numpy.random.seed(args.seed)
from toupee import data
from toupee import config
from toupee.mlp import sequential_model
params = config.load_parameters(args.params_file)
def arg_params(arg_value,param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg,param)
original_params = copy.deepcopy(params)
dataset = data.load_data(params.dataset,
pickled = params.pickled,
one_hot_y = params.one_hot,
join_train_and_valid = params.join_train_and_valid)
method = params.method
method.prepare(params,dataset)
train_set = method.resampler.get_train()
valid_set = method.resampler.get_valid()
members = []
intermediate_scores = []
final_score = None
for i in range(0,params.ensemble_size):
print 'training member {0}'.format(i)
members.append(method.create_member())
ensemble = method.create_aggregator(params,members,train_set,valid_set)
test_set_x, test_set_y = method.resampler.get_test()
test_score = accuracy(ensemble,test_set_x,test_set_y)
print 'Intermediate test accuracy: {0} %'.format(test_score * 100.)
if os.path.exists(dict_dir):
params.dataset = dict_dir
else:
print("The desired dict_number doesn't exist!")
def arg_params(arg_value, param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg, param)
dataset = data.load_data(params.dataset,
pickled=params.pickled,
one_hot_y=params.one_hot,
join_train_and_valid=params.join_train_and_valid,
zca_whitening=params.zca_whitening,
testfile=args.testfile,
validfile=args.validfile,
trainfile=args.trainfile)
method = params.method
method.prepare(params, dataset)
train_set = method.resampler.get_train()
valid_set = method.resampler.get_valid()
#selects the appropriate intermediate score: classification - accuracy; regression - euclidian_distance
scorer = []
scorer_name = []
if params.classification == True:
scorer.append(accuracy)
scorer_name.append('accuracy')
else:
from toupee import data
from toupee import config
from toupee.mlp import sequential_model
params = config.load_parameters(args.params_file)
def arg_params(arg_value,param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg,param)
original_params = copy.deepcopy(params)
dataset = data.load_data(params.dataset,
pickled = params.pickled,
one_hot_y = params.one_hot,
join_train_and_valid = params.join_train_and_valid,
zca_whitening = params.zca_whitening)
method = params.method
method.prepare(params,dataset)
train_set = method.resampler.get_train()
valid_set = method.resampler.get_valid()
members = []
intermediate_scores = []
final_score = None
continue_learning = True
for i in range(0,params.ensemble_size):
print('training member {0}'.format(i))
m = method.create_member()
if m[0] is not None:
members.append(m[:2])
arg_param_pairings = [
(args.seed, 'random_seed'),
(args.results_db, 'results_db'),
(args.results_host, 'results_host'),
(args.results_table, 'results_table'),
(args.epochs, 'n_epochs'),
]
from toupee import config
params = config.load_parameters(args.params_file)
def arg_params(arg_value, param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg, param)
from toupee import data
from toupee.mlp import MLP, test_mlp
dataset = data.load_data(params.dataset,
resize_to=params.resize_data_to,
shared=False,
pickled=params.pickled,
center_and_normalise=params.center_and_normalise,
join_train_and_valid=params.join_train_and_valid)
pretraining_set = data.make_pretraining_set(dataset, params.pretraining)
mlp = test_mlp(dataset, params, pretraining_set=pretraining_set)
if args.save_file is not None:
dill.dump(mlp, open(args.save_file, "wb"))
from toupee import data
import sys
import cPickle
import gzip
import os
import copy
import math
import numpy as np
if __name__ == '__main__':
if len(sys.argv) > 2:
dataset = sys.argv[1]
fileName = sys.argv[2]
else:
raise Exception("need source and destination")
dataset = data.load_data(dataset, pickled=False, shared=False)
train, valid, test = dataset
train_x, train_y = train
valid_x, valid_y = valid
test_x, test_y = test
# n_in = test_x.shape[1]
# params = { 'alpha': 0.0,
# 'beta': 30.0,
# 'gamma': 20.0,
# 'sigma': 1,
# 'pflip': 0.0,
# 'translation': 3.0,
# 'bilinear': True
# }
# t = data.GPUTransformer(sharedX(train_x),
# x=int(math.sqrt(n_in)),
print "setting random seed to: {0}".format(args.seed)
numpy.random.seed(args.seed)
from toupee import data
from toupee import config
from toupee.mlp import sequential_model
params = config.load_parameters(args.params_file)
def arg_params(arg_value,param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg,param)
dataset = data.load_data(params.dataset,
pickled = params.pickled,
one_hot_y = params.one_hot)
method = params.method
method.prepare(params,dataset)
train_set = method.resampler.get_train()
valid_set = method.resampler.get_valid()
members = []
intermediate_scores = []
final_score = None
for i in range(0,params.ensemble_size):
print 'training member {0}'.format(i)
members.append(method.create_member())
ensemble = method.create_aggregator(params,members,train_set,valid_set)
test_set_x, test_set_y = method.resampler.get_test()
test_score = accuracy(ensemble,test_set_x,test_set_y)
print 'Intermediate test accuracy: {0} %'.format(test_score * 100.)
