def __init__(self, data_dir, model_dir, task_id, isInteractive=True, OOV=False, memory_size=50, random_state=None,
batch_size=32, learning_rate=0.001, epsilon=1e-8, max_grad_norm=40.0, evaluation_interval=10, hops=3,
epochs=200, embedding_size=20,intro_times=20):
self.data_dir = data_dir
self.task_id = task_id
self.model_dir = model_dir
# self.isTrain=isTrain
self.isInteractive = isInteractive
self.OOV = OOV
self.memory_size = memory_size
self.random_state = random_state
self.batch_size = batch_size
self.learning_rate = learning_rate
self.epsilon = epsilon
self.max_grad_norm = max_grad_norm
self.evaluation_interval = evaluation_interval
self.hops = hops
self.epochs = epochs
self.embedding_size = embedding_size
self.intro_times=intro_times
candidates, self.candid2indx = load_candidates(
self.data_dir, self.task_id)
self.n_cand = len(candidates)
print("Candidate Size", self.n_cand)
self.indx2candid = dict(
(self.candid2indx[key], key) for key in self.candid2indx)
# task data
self.trainData, self.testData, self.valData = load_dialog_task(
self.data_dir, self.task_id, self.candid2indx, self.OOV)
data = self.trainData + self.testData + self.valData
self.build_vocab(data, candidates)
#build training words set
# pdb.set_trace()
self.train_val_wordset = self.words_set(self.valData+self.trainData)
all_wordset = self.words_set(data)
no_oov_word = len(self.train_val_wordset)
with_oov_word = len(all_wordset)
print('oov words', with_oov_word - no_oov_word)
# new_words=[]
# for word in all_wordset:
# if word not in self.train_val_wordset:
# new_words.append(self.idx_word[word])
# print('These words are new:',new_words)
# pdb.set_trace()
# self.candidates_vec=vectorize_candidates_sparse(candidates,self.word_idx)
self.candidates_vec = vectorize_candidates(
candidates, self.word_idx, self.candidate_sentence_size)
optimizer = tf.train.AdamOptimizer(
learning_rate=self.learning_rate, epsilon=self.epsilon)
self.sess = tf.Session()
self.model = MemN2NDialog(self.batch_size, self.vocab_size, self.n_cand, self.sentence_size,
self.embedding_size, self.candidates_vec, session=self.sess,
hops=self.hops, max_grad_norm=self.max_grad_norm, optimizer=optimizer,
task_id=task_id,introspection_times=self.intro_times)
self.saver = tf.train.Saver(max_to_keep=1)
self.summary_writer = tf.summary.FileWriter(
self.model.root_dir, self.model.graph_output.graph)
def __init__(self, data_dir, model_dir, task_id, isInteractive=True, OOV=False, memory_size=50, random_state=None, batch_size=32, learning_rate=0.001, epsilon=1e-8, max_grad_norm=40.0, evaluation_interval=10, hops=3, epochs=200, embedding_size=20):
self.data_dir = data_dir
self.task_id = task_id
self.model_dir = model_dir
# self.isTrain=isTrain
self.isInteractive = isInteractive
self.OOV = OOV
self.memory_size = memory_size
self.random_state = random_state
self.batch_size = batch_size
self.learning_rate = learning_rate
self.epsilon = epsilon
self.max_grad_norm = max_grad_norm
self.evaluation_interval = evaluation_interval
self.hops = hops
self.epochs = epochs
self.embedding_size = embedding_size
candidates, self.candid2indx = load_candidates(
self.data_dir, self.task_id)
self.n_cand = len(candidates)
print("Candidate Size", self.n_cand)
self.indx2candid = dict(
(self.candid2indx[key], key) for key in self.candid2indx)
# task data
self.trainData, self.testData, self.valData = load_dialog_task(
self.data_dir, self.task_id, self.candid2indx, self.OOV)
data = self.trainData + self.testData + self.valData
self.build_vocab(data, candidates)
# self.candidates_vec=vectorize_candidates_sparse(candidates,self.word_idx)
self.candidates_vec = vectorize_candidates(
candidates, self.word_idx, self.candidate_sentence_size)
optimizer = tf.train.AdamOptimizer(
learning_rate=self.learning_rate, epsilon=self.epsilon)
self.sess = tf.Session()
self.model = MemN2NDialog(self.batch_size, self.vocab_size, self.n_cand, self.sentence_size, self.embedding_size, self.candidates_vec, session=self.sess,
hops=self.hops, max_grad_norm=self.max_grad_norm, optimizer=optimizer, task_id=task_id)
self.saver = tf.train.Saver(max_to_keep=50)
self.summary_writer = tf.summary.FileWriter(
self.model.root_dir, self.model.graph_output.graph)
def __init__(self,
data_dir,
model_dir,
task_id,
OOV=False,
memory_size=250,
random_state=None,
batch_size=32,
learning_rate=0.001,
epsilon=1e-8,
max_grad_norm=40.0,
evaluation_interval=10,
hops=3,
epochs=10,
embedding_size=20,
save_vocab=False,
load_vocab=False):
"""Creates wrapper for training and testing a chatbot model.
