本文整理匯總了Python中modeling.create_initializer方法的典型用法代碼示例。如果您正苦於以下問題：Python modeling.create_initializer方法的具體用法？Python modeling.create_initializer怎麽用？Python modeling.create_initializer使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類modeling的用法示例。
在下文中一共展示了modeling.create_initializer方法的5個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: get_next_sentence_output
# 需要導入模塊: import modeling [as 別名]
# 或者: from modeling import create_initializer [as 別名]
def get_next_sentence_output(bert_config, input_tensor, labels):
"""Get loss and log probs for the next sentence prediction."""
# Simple binary classification. Note that 0 is "next sentence" and 1 is
# "random sentence". This weight matrix is not used after pre-training.
with tf.variable_scope("cls/seq_relationship"):
output_weights = tf.get_variable(
"output_weights",
shape=[2, bert_config.hidden_size],
initializer=modeling.create_initializer(bert_config.initializer_range))
output_bias = tf.get_variable(
"output_bias", shape=[2], initializer=tf.zeros_initializer())
logits = tf.matmul(input_tensor, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
log_probs = tf.nn.log_softmax(logits, axis=-1)
labels = tf.reshape(labels, [-1])
one_hot_labels = tf.one_hot(labels, depth=2, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(per_example_loss)
return (loss, per_example_loss, log_probs) 開發者ID:Nagakiran1，項目名稱:Extending-Google-BERT-as-Question-and-Answering-model-and-Chatbot，代碼行數:23，代碼來源:run_pretraining.py
示例2: get_next_sentence_output
# 需要導入模塊: import modeling [as 別名]
# 或者: from modeling import create_initializer [as 別名]
def get_next_sentence_output(bert_config, input_tensor, labels):
"""Get loss and log probs for the next sentence prediction."""
# Simple binary classification. Note that 0 is "next sentence" and 1 is
# "random sentence". This weight matrix is not used after pre-training.
with tf.compat.v1.variable_scope("cls/seq_relationship"):
output_weights = tf.compat.v1.get_variable(
"output_weights",
shape=[2, bert_config.hidden_size],
initializer=modeling.create_initializer(bert_config.initializer_range))
output_bias = tf.compat.v1.get_variable(
"output_bias", shape=[2], initializer=tf.compat.v1.zeros_initializer())
logits = bf.matmul(input_tensor, output_weights, transpose_b=True)
logits = bf.i_cast(logits)
logits = tf.nn.bias_add(logits, output_bias)
log_probs = tf.nn.log_softmax(logits, axis=-1)
labels = tf.reshape(labels, [-1])
one_hot_labels = tf.one_hot(labels, depth=2, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(input_tensor=one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(input_tensor=per_example_loss)
return (loss, per_example_loss, log_probs) 示例3: get_next_sentence_output
# 需要導入模塊: import modeling [as 別名]
# 或者: from modeling import create_initializer [as 別名]
def get_next_sentence_output(bert_config, input_tensor, labels):
"""Get loss and log probs for the next sentence prediction."""
# Simple binary classification. Note that 0 is "next sentence" and 1 is
# "random sentence". This weight matrix is not used after pre-training.
with tf.compat.v1.variable_scope("cls/seq_relationship"):
output_weights = tf.compat.v1.get_variable(
"output_weights",
shape=[2, bert_config.hidden_size],
initializer=modeling.create_initializer(bert_config.initializer_range))
output_bias = tf.compat.v1.get_variable(
"output_bias", shape=[2], initializer=tf.compat.v1.zeros_initializer())
input_tensor = bf.i_cast(input_tensor)
output_weights = bf.i_cast(output_weights)
logits = tf.matmul(input_tensor, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
log_probs = tf.nn.log_softmax(logits, axis=-1)
labels = tf.reshape(labels, [-1])
one_hot_labels = tf.one_hot(labels, depth=2, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(input_tensor=one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(input_tensor=per_example_loss)
return (loss, per_example_loss, log_probs) 示例4: get_next_sentence_output
# 需要導入模塊: import modeling [as 別名]
# 或者: from modeling import create_initializer [as 別名]
def get_next_sentence_output(bert_config, input_tensor, labels):
"""Get loss and log probs for the next sentence prediction."""
# Simple binary classification. Note that 0 is "next sentence" and 1 is
# "random sentence". This weight matrix is not used after pre-training.
with tf.variable_scope("cls/seq_relationship"):
output_weights = tf.get_variable(
"output_weights",
shape=[2, bert_config.hidden_size],
initializer=modeling.create_initializer(
bert_config.initializer_range))
output_bias = tf.get_variable(
"output_bias", shape=[2], initializer=tf.zeros_initializer())
logits = tf.matmul(input_tensor, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
log_probs = tf.nn.log_softmax(logits, axis=-1)
labels = tf.reshape(labels, [-1])
one_hot_labels = tf.one_hot(labels, depth=2, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(per_example_loss)
return (loss, per_example_loss, log_probs) 示例5: get_next_sentence_output
# 需要導入模塊: import modeling [as 別名]
# 或者: from modeling import create_initializer [as 別名]
def get_next_sentence_output(bert_config, input_tensor, labels):
"""Get loss and log probs for the next sentence prediction."""
# Simple binary classification. Note that 0 is "next sentence" and 1 is
# "random sentence". This weight matrix is not used after pre-training.
with tf.variable_scope("cls/seq_relationship"):
output_weights = tf.get_variable(
"output_weights",
shape=[2, bert_config.hidden_size],
initializer=modeling.create_initializer(bert_config.initializer_range))
output_bias = tf.get_variable(
"output_bias", shape=[2], initializer=tf.zeros_initializer())
logits = tf.matmul(input_tensor, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
log_probs = tf.nn.log_softmax(logits, axis=-1)
labels = tf.reshape(labels, [-1])
one_hot_labels = tf.one_hot(labels, depth=2, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(per_example_loss)
return (loss, per_example_loss, log_probs)