Python tensorflow.contrib.cudnn_rnn.python.ops.cudnn_rnn_ops.CudnnLSTM() Examples
The following are 7
code examples of tensorflow.contrib.cudnn_rnn.python.ops.cudnn_rnn_ops.CudnnLSTM().
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.contrib.cudnn_rnn.python.ops.cudnn_rnn_ops
, or try the search function
.
.
Example #1
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
Example #2
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
Example #3
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
Example #4
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
Example #5
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
Example #6
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
Example #7
| Source File: cudnn_recurrent.py From DeepLearning_Wavelet-LSTM with MIT License | 4 votes |
|
def build(self, input_shape):
super(CuDNNLSTM, self).build(input_shape)
if isinstance(input_shape, list):
input_shape = input_shape[0]
input_dim = input_shape[-1]
from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
self._cudnn_lstm = cudnn_rnn_ops.CudnnLSTM(
num_layers=1,
num_units=self.units,
input_size=input_dim,
input_mode='linear_input')
self.kernel = self.add_weight(shape=(input_dim, self.units * 4),
name='kernel',
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint)
self.recurrent_kernel = self.add_weight(
shape=(self.units, self.units * 4),
name='recurrent_kernel',
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.unit_forget_bias:
def bias_initializer(shape, *args, **kwargs):
return K.concatenate([
self.bias_initializer((self.units * 5,), *args, **kwargs),
initializers.Ones()((self.units,), *args, **kwargs),
self.bias_initializer((self.units * 2,), *args, **kwargs),
])
else:
bias_initializer = self.bias_initializer
self.bias = self.add_weight(shape=(self.units * 8,),
name='bias',
initializer=bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
self.kernel_i = self.kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
self.bias_i_i = self.bias[:self.units]
self.bias_f_i = self.bias[self.units: self.units * 2]
self.bias_c_i = self.bias[self.units * 2: self.units * 3]
self.bias_o_i = self.bias[self.units * 3: self.units * 4]
self.bias_i = self.bias[self.units * 4: self.units * 5]
self.bias_f = self.bias[self.units * 5: self.units * 6]
self.bias_c = self.bias[self.units * 6: self.units * 7]
self.bias_o = self.bias[self.units * 7:]
self.built = True
