def __init__(self, nb_filter, nb_row, nb_col, transform_bias=-1,
init='glorot_uniform', activation='relu', weights=None,
border_mode='same', subsample=(1, 1), dim_ordering='th',
W_regularizer=None, b_regularizer=None, activity_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
if border_mode not in {'valid', 'same'}:
raise Exception('Invalid border mode for Convolution2D:', border_mode)
self.nb_filter = nb_filter
self.nb_row = nb_row
self.nb_col = nb_col
self.transform_bias = transform_bias
self.init = initializations.get(init, dim_ordering=dim_ordering)
self.activation = activations.get(activation)
assert border_mode in {'valid', 'same'}, 'border_mode must be in {valid, same}'
self.border_mode = border_mode
self.subsample = tuple(subsample)
assert dim_ordering in {'tf', 'th'}, 'dim_ordering must be in {tf, th}'
self.dim_ordering = dim_ordering
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.input_spec = [InputSpec(ndim=4)]
self.initial_weights = weights
super(Conv2DHighway, self).__init__(**kwargs)
python类get()的实例源码
def __init__(self, output_dim,
init = 'glorot_uniform', inner_init = 'orthogonal',
activation = 'tanh', W_regularizer = None,
U_regularizer = None, b_regularizer = None,
dropout_W = 0.0, dropout_U = 0.0,
tau=100, dt=20, noise=.1,
dale_ratio = None, **kwargs):
self.output_dim = output_dim
self.init = initializations.get(init)
self.inner_init = initializations.get(inner_init)
self.activation = activations.get(activation)
self.W_regularizer = regularizers.get(W_regularizer)
self.U_regularizer = regularizers.get(U_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.dropout_W, self.dropout_U = dropout_W, dropout_U
self.tau = tau
self.dt = dt
self.noise = noise
self.dale_ratio = dale_ratio
if dale_ratio:
#make dales law matrix
dale_vec = np.ones(output_dim)
dale_vec[int(dale_ratio*output_dim):] = -1
dale = np.diag(dale_vec)
self.Dale = K.variable(dale)
if self.dropout_W or self.dropout_U:
self.uses_learning_phase = True
super(leak_recurrent, self).__init__(**kwargs)
def __init__(self, output_dim, init='glorot_uniform',
activation='linear', weights=None,
W_regularizer=None, b_regularizer=None, activity_regularizer=None,
W_constraint=None, b_constraint=None,
bias=False, input_dim=None, dale_ratio = .8, **kwargs):
self.init = initializations.get(init)
self.activation = activations.get(activation)
self.output_dim = output_dim
self.input_dim = input_dim
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.initial_weights = weights
self.input_spec = [InputSpec(ndim=2)]
# OUR CHANGE
self.dale_ratio = dale_ratio
if dale_ratio:
dale_vec = np.ones((input_dim, 1))
dale_vec[int(dale_ratio*input_dim):, 0] = 0
self.Dale = K.variable(dale_vec)
if self.input_dim:
kwargs['input_shape'] = (self.input_dim,)
super(Dense, self).__init__(**kwargs)
def __init__(self,
init='glorot_uniform',
activation=None,
weights=None,
W_regularizer=None,
b_regularizer=None,
activity_regularizer=None,
W_constraint=None,
b_constraint=None,
bias=True,
input_dim=None,
**kwargs):
self.init = initializers.get(init)
self.activation = activations.get(activation)
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.initial_weights = weights
self.input_spec = InputSpec(ndim=2)
self.input_dim = input_dim
if self.input_dim:
kwargs['input_shape'] = (self.input_dim,)
super(Highway, self).__init__(**kwargs)
def __init__(self, nb_filter, nb_row, nb_col, rate=2,
init='glorot_uniform', activation='linear', weights=None,
border_mode='valid', dim_ordering=K.image_dim_ordering(),
W_regularizer=None, b_regularizer=None, activity_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
if K._BACKEND != 'tensorflow':
raise Exception('TensorBoard callback only works '
'with the TensorFlow backend.')
