if args.device is not None:
if 'THEANO_FLAGS' in os.environ is not None:
env = os.environ['THEANO_FLAGS']
env = re.sub(r'/device=[a-zA-Z0-9]+/',r'/device=' + args.device, env)
else:
env = 'device=' + args.device
os.environ['THEANO_FLAGS'] = env
arg_param_pairings = [
(args.seed, 'random_seed'),
(args.results_db, 'results_db'),
(args.results_host, 'results_host'),
(args.results_table, 'results_table'),
]
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.data import *
from toupee.mlp import MLP, test_mlp
from toupee import common
import theano
import theano.tensor as T
dataset = load_data(params.dataset,
resize_to = params.resize_data_to,
#!/usr/bin/python
import gc
import sys
import numpy as np
import numpy.random
import theano
import theano.tensor as T
import dill
from toupee import config
from toupee.data import *
from toupee.mlp import test_mlp
if __name__ == '__main__':
params = config.load_parameters(sys.argv[1])
dataset = load_data(params.dataset,
resize_to = params.resize_data_to,
shared = False,
pickled = params.pickled)
x = T.matrix('x')
y = T.ivector('y')
index = T.lscalar('index')
method = params.method
method.prepare(params,dataset)
train_set = method.resampler.get_train()
valid_set = method.resampler.get_valid()
test_set = method.resampler.get_test()
test_set_x, test_set_y = test_set
shared_dataset = [train_set,valid_set,test_set]
continuations = dill.load(open(sys.argv[2]))
#!/usr/bin/python
import gc
import sys
import numpy as np
import numpy.random
import theano
import theano.tensor as T
import dill
from toupee import config
from toupee.data import *
if __name__ == '__main__':
params = config.load_parameters(sys.argv[1])
dataset = load_data(params.dataset, shared=False, pickled=params.pickled)
x = T.matrix('x')
y = T.ivector('y')
method = params.method
method.prepare(params, dataset)
train_set = method.resampler.get_train()
valid_set = method.resampler.get_valid()
members = []
for i in range(0, params.ensemble_size):
print('training member {0}'.format(i))
new_member = method.create_member(x, y)
members.append(new_member)
gc.collect()
dill.dump(members, open(sys.argv[2], "wb"))
(args.trainfile, 'trainfile'),
(args.verbose, 'verbose'),
(str(round(time.time())), 'ensemble_id'
) #<-- unique ID for this ensemble
]
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
#sets the ensemble parameters
#TODO: if any data transform option is true, :poop_emoji:
params = config.load_parameters(args.params_file)
if args.model_dir is not None:
params.model_dir = args.model_dir
if args.data_dir is not None:
params.dataset = args.data_dir
elif args.model_dir is not None:
params.dataset = params.model_dir
if params.model_file is not None:
params.model_file = os.path.join(params.model_dir, params.model_file)
else:
params.model_file = os.path.join(params.model_dir, args.model_file)
def arg_params(arg_value, param):