#!/usr/bin/python
import sys
import numpy as np
import os
from toupee import data
if __name__ == '__main__':
location = sys.argv[1]
dest = sys.argv[1] + "_th/"
if not os.path.exists(dest):
os.mkdir(dest)
shape = [int(x) for x in sys.argv[2].split(',')]
dataset = data.load_data(location, pickled=False, one_hot_y=True)
print dataset[0][0].shape
np.savez_compressed(dest + 'train',
x=dataset[0][0].reshape([dataset[0][0].shape[0]] +
shape),
y=dataset[0][1])
np.savez_compressed(dest + 'valid',
x=dataset[1][0].reshape([dataset[1][0].shape[0]] +
shape),
y=dataset[1][1])
np.savez_compressed(dest + 'test',
x=dataset[2][0].reshape([dataset[2][0].shape[0]] +
shape),
y=dataset[2][1])
#!/usr/bin/python
import sys
import numpy as np
import os
from toupee import data
if __name__ == '__main__':
location = sys.argv[1]
dest = sys.argv[1] + "_th/"
if not os.path.exists(dest):
os.mkdir(dest)
shape = [int(x) for x in sys.argv[2].split(',')]
dataset = data.load_data(location,
pickled = False,
one_hot_y = True)
print dataset[0][0].shape
np.savez_compressed(dest + 'train',
x=dataset[0][0].reshape([dataset[0][0].shape[0]] + shape),
y=dataset[0][1])
np.savez_compressed(dest + 'valid',
x=dataset[1][0].reshape([dataset[1][0].shape[0]] + shape),
y=dataset[1][1])
np.savez_compressed(dest + 'test',
x=dataset[2][0].reshape([dataset[2][0].shape[0]] + shape),
y=dataset[2][1])
arg_param_pairings = [
(args.seed, 'random_seed'),
(args.results_db, 'results_db'),
(args.results_host, 'results_host'),
(args.results_table, 'results_table'),
(args.epochs, 'n_epochs'),
]
from toupee import config
params = config.load_parameters(args.params_file)
def arg_params(arg_value,param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg,param)
from toupee import data
from toupee.mlp import MLP, test_mlp
dataset = data.load_data(params.dataset,
resize_to = params.resize_data_to,
shared = False,
pickled = params.pickled,
center_and_normalise = params.center_and_normalise,
join_train_and_valid = params.join_train_and_valid)
pretraining_set = data.make_pretraining_set(dataset,params.pretraining)
mlp = test_mlp(dataset, params, pretraining_set = pretraining_set)
if args.save_file is not None:
dill.dump(mlp,open(args.save_file,"wb"))
arg_param_pairings = [
(args.results_db, 'results_db'),
(args.results_host, 'results_host'),
(args.results_table, 'results_table'),
(args.epochs, 'n_epochs'),
]
if 'seed' in args.__dict__:
print "setting random seed to: {0}".format(args.seed)
numpy.random.seed(args.seed)
from toupee import data
from toupee import config
from toupee.mlp import sequential_model
import toupee
print "using toupee version {0}".format(toupee.version)
params = config.load_parameters(args.params_file)
def arg_params(arg_value, param):
if arg_value is not None:
params.__dict__[param] = arg_value
for arg, param in arg_param_pairings:
arg_params(arg, param)
dataset = data.load_data(params.dataset,
pickled=params.pickled,
one_hot_y=params.one_hot,
join_train_and_valid=params.join_train_and_valid)
mlp = sequential_model(dataset, params)
#!/usr/bin/python
from toupee import data
import numpy as np
import argparse
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Convert a pylearn2 dataset')
parser.add_argument('--dest', help='the destination for the dataset')
parser.add_argument('--source', help='the source of the data')
parser.add_argument('--shape', help='new shape to enforce')
parser.add_argument('--tf-to-th',
help='reorder dimensions from tf to th',
action='store_true')
parser.add_argument('--th-to-tf',
help='reorder dimensions from th to tf',
action='store_true')
args = parser.parse_args()
dataset = data.load_data(args.source,
pickled=False,
one_hot_y=False,
center_and_normalise=True,
join_train_and_valid=False,
zca_whitening=True)
np.savez_compressed(args.dest + "/train", x=dataset[0][0], y=dataset[0][1])
np.savez_compressed(args.dest + "/valid", x=dataset[1][0], y=dataset[1][1])
np.savez_compressed(args.dest + "/test", x=dataset[2][0], y=dataset[2][1])
from toupee import data
import sys
import cPickle
import gzip
import os
import copy
import math
import numpy as np
if __name__ == '__main__':
if len(sys.argv) > 2:
dataset = sys.argv[1]
fileName = sys.argv[2]
else:
raise Exception("need source and destination")
dataset = data.load_data(dataset,pickled=False,shared=False)
train,valid,test = dataset
train_x, train_y = train
valid_x, valid_y = valid
test_x, test_y = test
# n_in = test_x.shape[1]
# params = { 'alpha': 0.0,
# 'beta': 30.0,
# 'gamma': 20.0,
# 'sigma': 1,
# 'pflip': 0.0,
# 'translation': 3.0,
# 'bilinear': True
# }
# t = data.GPUTransformer(sharedX(train_x),
# x=int(math.sqrt(n_in)),
