def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
python类xw_plus_b()的实例源码
def _extract_argmax_and_one_hot(one_hot_size,
output_projection=None):
"""Get a loop_function that extracts the previous symbol and build a one-hot vector for it.
Args:
one_hot_size: total size of one-hot vector.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = tf.one_hot(prev_symbol, one_hot_size)
return emb_prev
return loop_function
def _argmax_or_mcsearch(embedding, output_projection=None, update_embedding=True, mc_search=False):
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(prev, output_projection[0], output_projection[1])
if isinstance(mc_search, bool):
#tf.multinomial???prev????????? ?-1??????????
prev_symbol = tf.reshape(tf.multinomial(prev, 1), [-1]) if mc_search else math_ops.argmax(prev, 1)
else:
prev_symbol = tf.cond(mc_search, lambda: tf.reshape(tf.multinomial(prev, 1), [-1]), lambda: tf.argmax(prev, 1))
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
#???????????
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None, update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1) #??????????
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol) #????????????
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def sequence_loss_by_mle(logits, targets, vocab_size, sequence_length, batch_size, output_projection=None):
#print("logits: ", np.shape(logits[0]))
#logits: [seq_len, batch_size, emb_dim]
#targets: [seq_len, batch_size] =====transpose====> [batch_size, seq_len]
# labels = tf.to_int32(tf.transpose(targets))
#targets: [seq_len, batch_size] ====reshape[-1]====> [seq_len * batch_size]
labels = tf.to_int32(tf.reshape(targets, [-1]))
if output_projection is not None:
#logits = nn_ops.xw_plus_b(logits, output_projection[0], output_projection[1])
logits = [tf.matmul(logit, output_projection[0]) + output_projection[1] for logit in logits]
reshape_logits = tf.reshape(logits, [-1, vocab_size]) #[seq_len * batch_size, vocab_size]
prediction = tf.clip_by_value(reshape_logits, 1e-20, 1.0)
pretrain_loss = -tf.reduce_sum(
# [seq_len * batch_size , vocab_size]
tf.one_hot(labels, vocab_size, 1.0, 0.0) * tf.log(prediction)
) / (sequence_length * batch_size)
return pretrain_loss
grl_seq2seq.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 27
收藏 0
点赞 0
评论 0
def _extract_argmax_and_embed(embedding, output_projection=None, update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_one_hot(one_hot_size,
output_projection=None):
"""Get a loop_function that extracts the previous symbol and build a one-hot vector for it.
Args:
one_hot_size: total size of one-hot vector.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = tf.one_hot(prev_symbol, one_hot_size)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding,
output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding,
output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None, update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def project_and_apply_input_bias(logits, output_projection, input_bias):
if output_projection is not None:
logits = nn_ops.xw_plus_b(
logits, output_projection[0], output_projection[1])
# Apply softmax to ensure all tokens have a positive value.
probs = tf.nn.softmax(logits)
# Apply input bias, which is a mask of shape [batch, vocab len]
# where each token from the input in addition to all "corrective"
# tokens are set to 1.0.
return tf.mul(probs, input_bias)
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
# decoder outputs thus far.
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev, prev_symbol
return loop_function
def _extract_argmax_and_embed(embedding,
output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
def _extract_argmax_and_embed(embedding, output_projection=None,
update_embedding=True):
"""Get a loop_function that extracts the previous symbol and embeds it.
Args:
embedding: embedding tensor for symbols.
output_projection: None or a pair (W, B). If provided, each fed previous
output will first be multiplied by W and added B.
update_embedding: Boolean; if False, the gradients will not propagate
through the embeddings.
Returns:
A loop function.
"""
def loop_function(prev, _):
if output_projection is not None:
prev = nn_ops.xw_plus_b(
prev, output_projection[0], output_projection[1])
prev_symbol = math_ops.argmax(prev, 1)
# Note that gradients will not propagate through the second parameter of
# embedding_lookup.
emb_prev = embedding_ops.embedding_lookup(embedding, prev_symbol)
if not update_embedding:
emb_prev = array_ops.stop_gradient(emb_prev)
return emb_prev
return loop_function
