def get_batch(self, data, bucket_id):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(data[bucket_id])
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
python类GO_ID的实例源码
def get_mix_batch(self, bucketed_data, bucket_id, this_batch_size):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(this_batch_size):
encoder_input, decoder_input = random.choice(bucketed_data)
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(this_batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(this_batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(this_batch_size, dtype=np.float32)
for batch_idx in xrange(this_batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
seq2seq_model.py 文件源码
项目：Seq2Seq-Tensorflow-1.0-Chatbot
作者: igorvishnevskiy
项目源码
文件源码
阅读 24
收藏 0
点赞 0
评论 0
def get_batch(self, data, bucket_id):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(data[bucket_id])
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
def get_batch(self, data, bucket_id):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(data[bucket_id])
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
#encoder_inputs?shape?(batch_size,encoder_size)
#batch_encoder_inputs?shape?(encoder_size,batch_size)
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
#????decoder????????target?pad,????????????????????
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight) #shape?(encoder_size,batch_size)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
def evaluate():
with open (os.path.join(FLAGS.data_dir, 'feature.test'), 'rb') as f:
feature = cPickle.load(f)
with open(os.path.join(FLAGS.data_dir, 'caption.test'), 'rb') as f:
sentence = cPickle.load(f)
with open (os.path.join(FLAGS.data_dir, 'video.length'), 'rb') as f:
length = cPickle.load(f)
scorers = [(Bleu(4), ["Bleu_1", "Bleu_2", "Bleu_3", "Bleu_4"]), (Meteor(),"METEOR"), (Rouge(), "ROUGE_L"), (Cider(), "CIDEr")]
vocab, re_vocab = data_utils.initialize_vocabulary()
GTS = {}
RES = {}
batch_size = 1
max_meteor = 0
with tf.Session() as sess:
model = Seq2Seq(FLAGS.num_units, FLAGS.use_lstm, FLAGS.encoder_max_sequence_length, 1, FLAGS.feature_size, FLAGS.vocab_size, FLAGS.learning_rate, FLAGS.learning_rate_decay_factor, FLAGS.max_gradient_norm, forward_only=True)
step = 0
while True:
step += FLAGS.steps_per_checkpoint
ckpt_path = os.path.join(FLAGS.checkpoint_dir,'ckpt-%d'%step)
if os.path.isfile(ckpt_path+'.meta'):
model.saver.restore(sess, ckpt_path)
cg = CaptionGenerator(model=model,start_id=data_utils.GO_ID,end_id=data_utils.EOS_ID, beam_size=3, max_caption_length=FLAGS.decoder_max_sentence_length, length_normalization_factor=0.0)
for vid, _ in feature.iteritems():
feature_inputs, feature_lengths, batch_decoder_inputs, batch_weights = model.get_batch(feature, [(vid, [0])], length)
sen = cg.beam_search(sess, feature_inputs, feature_lengths)
sen = " ".join([tf.compat.as_str(re_vocab[w]) for w in sen])
print ("%s: %s"%(sen, sentence[vid][9]))
GTS[vid] = sentence[vid]
RES[vid] = [sen]
print('STEP: %d'%step)
for scorer, method in scorers:
score, scores = scorer.compute_score(GTS, RES)
if method == "METEOR" and score > max_meteor:
max_meteor = score
if isinstance(method, list):
for k, v in zip(method, score):
print("%s:\t%f"%(k, v))
else:
print("%s:\t%f"%(method, score))
sys.stdout.flush()
else:
break
print("Max METEOR:\t%f"%max_meteor)
def evaluate():
with open (os.path.join(FLAGS.data_dir, 'feature.test'), 'rb') as f:
feature = cPickle.load(f)
with open(os.path.join(FLAGS.data_dir, 'caption.test'), 'rb') as f:
sentence = cPickle.load(f)
scorers = [(Bleu(4), ["Bleu_1", "Bleu_2", "Bleu_3", "Bleu_4"]), (Meteor(),"METEOR"), (Rouge(), "ROUGE_L"), (Cider(), "CIDEr")]
vocab, re_vocab = data_utils.initialize_vocabulary()
GTS = {}
RES = {}
batch_size = 1
max_meteor = 0
with tf.Session() as sess:
model = Seq2Seq(FLAGS.num_units, FLAGS.use_lstm, FLAGS.encoder_max_sequence_length, 1, FLAGS.feature_size, FLAGS.vocab_size, FLAGS.learning_rate, FLAGS.learning_rate_decay_factor, FLAGS.max_gradient_norm, forward_only=True)
step = 0
while True:
step += FLAGS.steps_per_checkpoint
ckpt_path = os.path.join(FLAGS.checkpoint_dir,'ckpt-%d'%step)
if os.path.isfile(ckpt_path+'.meta'):
model.saver.restore(sess, ckpt_path)
cg = CaptionGenerator(model=model,start_id=data_utils.GO_ID,end_id=data_utils.EOS_ID, beam_size=3, max_caption_length=FLAGS.decoder_max_sentence_length, length_normalization_factor=0.0)
for vid, _ in feature.iteritems():
feature_inputs, batch_decoder_inputs, batch_weights = model.get_batch(feature, [(vid, [0])])
sen = cg.beam_search(sess, feature_inputs)
sen = " ".join([tf.compat.as_str(re_vocab[w]) for w in sen])
print ("%s: %s"%(sen, sentence[vid][9]))
GTS[vid] = sentence[vid]
RES[vid] = [sen]
print('STEP: %d'%step)
for scorer, method in scorers:
score, scores = scorer.compute_score(GTS, RES)
if method == "METEOR" and score > max_meteor:
max_meteor = score
if isinstance(method, list):
for k, v in zip(method, score):