if border_mode not in {'valid', 'same'}:
raise Exception('Invalid border mode for Convolution2D:', border_mode)
self.nb_filter = nb_filter
self.nb_row = nb_row
self.nb_col = nb_col
self.rate = rate
self.init = initializations.get(init, dim_ordering=dim_ordering)
self.activation = activations.get(activation)
assert border_mode in {'valid', 'same'}, 'border_mode must be in {valid, same}'
self.border_mode = border_mode
assert dim_ordering in {'tf', 'th'}, 'dim_ordering must be in {tf, th}'
self.dim_ordering = dim_ordering
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.input_spec = [InputSpec(ndim=4)]
self.initial_weights = weights
super(ATrousConvolution2D, self).__init__(**kwargs)
def __init__(self, nb_filter, nb_row, nb_col,
init='glorot_uniform', activation='linear', weights=None,
border_mode='valid', subsample=(1, 1), dim_ordering=K.image_dim_ordering(),
W_regularizer=None, b_regularizer=None, activity_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
if border_mode not in {'valid', 'same'}:
raise Exception('Invalid border mode for Convolution2D:', border_mode)
self.nb_filter = nb_filter
self.nb_row = nb_row
self.nb_col = nb_col
self.dim_ordering = dim_ordering
self.init = initializations.get(init, dim_ordering=self.dim_ordering)
self.activation = activations.get(activation)
assert border_mode in {'valid', 'same'}, 'border_mode must be in {valid, same}'
self.border_mode = border_mode
self.subsample = tuple(subsample)
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.input_spec = [InputSpec(ndim=4)]
self.initial_weights = weights
super(ConvolutionTranspose2D, self).__init__(**kwargs)
def __init__(self,
kernel_initializer=initializers.Constant(1.0),
kernel_regularizer=None,
kernel_constraint=None,
bias_initializer='zeros',
bias_regularizer=None,
bias_constraint=None,
**kwargs):
super(Scale, self).__init__(**kwargs)
self.kernel_initializer = initializers.get(kernel_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.bias_initializer = initializers.get(bias_initializer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.bias_constraint = constraints.get(bias_constraint)
def __init__(self, step_dim,
W_regularizer=None, b_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
"""
Keras Layer that implements an Attention mechanism for temporal data.
Supports Masking.
Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
# Input shape
3D tensor with shape: `(samples, steps, features)`.
# Output shape
2D tensor with shape: `(samples, features)`.
:param kwargs:
Just put it on top of an RNN Layer (GRU/LSTM/SimpleRNN) with return_sequences=True.
The dimensions are inferred based on the output shape of the RNN.
Example:
model.add(LSTM(64, return_sequences=True))
model.add(Attention(step_dim))
"""
self.supports_masking = True
# self.init = initializations.get('glorot_uniform')
self.init = initializers.get('glorot_uniform')
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.step_dim = step_dim
self.features_dim = 0
super(Attention, self).__init__(**kwargs)
mf_lstm_att_sia_self.py 文件源码
项目：kaggle-quora-solution-8th
作者: qqgeogor
项目源码
文件源码
阅读 15
收藏 0
点赞 0
评论 0
def __init__(self, step_dim,
W_regularizer=None, b_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
"""
Keras Layer that implements an Attention mechanism for temporal data.
Supports Masking.
Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
# Input shape
3D tensor with shape: `(samples, steps, features)`.
# Output shape
2D tensor with shape: `(samples, features)`.
:param kwargs:
Just put it on top of an RNN Layer (GRU/LSTM/SimpleRNN) with return_sequences=True.
The dimensions are inferred based on the output shape of the RNN.