Args:
data_dir: Directory containing personalized dialog tasks.
model_dir: Directory containing memn2n model checkpoints.
task_id: Personalized dialog task id, 1 <= id <= 5. Defaults to `1`.
OOV: If `True`, use OOV test set. Defaults to `False`
memory_size: The max size of the memory. Defaults to `250`.
random_state: Random state to set graph-level random seed. Defaults to `None`.
batch_size: Size of the batch for training. Defaults to `32`.
learning_rate: Learning rate for Adam Optimizer. Defaults to `0.001`.
epsilon: Epsilon value for Adam Optimizer. Defaults to `1e-8`.
max_gradient_norm: Maximum L2 norm clipping value. Defaults to `40.0`.
evaluation_interval: Evaluate and print results every x epochs.
Defaults to `10`.
hops: The number of hops over memory for responding. A hop consists
of reading and addressing a memory slot. Defaults to `3`.
epochs: Number of training epochs. Defualts to `200`.
embedding_size: The size of the word embedding. Defaults to `20`.
save_vocab: If `True`, save vocabulary file. Defaults to `False`.
load_vocab: If `True`, load vocabulary from file. Defaults to `False`.
"""
self.data_dir = data_dir
self.task_id = task_id
self.model_dir = model_dir
self.OOV = OOV
self.memory_size = memory_size
self.random_state = random_state
self.batch_size = batch_size
self.learning_rate = learning_rate
self.epsilon = epsilon
self.max_grad_norm = max_grad_norm
self.evaluation_interval = evaluation_interval
self.hops = hops
self.epochs = epochs
self.embedding_size = embedding_size
self.save_vocab = save_vocab
self.load_vocab = load_vocab
candidates, self.candid2indx = load_candidates(self.data_dir,
self.task_id)
self.n_cand = len(candidates)
# print("Candidate Size", self.n_cand)
self.indx2candid = dict(
(self.candid2indx[key], key) for key in self.candid2indx)
# Task data
self.trainData, self.testData, self.valData = load_dialog_task(
self.data_dir, self.task_id, self.candid2indx, self.OOV)
# print(self.testData)
data = self.trainData + self.testData + self.valData
self.build_vocab(data, candidates, self.save_vocab, self.load_vocab)
print("build_vocab", self.build_vocab)
self.candidates_vec = vectorize_candidates(
candidates, self.word_idx, self.candidate_sentence_size)
print("build_vocab", self.candidates_vec)
optimizer = tf.train.AdamOptimizer(learning_rate=self.learning_rate,
epsilon=self.epsilon)
self.sess = tf.Session()
self.model = MemN2NDialog(self.batch_size,
self.vocab_size,
self.n_cand,
self.sentence_size,
self.embedding_size,
self.candidates_vec,
session=self.sess,
hops=self.hops,
max_grad_norm=self.max_grad_norm,
optimizer=optimizer,
task_id=task_id)
self.saver = tf.train.Saver(max_to_keep=50)
def __init__(self,
data_dir,
model_dir,
task_id,
source,
resFlag,
wrong_conversations,
error,
acc_each_epoch,
acc_ten_epoch,
conv_wrong_right,
epochs,
OOV=False,
memory_size=50,
random_state=None,
batch_size=32,
learning_rate=0.001,
epsilon=1e-8,
max_grad_norm=40.0,
evaluation_interval=10,
hops=3,
embedding_size=20):
self.data_dir = data_dir
self.task_id = task_id
self.model_dir = model_dir
self.OOV = OOV
self.memory_size = memory_size
self.random_state = random_state
self.batch_size = batch_size
self.learning_rate = learning_rate
self.epsilon = epsilon
self.max_grad_norm = max_grad_norm
self.evaluation_interval = evaluation_interval
self.hops = hops
self.epochs = epochs
self.embedding_size = embedding_size
self.source = source
self.resFlag = resFlag
self.wrong_conversations = wrong_conversations
self.error = error
self.acc_each_epoch = acc_each_epoch
self.acc_ten_epoch = acc_ten_epoch
candidates, self.candid2indx = load_candidates(self.data_dir,
self.task_id)
self.n_cand = len(candidates)
print("Candidate Size", self.n_cand)