print("%s:\t%f"%(k, v))
else:
print("%s:\t%f"%(method, score))
sys.stdout.flush()
else:
break
print("Max METEOR:\t%f"%max_meteor)
gst_rnn_model.py 文件源码
项目：Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow
作者: liuyuemaicha
项目源码
文件源码
阅读 15
收藏 0
点赞 0
评论 0
def get_batch(self, train_data, bucket_id):
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
batch_source_encoder, batch_source_decoder = [], []
#print("bucket_id: ", bucket_id)
for batch_i in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(train_data[bucket_id])
batch_source_encoder.append(encoder_input)
batch_source_decoder.append(decoder_input)
#print("encoder_input: ", encoder_input)
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
#print("encoder_input pad: ", list(reversed(encoder_input + encoder_pad)))
#print("decoder_input: ", decoder_input)
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
#print("decoder_pad: ",[data_utils.GO_ID] + decoder_input + [data_utils.PAD_ID] * decoder_pad_size)
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights, batch_source_encoder, batch_source_decoder
grl_rnn_model.py 文件源码
项目：Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow
作者: liuyuemaicha
项目源码
文件源码
阅读 15
收藏 0
点赞 0
评论 0
def get_batch(self, train_data, bucket_id, type=0):
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# print("Batch_Size: %s" %self.batch_size)
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
batch_source_encoder, batch_source_decoder = [], []
# print("bucket_id: %s" %bucket_id)
for batch_i in xrange(self.batch_size):
if type == 1:
# feed_data = {bucket_id: zip(tokens_a, tokens_b)}
encoder_input, decoder_input = train_data[bucket_id][batch_i]
elif type == 2:
# feed_data = {bucket_id: [(resp_tokens, [])]}
encoder_input_a, decoder_input = train_data[bucket_id][0]
encoder_input = encoder_input_a[batch_i]
elif type == 0:
encoder_input, decoder_input = random.choice(train_data[bucket_id])
print("train en: %s, de: %s" % (encoder_input, decoder_input))
batch_source_encoder.append(encoder_input)
batch_source_decoder.append(decoder_input)
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights, batch_source_encoder, batch_source_decoder
def get_batch(self, data, bucket_id):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(data[bucket_id])
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
def get_batch(self, data, bucket_id):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(data[bucket_id])
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
def get_batch(self, data, bucket_id):
"""Get a random batch of data from the specified bucket, prepare for step.
To feed data in step(..) it must be a list of batch-major vectors, while
data here contains single length-major cases. So the main logic of this
function is to re-index data cases to be in the proper format for feeding.
Args:
data: a tuple of size len(self.buckets) in which each element contains
lists of pairs of input and output data that we use to create a batch.
bucket_id: integer, which bucket to get the batch for.
Returns:
The triple (encoder_inputs, decoder_inputs, target_weights) for
the constructed batch that has the proper format to call step(...) later.
"""
encoder_size, decoder_size = self.buckets[bucket_id]
encoder_inputs, decoder_inputs = [], []
# Get a random batch of encoder and decoder inputs from data,
# pad them if needed, reverse encoder inputs and add GO to decoder.
for _ in xrange(self.batch_size):
encoder_input, decoder_input = random.choice(data[bucket_id])
# Encoder inputs are padded and then reversed.
encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))
# Decoder inputs get an extra "GO" symbol, and are padded then.
decoder_pad_size = decoder_size - len(decoder_input) - 1
decoder_inputs.append([data_utils.GO_ID] + decoder_input +
[data_utils.PAD_ID] * decoder_pad_size)
# Now we create batch-major vectors from the data selected above.
batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []
# Batch encoder inputs are just re-indexed encoder_inputs.
for length_idx in xrange(encoder_size):
batch_encoder_inputs.append(
np.array([encoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Batch decoder inputs are re-indexed decoder_inputs, we create weights.
for length_idx in xrange(decoder_size):
batch_decoder_inputs.append(
np.array([decoder_inputs[batch_idx][length_idx]
for batch_idx in xrange(self.batch_size)], dtype=np.int32))
# Create target_weights to be 0 for targets that are padding.
batch_weight = np.ones(self.batch_size, dtype=np.float32)
for batch_idx in xrange(self.batch_size):
# We set weight to 0 if the corresponding target is a PAD symbol.
# The corresponding target is decoder_input shifted by 1 forward.
if length_idx < decoder_size - 1:
target = decoder_inputs[batch_idx][length_idx + 1]
if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
batch_weight[batch_idx] = 0.0
batch_weights.append(batch_weight)
return batch_encoder_inputs, batch_decoder_inputs, batch_weights