Example:
model.add(LSTM(64, return_sequences=True))
model.add(Attention())
"""
self.supports_masking = True
#self.init = initializations.get('glorot_uniform')
self.init = initializers.get('glorot_uniform')
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.step_dim = step_dim
self.features_dim = 0
super(Attention, self).__init__(**kwargs)
mf_lstm_att_siamese.py 文件源码
项目：kaggle-quora-solution-8th
作者: qqgeogor
项目源码
文件源码
阅读 14
收藏 0
点赞 0
评论 0
def __init__(self, step_dim,
W_regularizer=None, b_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
"""
Keras Layer that implements an Attention mechanism for temporal data.
Supports Masking.
Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
# Input shape
3D tensor with shape: `(samples, steps, features)`.
# Output shape
2D tensor with shape: `(samples, features)`.
:param kwargs:
Just put it on top of an RNN Layer (GRU/LSTM/SimpleRNN) with return_sequences=True.
The dimensions are inferred based on the output shape of the RNN.
Example:
model.add(LSTM(64, return_sequences=True))
model.add(Attention())
"""
self.supports_masking = True
#self.init = initializations.get('glorot_uniform')
self.init = initializers.get('glorot_uniform')
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.step_dim = step_dim
self.features_dim = 0
super(Attention, self).__init__(**kwargs)
def __init__(self, step_dim,
W_regularizer=None, b_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
"""
Keras Layer that implements an Attention mechanism for temporal data.
Supports Masking.
Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
# Input shape
3D tensor with shape: `(samples, steps, features)`.
# Output shape
2D tensor with shape: `(samples, features)`.
:param kwargs:
Just put it on top of an RNN Layer (GRU/LSTM/SimpleRNN) with return_sequences=True.
The dimensions are inferred based on the output shape of the RNN.
Example:
model.add(LSTM(64, return_sequences=True))
model.add(Attention())
"""
self.supports_masking = True
#self.init = initializations.get('glorot_uniform')
self.init = initializers.get('glorot_uniform')
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.step_dim = step_dim
self.features_dim = 0
super(Attention, self).__init__(**kwargs)
def __init__(self,
init='glorot_uniform',
activation=None,
weights=None,
W_regularizer=None,
b_regularizer=None,
activity_regularizer=None,
W_constraint=None,
b_constraint=None,
bias=True,
input_dim=None,
**kwargs):
self.init = initializers.get(init)
self.activation = activations.get(activation)
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.initial_weights = weights
self.input_spec = InputSpec(ndim=2)
self.input_dim = input_dim
if self.input_dim:
kwargs['input_shape'] = (self.input_dim,)
super(Highway, self).__init__(**kwargs)
def __init__(self, units=None,
activation='tanh',
recurrent_activation='hard_sigmoid',
use_bias=True,
kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal',
bias_initializer='zeros',
kernel_regularizer=None,
recurrent_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
recurrent_constraint=None,
bias_constraint=None,
**kwargs):
if units is None:
assert 'output_dim' in kwargs, 'Missing argument: units'
else:
kwargs['output_dim'] = units
self.activation = activations.get(activation)
self.recurrent_activation = activations.get(recurrent_activation)
self.use_bias = use_bias
self.kernel_initializer = initializers.get(kernel_initializer)
self.recurrent_initializer = initializers.get(recurrent_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.recurrent_regularizer = regularizers.get(recurrent_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.recurrent_constraint = constraints.get(recurrent_constraint)
self.bias_constraint = constraints.get(bias_constraint)
super(ExtendedRNNCell, self).__init__(**kwargs)
def __init__(self,
kernel_size,
strides=(1, 1),
padding='valid',
depth_multiplier=1,
data_format=None,
activation=None,
use_bias=True,
depthwise_initializer='glorot_uniform',
bias_initializer='zeros',
depthwise_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
depthwise_constraint=None,
bias_constraint=None, **kwargs):
super(DepthwiseConv2D, self).__init__(
