本文整理汇总了Python中chainer.functions.log方法的典型用法代码示例。如果您正苦于以下问题:Python functions.log方法的具体用法?Python functions.log怎么用?Python functions.log使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类chainer.functions
的用法示例。
在下文中一共展示了functions.log方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _compute_loss
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def _compute_loss(self, exp_batch, errors_out=None):
"""Compute a loss of categorical DQN."""
y, t = self._compute_y_and_t(exp_batch)
# Minimize the cross entropy
# y is clipped to avoid log(0)
eltwise_loss = -t * F.log(F.clip(y, 1e-10, 1.))
if errors_out is not None:
del errors_out[:]
# The loss per example is the sum of the atom-wise loss
# Prioritization by KL-divergence
delta = F.sum(eltwise_loss, axis=1)
delta = cuda.to_cpu(delta.array)
for e in delta:
errors_out.append(e)
if 'weights' in exp_batch:
return compute_weighted_value_loss(
eltwise_loss, y.shape[0], exp_batch['weights'],
batch_accumulator=self.batch_accumulator)
else:
return compute_value_loss(
eltwise_loss, batch_accumulator=self.batch_accumulator)
示例2: __init__
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def __init__(self, Vi, Ei, Hi, Vo, Eo, Ho, Ha, Hl, attn_cls=attention.AttentionModule, init_orth=False, use_bn_length=0,
encoder_cell_type=rnn_cells.LSTMCell,
decoder_cell_type=rnn_cells.LSTMCell,
lexical_probability_dictionary=None, lex_epsilon=1e-3,
use_goto_attention=False
):
log.info("constructing encoder decoder with Vi:%i Ei:%i Hi:%i Vo:%i Eo:%i Ho:%i Ha:%i Hl:%i" %
(Vi, Ei, Hi, Vo, Eo, Ho, Ha, Hl))
super(EncoderDecoder, self).__init__(
enc=encoders.make_encoder(Vi, Ei, Hi, init_orth=init_orth, use_bn_length=use_bn_length,
cell_type=encoder_cell_type),
dec=decoder_cells.Decoder(Vo, Eo, Ho, Ha, 2 * Hi, Hl, attn_cls=attn_cls, init_orth=init_orth,
cell_type=decoder_cell_type, use_goto_attention=use_goto_attention)
)
self.Vo = Vo
self.lexical_probability_dictionary = lexical_probability_dictionary
self.lex_epsilon = lex_epsilon
示例3: get_gaussian_params
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def get_gaussian_params(self, x):
h = F.tanh(self.l1(x))
h = self.l2(h)
pi = h[:, :self.gaussian_mixtures]
mu_var_dim = self.gaussian_mixtures * self.input_dim
mu = h[:, self.gaussian_mixtures:self.gaussian_mixtures + mu_var_dim]
log_var = h[:, self.gaussian_mixtures + mu_var_dim:]
n_batch = x.shape[0]
# mixing coefficients
pi = F.reshape(pi, (n_batch, self.gaussian_mixtures))
pi = F.softmax(pi, axis=1)
# mean
mu = F.reshape(mu, (n_batch, self.gaussian_mixtures, self.input_dim))
# log variance
log_var = F.reshape(
log_var, (n_batch, self.gaussian_mixtures, self.input_dim))
return pi, mu, log_var
示例4: sample_discrete_actions
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def sample_discrete_actions(batch_probs):
"""Sample a batch of actions from a batch of action probabilities.
Args:
batch_probs (ndarray): batch of action probabilities BxA
Returns:
ndarray consisting of sampled action indices
"""
xp = chainer.cuda.get_array_module(batch_probs)
return xp.argmax(
xp.log(batch_probs) + xp.random.gumbel(size=batch_probs.shape),
axis=1).astype(np.int32, copy=False)
示例5: log_prob
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def log_prob(self, x):
"""Compute log p(x).
Returns:
chainer.Variable
"""
raise NotImplementedError()
示例6: all_log_prob
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def all_log_prob(self):
with chainer.force_backprop_mode():
if self.min_prob > 0:
return F.log(self.all_prob)
else:
return F.log_softmax(self.beta * self.logits)
示例7: _eltwise_gaussian_log_likelihood
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def _eltwise_gaussian_log_likelihood(x, mean, var, ln_var):
# log N(x|mean,var)
# = -0.5log(2pi) - 0.5log(var) - (x - mean)**2 / (2*var)
return -0.5 * np.log(2 * np.pi) - \
0.5 * ln_var - \
((x - mean) ** 2) / (2 * var)
示例8: entropy
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def entropy(self):
# Differential entropy of Gaussian is:
# 0.5 * (log(2 * pi * var) + 1)
# = 0.5 * (log(2 * pi) + log var + 1)
with chainer.force_backprop_mode():
return 0.5 * self.mean.array.shape[1] * (np.log(2 * np.pi) + 1) + \
0.5 * F.sum(self.ln_var, axis=1)
示例9: _tanh_forward_log_det_jacobian
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def _tanh_forward_log_det_jacobian(x):
"""Compute log|det(dy/dx)| except summation where y=tanh(x)."""
