# mode=theano.compile.MonitorMode(post_func=detect_nan)
)
update = theano.function(
inputs=[lr],
updates = param_update + clear_update,
outputs = [ T.sqrt(T.sum(T.sqr(w))) for w in deltas ],
on_unused_input='warn',
# mode=theano.compile.MonitorMode(post_func=detect_nan)
)
return acc,update
if __name__ == "__main__":
training_file = sys.argv[1]
compute_tree_exists = False
vocab_in = vocab.load("qa2.pkl")
vocab_size = len(vocab_in)
print "Vocab size is:", vocab_size
evidence_count = 2
if compute_tree_exists:
inputs,outputs,params,grads = pickle.load(open("compute_tree.pkl"))
else:
print "Creating compute tree...",
P = Parameters()
story = T.ivector('story')
idxs = T.ivector('idxs')
qstn = T.ivector('qstn')
ans_evds = T.ivector('ans_evds')
ans_lbl = T.iscalar('ans_lbl')
attention = model.build(P,
# -*- coding: utf-8 -*- import os, sys, time import numpy as np import model import vocab from config import config data_dir = "text" model_dir = "model" dataset, config.n_vocab, config.n_dataset = vocab.load(data_dir) lm = model.build() lm.load(model_dir) n_epoch = 1000 n_train = 5000 batchsize = 64 total_time = 0 # 長すぎるデータはメモリに乗らないこともあります max_length_of_chars = 100 # 学習初期は短い文章のみ学習し、徐々に長くしていきます。 # この機能が必要ない場合は最初から大きな値を設定します。 current_length_limit = 15 def make_batch(): target_batch_array = [] max_length_in_batch = 0 for b in xrange(batchsize): length = current_length_limit + 1 while length > current_length_limit:
tmp_file = args.temporary_file
max_epochs = args.max_epochs
batch_size = args.batch_size
improvement_threshold = args.improvement_threshold
validation_percent = args.validation_percent
patience = args.patience
checkpoint = args.checkpoint
embedding_size = args.embedding_size
hidden_size = args.hidden_size
l2_coefficient = args.l2
id2char = pickle.load(open(vocab_file,'r'))
char2id = vocab.load(vocab_file)
P = Parameters()
lang_model = model.build(P,
character_count=len(char2id) + 1,
embedding_size=embedding_size,
hidden_size=hidden_size
)
def cost(X, P): # batch_size x time
eps = 1e-3
X = X.T # time x batch_size
char_prob_dist = lang_model(X[:-1]) # time x batch_size x output_size
char_prob_dist = (1 - 2 * eps) * char_prob_dist + eps
label_prob = char_prob_dist[
T.arange(X.shape[0] - 1).dimshuffle(0, 'x'),
T.arange(X.shape[1]).dimshuffle('x', 0),
import numpy as np
import cPickle as pickle
import theano
import theano.tensor as T
import numpy as np
import vocab
import model
from theano_toolkit.parameters import Parameters
if __name__ == "__main__":
model_file = args.model_file
temp_input = args.temperature
id2char = pickle.load(args.vocab_file)
char2id = vocab.load(args.vocab_file.name)
prime_str = args.prime
P = Parameters()
sampler = model.build_sampler(P,
character_count=len(char2id) + 1,
embedding_size=20,
hidden_size=100
)
P.load(model_file)
temp = T.scalar('temp')
char = T.iscalar('char')
p_cell_1, p_hidden_1, p_cell_2, p_hidden_2 = T.vector("p_cell_1"), T.vector("p_hidden_2"), T.vector("p_cell_2"), T.vector("p_hidden_2")
output, cell_1, hidden_1, cell_2, hidden_2 = sampler(temp, char, p_cell_1, p_hidden_1, p_cell_2, p_hidden_2)
sample = theano.function(
import numpy as np
import cPickle as pickle
import theano
import theano.tensor as T
import numpy as np
import vocab
import model
from theano_toolkit.parameters import Parameters
if __name__ == "__main__":
model_file = args.model_file
temp_input = args.temperature
id2char = pickle.load(args.vocab_file)
char2id = vocab.load(args.vocab_file.name)
prime_str = args.prime
P = Parameters()
sampler = model.build_sampler(P,
character_count=len(char2id) + 1,
embedding_size=20,
hidden_size=100)
P.load(model_file)
temp = T.scalar('temp')
char = T.iscalar('char')
p_cell_1, p_hidden_1, p_cell_2, p_hidden_2 = T.vector(
"p_cell_1"), T.vector("p_hidden_2"), T.vector("p_cell_2"), T.vector(
"p_hidden_2")
output, cell_1, hidden_1, cell_2, hidden_2 = sampler(
# -*- coding: utf-8 -*- import sys, os from args import args sys.path.append(os.path.split(os.getcwd())[0]) import vocab from model import Conf, Model dataset, n_vocab, n_dataset = vocab.load(args.text_dir) conf = Conf() conf.gpu_enabled = False if args.gpu_enabled == -1 else True conf.n_vocab = n_vocab # Embed conf.char_embed_size = 50 conf.word_embed_size = 200 # Encoder conf.word_encoder_lstm_units = [500] conf.word_encoder_lstm_apply_batchnorm = False conf.word_encoder_fc_hidden_units = [] conf.word_encoder_fc_apply_batchnorm = False conf.word_encoder_fc_apply_dropout = False conf.word_encoder_fc_nonlinear = "elu" # Decoder conf.word_decoder_lstm_units = [500] conf.word_decoder_lstm_apply_batchnorm = False conf.word_decoder_merge_type = "concat" # Discriminator conf.discriminator_hidden_units = [200, 200]
# -*- coding: utf-8 -*-
import os, sys, time, codecs
import numpy as np
import model
import vocab
from config import config
# Windowsでprintする用
sys.stdout = codecs.getwriter(sys.stdout.encoding)(sys.stdout,
errors="xmlcharrefreplace")
data_dir = "text"
model_dir = "model"
dataset, config.n_vocab, config.n_dataset = vocab.load(data_dir)
lm = model.build()
lm.load(model_dir)
def sample_seq():
target_batch_array = []
max_length_in_batch = 0
k = np.random.randint(0, config.n_dataset)
target_seq = dataset[k]
source_seq = target_seq[::-1]
return source_seq, target_seq
for phrase in xrange(50):
source_seq, target_seq = sample_seq()
lm.reset_state()
y_seq = lm.decode(source_seq, sampling_y=True, test=True)
)
update = theano.function(
inputs=[lr],
updates=param_update + clear_update,
outputs=[T.sqrt(T.sum(T.sqr(w))) for w in deltas],
on_unused_input='warn',
# mode=theano.compile.MonitorMode(post_func=detect_nan)
)
return acc, update
if __name__ == "__main__":
training_file = sys.argv[1]
compute_tree_exists = False
vocab_in = vocab.load("qa2.pkl")
vocab_size = len(vocab_in)
print "Vocab size is:", vocab_size
evidence_count = 2
if compute_tree_exists:
inputs, outputs, params, grads = pickle.load(open("compute_tree.pkl"))
else:
print "Creating compute tree...",
P = Parameters()
story = T.ivector('story')
idxs = T.ivector('idxs')
qstn = T.ivector('qstn')
ans_evds = T.ivector('ans_evds')
ans_lbl = T.iscalar('ans_lbl')
attention = model.build(P,
