a214f4e64d9e1f09a6ffdcad5e9595d0534e08f0,keras/layers/recurrent.py,LSTM,build,#LSTM#Any#,880
Before Change
self.recurrent_dropout = min(1., max(0., recurrent_dropout))
def build(self, input_shape):
self.input_spec = InputSpec(shape=input_shape)
self.input_dim = input_shape[2]
if self.stateful:
self.reset_states()
else:
// initial states: 2 all-zero tensors of shape (output_dim)
self.states = [None, None]
self.kernel = self.add_weight((self.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(
(self.units, self.units * 4),
name="recurrent_kernel",
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.use_bias:
self.bias = self.add_weight((self.units * 4,),
name="bias",
initializer=self.bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
if self.unit_forget_bias:
self.bias += K.concatenate([K.zeros((self.units,)),
K.ones((self.units,)),
K.zeros((self.units * 2,))])
else:
self.bias = None
self.kernel_i = self.kernel[:, :self.units]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
if self.use_bias:
After Change
self.recurrent_dropout = min(1., max(0., recurrent_dropout))
def build(self, input_shape):
if isinstance(input_shape, list):
input_shape = input_shape[0]
self.input_dim = input_shape[2]
if self.stateful:
self.reset_states()
else:
// initial states: 2 all-zero tensors of shape (output_dim)
self.states = [None, None]
self.kernel = self.add_weight((self.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(
(self.units, self.units * 4),
name="recurrent_kernel",
initializer=self.recurrent_initializer,
regularizer=self.recurrent_regularizer,
constraint=self.recurrent_constraint)
if self.use_bias:
self.bias = self.add_weight((self.units * 4,),
name="bias",
initializer=self.bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint)
if self.unit_forget_bias:
self.bias += K.concatenate([K.zeros((self.units,)),
K.ones((self.units,)),
K.zeros((self.units * 2,))])
else:
self.bias = None
self.kernel_i = self.kernel[:, :self.units]
self.recurrent_kernel_i = self.recurrent_kernel[:, :self.units]
self.kernel_f = self.kernel[:, self.units: self.units * 2]
self.recurrent_kernel_f = self.recurrent_kernel[:, self.units: self.units * 2]
self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
self.recurrent_kernel_c = self.recurrent_kernel[:, self.units * 2: self.units * 3]
self.kernel_o = self.kernel[:, self.units * 3:]
self.recurrent_kernel_o = self.recurrent_kernel[:, self.units * 3:]
if self.use_bias:
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 13
Instances
Project Name: keras-team/keras
Commit Name: a214f4e64d9e1f09a6ffdcad5e9595d0534e08f0
Time: 2017-03-03
Author: joshuarchin@gmail.com
File Name: keras/layers/recurrent.py
Class Name: LSTM
Method Name: build
Project Name: keras-team/keras
Commit Name: a214f4e64d9e1f09a6ffdcad5e9595d0534e08f0
Time: 2017-03-03
Author: joshuarchin@gmail.com
File Name: keras/layers/recurrent.py
Class Name: GRU
Method Name: build
Project Name: keras-team/keras
Commit Name: a214f4e64d9e1f09a6ffdcad5e9595d0534e08f0
Time: 2017-03-03
Author: joshuarchin@gmail.com
File Name: keras/layers/recurrent.py
Class Name: SimpleRNN
Method Name: build
Project Name: keras-team/keras
Commit Name: a214f4e64d9e1f09a6ffdcad5e9595d0534e08f0
Time: 2017-03-03
Author: joshuarchin@gmail.com
File Name: keras/layers/recurrent.py
Class Name: LSTM
Method Name: build