# For the derivation of this formula, see:
# https://github.com/tensorflow/probability/blob/master/tensorflow_probability/python/bijectors/tanh.py # NOQA
return 2. * (np.log(2.) - x - F.softplus(-2. * x))
示例10: __init__
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def __init__(self, mean, var):
self.mean = _wrap_by_variable(mean)
self.var = _wrap_by_variable(var)
self.ln_var = F.log(var)
示例11: initialize_embeddings
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def initialize_embeddings(self, src_emb=None, tgt_emb=None, no_unk_src=False, no_unk_tgt=False):
if src_emb is None and tgt_emb is None:
log.warn("called initialize_embeddings with 2 None args")
if src_emb is not None:
self.enc.initialize_embeddings(src_emb, no_unk=no_unk_src)
if tgt_emb is not None:
self.dec.initialize_embeddings(tgt_emb, no_unk=no_unk_tgt)
示例12: compute_logits
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def compute_logits(self, new_states, concatenated, attn):
new_output_state = new_states[-1]
all_concatenated = F.concat((concatenated, new_output_state))
logits = self.decoder_chain.lin_o(self.decoder_chain.maxo(all_concatenated))
if self.lexicon_probability_matrix is not None:
current_mb_size = new_output_state.data.shape[0]
assert self.mb_size is None or current_mb_size <= self.mb_size
lexicon_probability_matrix = self.lexicon_probability_matrix[:current_mb_size]
# Just making sure data shape is as expected
attn_mb_size, max_source_length_attn = attn.data.shape
assert attn_mb_size == current_mb_size
lex_mb_size, max_source_length_lexicon, v_size_lexicon = lexicon_probability_matrix.shape
assert max_source_length_lexicon == max_source_length_attn
assert logits.data.shape == (current_mb_size, v_size_lexicon)
if self.demux:
assert lex_mb_size == 1
weighted_lex_probs = F.reshape(
matmul_constant(attn, lexicon_probability_matrix.reshape(lexicon_probability_matrix.shape[1],
lexicon_probability_matrix.shape[2])),
logits.data.shape)
else:
assert lex_mb_size == current_mb_size
# weighted_lex_probs = F.reshape(
# F.batch_matmul(attn, ConstantFunction(lexicon_probability_matrix)(), transa = True),
# logits.data.shape)
weighted_lex_probs = F.reshape(
batch_matmul_constant(attn, lexicon_probability_matrix, transa=True),
logits.data.shape)
logits += F.log(weighted_lex_probs + self.lex_epsilon)
return logits
示例13: forward
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def forward(self, x):
y1 = F.log(x)
return y1
示例14: main
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def main():
np.random.seed(314)
x = np.random.rand(6, 4).astype(np.float32)
s_int = np.array(-10)
s_float = np.array(10.0)
testtools.generate_testcase(Sin(), [x], subname='sin')
testtools.generate_testcase(Sinh(), [x], subname='sinh')
testtools.generate_testcase(Sign(), [x], subname='sign')
testtools.generate_testcase(Cos(), [x], subname='cos')
testtools.generate_testcase(Cosh(), [x], subname='cosh')
testtools.generate_testcase(Tan(), [x], subname='tan')
testtools.generate_testcase(Tanh(), [x], subname='tanh')
testtools.generate_testcase(ArcSin(), [x], subname='arcsin')
testtools.generate_testcase(ArcCos(), [x], subname='arccos')
testtools.generate_testcase(ArcTan(), [x], subname='arctan')
testtools.generate_testcase(Exp(), [x], subname='exp')
testtools.generate_testcase(Log(), [x], subname='log')
testtools.generate_testcase(Clip(), [x], subname='clip')
testtools.generate_testcase(ClipNp(), [x], subname='clip_np')
testtools.generate_testcase(Abs(), [x], subname='abs')
testtools.generate_testcase(AbsNp(), [x], subname='abs_np')
testtools.generate_testcase(Sqrt(), [x], subname='sqrt')
testtools.generate_testcase(Round(), [x], subname='round')
testtools.generate_testcase(AbsBuiltin(), [x], subname='abs_builtin')
testtools.generate_testcase(AbsBuiltin(), [s_float], subname='abs_builtin_scalar_float')
testtools.generate_testcase(AbsBuiltin(), [s_int], subname='abs_builtin_scalar_int')
示例15: listnet
# 需要导入模块: from chainer import functions [as 别名]
# 或者: from chainer.functions import log [as 别名]
def listnet(x, t):
"""
The Top-1 approximated ListNet loss as in Cao et al (2006), Learning to
Rank: From Pairwise Approach to Listwise Approach
:param x: The activation of the previous layer
:param t: The target labels
:return: The loss
"""
# ListNet top-1 reduces to a softmax and simple cross entropy
st = F.softmax(t, axis=0)
sx = F.softmax(x, axis=0)
return -F.mean(st * F.log(sx))