self.indx2candid = dict(
(self.candid2indx[key], key) for key in self.candid2indx)
# create train, test and validation data
self.trainData, self.testData, self.valData = load_dialog_task(
self.data_dir, self.task_id, self.candid2indx, self.OOV)
data = self.trainData + self.testData + self.valData
self.build_vocab(data, candidates)
self.test_acc_list = []
self.candidates_vec = vectorize_candidates(
candidates, self.word_idx, self.candidate_sentence_size)
optimizer = tf.train.AdamOptimizer(learning_rate=self.learning_rate,
epsilon=self.epsilon)
self.sess = tf.Session()
self.model = MemN2NDialog(self.batch_size,
self.vocab_size,
self.n_cand,
self.sentence_size,
self.embedding_size,
self.candidates_vec,
session=self.sess,
hops=self.hops,
max_grad_norm=self.max_grad_norm,
optimizer=optimizer,
task_id=task_id,
source=self.source,
resFlag=self.resFlag,
oov=self.OOV)
self.saver = tf.train.Saver(max_to_keep=50)
self.summary_writer = tf.summary.FileWriter(
self.model.root_dir, self.model.graph_output.graph)
def __init__(self,
data_dir,
model_dir,
task_id,
isInteractive=True,
OOV=False,
memory_size=250,
random_state=None,
batch_size=32,
learning_rate=0.001,
epsilon=1e-8,
max_grad_norm=40.0,
evaluation_interval=10,
hops=3,
epochs=200,
embedding_size=20,
alpha=.5,
save_vocab=None,
load_vocab=None,
verbose=False,
load_profiles=None,
save_profiles=None):
self.data_dir = data_dir
self.task_id = task_id
self.model_dir = model_dir
# self.isTrain=isTrain
self.isInteractive = isInteractive
self.OOV = OOV
self.memory_size = memory_size
self.random_state = random_state
self.batch_size = batch_size
self.learning_rate = learning_rate
self.epsilon = epsilon
self.max_grad_norm = max_grad_norm
self.evaluation_interval = evaluation_interval
self.hops = hops
self.epochs = epochs
self.embedding_size = embedding_size
self.save_vocab = save_vocab
self.load_vocab = load_vocab
self.verbose = verbose
self.alpha = alpha
# Loading possible answers
self.candidates, self.candid2indx = load_candidates(
self.data_dir, self.task_id)
self.n_cand = len(self.candidates)
print("Candidate Size", self.n_cand)
self.indx2candid = dict(
(self.candid2indx[key], key) for key in self.candid2indx)
# task data
self.trainData, self.testData, self.valData = load_dialog_task(
self.data_dir, self.task_id, self.candid2indx, self.OOV)
data = self.trainData + self.testData + self.valData
# Find profiles types
if load_profiles:
with open(load_profiles, 'rb') as f:
self._profiles_mapping = pickle.load(f)
else:
self._profiles_mapping = generate_profile_encoding(self.trainData)
if save_profiles:
with open(save_profiles, 'wb') as f:
pickle.dump(self._profiles_mapping, f)
profiles_idx_set = set(self._profiles_mapping.values())
print("Profiles:", self._profiles_mapping)
# Vocabulary
self.build_vocab(data, self.candidates, self.save_vocab,
self.load_vocab)
# self.candidates_vec=vectorize_candidates_sparse(self.candidates,self.word_idx)
self.candidates_vec = vectorize_candidates(
self.candidates, self.word_idx, self.candidate_sentence_size)
# Model initialisation
optimizer = tf.train.AdamOptimizer(learning_rate=self.learning_rate,
epsilon=self.epsilon)
self.sess = tf.Session()
self.model = MemN2NDialog(self.batch_size,
self.vocab_size,
self.n_cand,
self.sentence_size,
self.embedding_size,
self.candidates_vec,
profiles_idx_set,
session=self.sess,
hops=self.hops,
max_grad_norm=self.max_grad_norm,
alpha=alpha,
optimizer=optimizer,
task_id=task_id,
verbose=verbose)
self.saver = tf.train.Saver(max_to_keep=50)
# self.summary_writer = tf.train.SummaryWriter(self.model.root_dir, self.model.graph_output.graph)
self.summary_writer = tf.summary.FileWriter(
self.model.root_dir, self.model.graph_output.graph)