochs": 4,
"patience": 70000,
"patience_increase": 2,
"improvement_threshold": 0.995,
"validation_frequency": 20,
"lmbda": float(params["l2"][0]),
"dropout": float(params["dropout"][0]),
"training_size": None,
"validation_size": None,
"algorithm": "RMSProp",
"eta": float(params["eta"][0]),
"eta_min": params["eta_min"][0],
"border": 2,
"hidden": int(params["hidden"][0]),
"mini_batch_size": 500,
}
training_data = BatchProcessor(
X_dirpath=C["X_dirpath"],
y_dirpath=C["y_dirpath"],
batchsize=C["batchsize"],
border=C["border"],
limit=C["limit"],
random=True,
random_mode="fully",
dtype=theano.config.floatX,
rnd=rnd,
)
validation_data = BatchProcessor(
X_dirpath=C["X_valid_dirpath"],
y_dirpath=C["y_dirpath"],
batchsize=C["batchsize"],
border=C["border"],
limit=C["limit"],
random=False,
dtype=theano.config.floatX,
rnd=rnd,
)
C["training_size"] = training_data.size()
C["validation_size"] = validation_data.size()
print "Training size: %d" % C["training_size"]
print "Validation size: %d" % C["validation_size"]
metric_recorder.add_experiment_metainfo(constants=C)
metric_recorder.start()
n_in = (2 * border + 1) ** 2
net = Network(
[
FullyConnectedLayer(n_in=n_in, n_out=C["hidden"], rnd=rnd),
FullyConnectedLayer(n_in=C["hidden"], n_out=1, rnd=rnd),
],
C["mini_batch_size"],
)
result = net.train(
tdata=training_data,
epochs=C["epochs"],
mbs=C["mini_batch_size"],
eta=C["eta"],
eta_min=C["eta_min"],
vdata=validation_data,
lmbda=C["lmbda"],
momentum=None,
patience_increase=C["patience_increase"],
improvement_threshold=C["improvement_threshold"],
validation_frequency=C["validation_frequency"],
metric_recorder=metric_recorder,
save_dir="./models/%d_" % metric_recorder.job_id,
early_stoping=False,
)
print "Time = %f" % metric_recorder.stop()
print "Result = %f" % result
return float(result)