Python tensorflow.erf() Examples
The following are 30
code examples of tensorflow.erf().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tensorflow
, or try the search function
.
.
Example #1
| Source File: expert_utils.py From NMT_GAN with Apache License 2.0 | 6 votes |
|
def _NormalDistributionCDF(x, stddev):
"""Evaluates the CDF of the normal distribution.
Normal distribution with mean 0 and standard deviation stddev,
evaluated at x=x.
input and output `Tensor`s have matching shapes.
Args:
x: a `Tensor`
stddev: a `Tensor` with the same shape as `x`.
Returns:
a `Tensor` with the same shape as `x`.
"""
return 0.5 * (1.0 + tf.erf(x / (math.sqrt(2) * stddev + 1e-20)))
Example #2
| Source File: rnn_controller.py From Searching-for-activation-functions with MIT License | 6 votes |
|
def __init__(self, config):
self.config = config
self.n_steps = 10
self.n_input, self.n_hidden = 4, 2
self.state = tf.Variable(tf.random_normal(shape=[1, 4]))
self.lstm = tf.contrib.rnn.BasicLSTMCell(self.n_hidden, forget_bias=1.0, state_is_tuple=False)
self.Wc, self.bc = self.init_controller_vars()
self.Wv, self.bv = self.init_value_vars()
# Other functions used in the paper
# self.full_list_unary = {1:lambda x:x ,2:lambda x: -x, 3: tf.abs, 4:lambda x : tf.pow(x,2),5:lambda x : tf.pow(x,3),
# 6:tf.sqrt,7:lambda x: tf.Variable(tf.truncated_normal([1], stddev=0.08))*x,
# 8:lambda x : x + tf.Variable(tf.truncated_normal([1], stddev=0.08)),9:lambda x: tf.log(tf.abs(x)+10e-8),
# 10:tf.exp,11:tf.sin,12:tf.sinh,13:tf.cosh,14:tf.tanh,15:tf.asinh,16:tf.atan,17:lambda x: tf.sin(x)/x,
# 18:lambda x : tf.maximum(x,0),19:lambda x : tf.minimum(x,0),20:tf.sigmoid,21:lambda x:tf.log(1+tf.exp(x)),
# 22:lambda x:tf.exp(-tf.pow(x,2)),23:tf.erf,24:lambda x: tf.Variable(tf.truncated_normal([1], stddev=0.08))}
#
# self.full_list_binary = {1:lambda x,y: x+y,2:lambda x,y:x*y,3:lambda x,y:x-y,4:lambda x,y:x/(y+10e-8),
# 5:lambda x,y:tf.maximum(x,y),6:lambda x,y: tf.sigmoid(x)*y,7:lambda x,y:tf.exp(-tf.Variable(tf.truncated_normal([1], stddev=0.08))*tf.pow(x-y,2)),
# 8:lambda x,y:tf.exp(-tf.Variable(tf.truncated_normal([1], stddev=0.08))*tf.abs(x-y)),
# 9:lambda x,y: tf.Variable(tf.truncated_normal([1], stddev=0.08))*x + (1-tf.Variable(tf.truncated_normal([1], stddev=0.08)))*y}
#
# self.unary = {1:lambda x:x ,2:lambda x: -x, 3: lambda x: tf.maximum(x,0), 4:lambda x : tf.pow(x,2),5:tf.tanh}
# binary = {1:lambda x,y: x+y,2:lambda x,y:x*y,3:lambda x,y:x-y,4:lambda x,y:tf.maximum(x,y),5:lambda x,y: tf.sigmoid(x)*y}
# inputs = {1:lambda x:x , 2:lambda x:0, 3: lambda x:3.14159265,4: lambda x : 1, 5: lambda x: 1.61803399}
Example #3
| Source File: test_forward.py From incubator-tvm with Apache License 2.0 | 6 votes |
|
def test_forward_unary():
def _test_forward_unary(op, a_min=1, a_max=5, dtype=np.float32):
"""test unary operators"""
np_data = np.random.uniform(a_min, a_max, size=(2, 3, 5)).astype(dtype)
tf.reset_default_graph()
with tf.Graph().as_default():
in_data = tf.placeholder(dtype, (2, 3, 5), name="in_data")
out = op(in_data)
compare_tf_with_tvm([np_data], ['in_data:0'], out.name)
_test_forward_unary(tf.acos, -1, 1)
_test_forward_unary(tf.asin, -1, 1)
_test_forward_unary(tf.atanh, -1, 1)
_test_forward_unary(tf.sinh)
_test_forward_unary(tf.cosh)
_test_forward_unary(tf.acosh)
_test_forward_unary(tf.asinh)
_test_forward_unary(tf.atan)
_test_forward_unary(tf.sin)
_test_forward_unary(tf.cos)
_test_forward_unary(tf.tan)
_test_forward_unary(tf.tanh)
_test_forward_unary(tf.erf)
_test_forward_unary(tf.log)
_test_forward_unary(tf.log1p)
Example #4
| Source File: expert_utils.py From fine-lm with MIT License | 6 votes |
|
def _normal_distribution_cdf(x, stddev):
"""Evaluates the CDF of the normal distribution.
