def main(*_fold_info, **kwargs):
args = rasengan.Namespace()
args = args_creation_part1(args)
args = update_args(args, kwargs)
data = transducer_data.main(args)
args = args_creation_part2(args, data)
args = update_args(args, kwargs)
args.diff_kwargs = kwargs
# Start each run in a fresh directory to avoid interference
# with other running processes and avoiding overwriting results of
# previous processes.
import os
idx = 0
while os.path.exists(args.folder + '_' + str(idx)):
idx += 1
args.folder = args.folder + '_' + str(idx)
print 'Set args.folder to', args.folder
if __name__ != '__main__':
# We are probably running from the hpolibrary.
# In non-interactive batch runs, it is also important to
# disable debug_support so that we dont call post-mortem in
# case of an exception.
rasengan.disable_debug_support()
else:
#rasengan.warn('NOTE: I am using pretrained pkl')
# args.pretrained_param_pklfile = (args.folder + r'/' + args.pkl_name)
pass
with lstm_seqlabel_circuit_compilation.make(args, force=True):
error = lstm_seqlabel_circuit_compilation.perform_training_and_testing(
"", args, data)
return error
def get_train_test_namespace(args):
if args.perform_training:
print 'Compiling train_model'
train_model = compile_args(args)
set_dropout_to_zero(args)
print 'Compiling test_model'
test_model = compile_args(args)
# Prepare the `ttns` namespace by adding train and test prefixes.
ttns = rasengan.Namespace('ttns')
if args.perform_training:
ttns = ttns.update_and_append_prefix(train_model, 'train_')
ttns = ttns.update_and_append_prefix(test_model, 'test_')
return ttns
'''
| Filename : test_conjunctivemixture.py
| Description : Test ConjunctiveMixture Chip
| Author : Pushpendre Rastogi
| Created : Mon Nov 16 01:00:45 2015 (-0500)
| Last-Updated: Mon Nov 16 01:08:20 2015 (-0500)
| By: Pushpendre Rastogi
| Update #: 3
'''
import rasengan
import lstm_seqlabel_circuit
import lstm_seqlabel_circuit_compilation
import util_lstm_seqlabel
args = rasengan.Namespace()
args.conjmix_embed_BOS = 1
args.conjmix_clip_gradient = 0
chips = [(lstm_seqlabel_circuit.ConjunctiveMixture, 'conjmix')]
with util_lstm_seqlabel.debug_support():
ttns = lstm_seqlabel_circuit_compilation.get_train_test_namespace(args)
# Test value of ttns
def main(args):
with rasengan.debug_support():
with rasengan.tictoc("Loading Data"):
data_list = rasengan.namespacer(read_data(args.train_fn))
val_data_list = rasengan.namespacer(read_data(args.dev_fn))
if args.partition_dev_into_train > 0:
lim = args.partition_dev_into_test
data_list.extend(val_data_list[lim:])
val_data_list = val_data_list[:lim]
if args.partition_dev_into_test > 0:
lim = args.partition_dev_into_test
test_data_list = val_data_list[lim:]
val_data_list = val_data_list[:lim]
else:
test_data_list = rasengan.namespacer(read_data(args.test_fn))
# data_list = val_data_list = [(u'jason', u'eisner')]
lst_char = get_lst_char(data_list + val_data_list + test_data_list)
data_list = add_bos(data_list)
val_data_list = add_bos(val_data_list)
test_data_list = add_bos(test_data_list)
warnings.warn('''
NOTE: While preparing sigma, we add 1 to the index
returned by enumerate because the transducer unit that
Ryan wrote uses index 0 as the index for the epsilon
symbol. So essentially the epsilon symbol and the
integer 0 are reserved symbols that cannot appear in the
vocabulary.
ALSO, we need to add 1 to the vocsize because of that.
''')
# sigma :: char -> int
sigma = dict((b, a + 1) for (a, b) in enumerate(lst_char))
# sigma_inv :: int -> char
sigma_inv = dict((a + 1, b) for (a, b) in enumerate(lst_char))
if args.limit_corpus > 0:
data_list = data_list[:args.limit_corpus]
train_data = numerize(data_list, sigma, args.win)
val_data = numerize(val_data_list, sigma, args.win)
test_data = numerize(test_data_list, sigma, args.win)
data = rasengan.Namespace()
#-------------------------------------------------------------#
# Add sets that would be used by the tensorflow seq2seq #
# model. See~$PY/tensorflow/models/rnn/translate/translate.py #
#-------------------------------------------------------------#
data.train_data = data_list
data.val_data = val_data_list
data.test_data = test_data_list
data.train_set = train_data
data.dev_set = val_data
data.test_set = test_data
data.vocsize = len(sigma) + 1
data.idx2label = sigma_inv
data.label2idx = sigma
data.train_lex = [e[0] for e in train_data]
data.train_y = [e[1] for e in train_data]
data.valid_lex = [e[0] for e in val_data]
data.valid_y = util_lstm_seqlabel.convert_id_to_word(
[e[1] for e in val_data], data.idx2label)
data.test_lex = [e[0] for e in test_data]
data.test_y = util_lstm_seqlabel.convert_id_to_word(
[e[1] for e in test_data], data.idx2label)
data.words_train = []
data.words_valid = []
data.words_test = []
return data