Normal distribution with mean 0 and standard deviation stddev,
evaluated at x=x.
input and output `Tensor`s have matching shapes.
Args:
x: a `Tensor`
stddev: a `Tensor` with the same shape as `x`.
Returns:
a `Tensor` with the same shape as `x`.
"""
return 0.5 * (1.0 + tf.erf(x / (math.sqrt(2) * stddev + 1e-20)))
Example #5
| Source File: layers.py From variance-networks with Apache License 2.0 | 6 votes |
|
def fully_variance_dense(input_tensor, num_inputs, num_outputs, mean_initializer, name, stochastic=True, reuse=False):
with tf.variable_scope(name) as scope:
W = tf.get_variable('W', [num_inputs, num_outputs], initializer=mean_initializer, dtype=tf.float32,
trainable=False)
log_sigma2 = tf.get_variable('log_sigma2', [num_inputs, num_outputs],
initializer=tf.constant_initializer(-3.0),
dtype=tf.float32, trainable=True)
mu = tf.matmul(input_tensor, W)
si = tf.sqrt(tf.matmul(input_tensor * input_tensor, tf.exp(log_sigma2)) + 1e-16)
output = mu
if stochastic:
output += tf.random_normal(mu.shape, mean=0, stddev=1) * si
# summaries
if not reuse:
error = 0.5*(1.0+tf.erf((-mu)/tf.sqrt(2.0)/si))
tf.summary.scalar('error', tf.reduce_sum(error))
#tf.summary.histogram('log_sigma2', log_sigma2)
return output
Example #6
| Source File: expert_utils.py From BERT with Apache License 2.0 | 6 votes |
|
def _normal_distribution_cdf(x, stddev):
"""Evaluates the CDF of the normal distribution.
Normal distribution with mean 0 and standard deviation stddev,
evaluated at x=x.
input and output `Tensor`s have matching shapes.
Args:
x: a `Tensor`
stddev: a `Tensor` with the same shape as `x`.
Returns:
a `Tensor` with the same shape as `x`.
"""
return 0.5 * (1.0 + tf.erf(x / (math.sqrt(2) * stddev + 1e-20)))
Example #7
| Source File: expert_utils.py From training_results_v0.5 with Apache License 2.0 | 6 votes |
|
def _normal_distribution_cdf(x, stddev):
"""Evaluates the CDF of the normal distribution.
Normal distribution with mean 0 and standard deviation stddev,
evaluated at x=x.
input and output `Tensor`s have matching shapes.
Args:
x: a `Tensor`
stddev: a `Tensor` with the same shape as `x`.
Returns:
a `Tensor` with the same shape as `x`.
"""
return 0.5 * (1.0 + tf.erf(x / (math.sqrt(2) * stddev + 1e-20)))
Example #8
| Source File: expert_utils.py From training_results_v0.5 with Apache License 2.0 | 6 votes |
|
def _normal_distribution_cdf(x, stddev):
"""Evaluates the CDF of the normal distribution.
Normal distribution with mean 0 and standard deviation stddev,
evaluated at x=x.
input and output `Tensor`s have matching shapes.
Args:
x: a `Tensor`
stddev: a `Tensor` with the same shape as `x`.
Returns:
a `Tensor` with the same shape as `x`.
"""
return 0.5 * (1.0 + tf.erf(x / (math.sqrt(2) * stddev + 1e-20)))
Example #9
| Source File: activation.py From dpu-utils with MIT License | 6 votes |
|
def get_activation(activation_fun: Optional[str]) -> Optional[Callable]:
if activation_fun is None:
return None
activation_fun = activation_fun.lower()
if activation_fun == 'linear':
return None
if activation_fun == 'tanh':
return tf.tanh
if activation_fun == 'relu':
return tf.nn.relu
if activation_fun == 'leaky_relu':
return tf.nn.leaky_relu
if activation_fun == 'elu':
return tf.nn.elu
if activation_fun == 'selu':
return tf.nn.selu
if activation_fun == 'gelu':
def gelu(input_tensor):
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
return gelu
else:
raise ValueError("Unknown activation function '%s'!" % activation_fun)
Example #10
| Source File: __init__.py From clfzoo with MIT License | 6 votes |
|
def gelu(inputs, scope='gelu', reuse=None):
"""Gaussian Error Linear Unit.
This is a smoother version of the ReLU.
Paper: https://arxiv.org/abs/1606.08415
Args:
- inputs: float Tensor
- scope: scope name
- reuse: whether to reuse
Returns:
`inputs` with the gelu activation applied.
"""
with tf.variable_scope(scope, reuse=reuse):
alpha = 0.5 * (1.0 + tf.erf(inputs / tf.sqrt(2.0)))
return inputs * alpha
Example #11
| Source File: expert_utils.py From ASR with Apache License 2.0 | 6 votes |
|
def _NormalDistributionCDF(x, stddev):
"""Evaluates the CDF of the normal distribution.
Normal distribution with mean 0 and standard deviation stddev,
evaluated at x=x.
input and output `Tensor`s have matching shapes.
Args:
x: a `Tensor`
stddev: a `Tensor` with the same shape as `x`.
Returns:
a `Tensor` with the same shape as `x`.
"""
return 0.5 * (1.0 + tf.erf(x / (math.sqrt(2) * stddev + 1e-20)))
Example #12
| Source File: utils.py From tf-gnn-samples with MIT License | 6 votes |
|
def get_activation(activation_fun: Optional[str]):
if activation_fun is None:
return None
activation_fun = activation_fun.lower()
if activation_fun == 'linear':
return None
if activation_fun == 'tanh':
return tf.tanh
if activation_fun == 'relu':
return tf.nn.relu
if activation_fun == 'leaky_relu':
return tf.nn.leaky_relu
if activation_fun == 'elu':
return tf.nn.elu
if activation_fun == 'selu':
return tf.nn.selu
if activation_fun == 'gelu':
def gelu(input_tensor):
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
return gelu
else:
raise ValueError("Unknown activation function '%s'!" % activation_fun)
Example #13
| Source File: modules.py From pynlp with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #14
| Source File: modeling.py From pynlp with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #15
| Source File: modeling.py From pynlp with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #16
| Source File: modeling.py From dl4marco-bert with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #17
| Source File: modeling.py From bern with BSD 2-Clause "Simplified" License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #18
| Source File: bert_modeling.py From text_classification with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #19
| Source File: modeling.py From KBQA-BERT with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #20
| Source File: modeling.py From bert-qa with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #21
| Source File: modeling.py From uda with Apache License 2.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #22
| Source File: reading_comprehension_util.py From reading_comprehension_tf with Apache License 2.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #23
| Source File: modeling.py From text2vec with Apache License 2.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #24
| Source File: modeling.py From curriculum with GNU General Public License v3.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #25
| Source File: modeling.py From SIGIR19-BERT-IR with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #26
| Source File: modeling.py From r2c with MIT License | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #27
| Source File: modeling.py From bert-as-language-model with Apache License 2.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #28
| Source File: modeling.py From FASPell with GNU General Public License v3.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #29
| Source File: modeling.py From BERT-Classification-Tutorial with Apache License 2.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
Example #30
| Source File: modeling.py From BERT_STS-B with Apache License 2.0 | 5 votes |
|
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + tf.erf(input_tensor / tf.sqrt(2.0)))
return input_tensor * cdf