filters=None,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
activation=activation,
use_bias=use_bias,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
bias_constraint=bias_constraint,
**kwargs)
self.depth_multiplier = depth_multiplier
self.depthwise_initializer = initializers.get(depthwise_initializer)
self.depthwise_regularizer = regularizers.get(depthwise_regularizer)
self.depthwise_constraint = constraints.get(depthwise_constraint)
self.bias_initializer = initializers.get(bias_initializer)
multiplicative_lstm.py 文件源码
项目：Keras-Multiplicative-LSTM
作者: titu1994
项目源码
文件源码
阅读 17
收藏 0
点赞 0
评论 0
def __init__(self, units,
activation='tanh',
recurrent_activation='hard_sigmoid',
use_bias=True,
kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal',
bias_initializer='zeros',
unit_forget_bias=True,
kernel_regularizer=None,
recurrent_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
recurrent_constraint=None,
bias_constraint=None,
dropout=0.,
recurrent_dropout=0.,
implementation=1,
**kwargs):
super(MultiplicativeLSTM, self).__init__(**kwargs)
self.units = units
self.activation = activations.get(activation)
self.recurrent_activation = activations.get(recurrent_activation)
self.use_bias = use_bias
self.kernel_initializer = initializers.get(kernel_initializer)
self.recurrent_initializer = initializers.get(recurrent_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.unit_forget_bias = unit_forget_bias
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.recurrent_regularizer = regularizers.get(recurrent_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.recurrent_constraint = constraints.get(recurrent_constraint)
self.bias_constraint = constraints.get(bias_constraint)
self.dropout = min(1., max(0., dropout))
self.recurrent_dropout = min(1., max(0., recurrent_dropout))
self.state_spec = [InputSpec(shape=(None, self.units)),
InputSpec(shape=(None, self.units))]
self.state_size = (self.units, self.units)
self.implementation = implementation
def __init__(self,
kernel_initializer='he_normal',
kernel_regularizer=None,
kernel_constraint=None,
use_bias=True,
bias_initializer='zeros',
bias_regularizer=None,
bias_constraint=None,
use_context=True,
context_initializer='he_normal',
context_regularizer=None,
context_constraint=None,
attention_dims=None,
**kwargs):
"""
Args:
attention_dims: The dimensionality of the inner attention calculating neural network.
For input `(32, 10, 300)`, with `attention_dims` of 100, the output is `(32, 10, 100)`.
i.e., the attended words are 100 dimensional. This is then collapsed via summation to
`(32, 10, 1)` to indicate the attention weights for 10 words.
If set to None, `features` dims are used as `attention_dims`. (Default value: None)
"""
if 'input_shape' not in kwargs and 'input_dim' in kwargs:
kwargs['input_shape'] = (kwargs.pop('input_dim'),)
super(AttentionLayer, self).__init__(**kwargs)
self.kernel_initializer = initializers.get(kernel_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.use_bias = use_bias
self.bias_initializer = initializers.get(bias_initializer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.bias_constraint = constraints.get(bias_constraint)
self.use_context = use_context
self.context_initializer = initializers.get(context_initializer)
self.context_regularizer = regularizers.get(context_regularizer)
self.context_constraint = constraints.get(context_constraint)
self.attention_dims = attention_dims
self.supports_masking = True
def __init__(self,
kernel_size,
strides=(1, 1),
padding='valid',
depth_multiplier=1,
data_format=None,
activation=None,
use_bias=True,
depthwise_initializer='glorot_uniform',
bias_initializer='zeros',
depthwise_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
depthwise_constraint=None,
bias_constraint=None,
**kwargs):
super(DepthwiseConv2D, self).__init__(
filters=None,
kernel_size=kernel_size,
strides=strides,
padding=padding,
data_format=data_format,
activation=activation,
use_bias=use_bias,
bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer,
bias_constraint=bias_constraint,
**kwargs)
self.depth_multiplier = depth_multiplier
self.depthwise_initializer = initializers.get(depthwise_initializer)
self.depthwise_regularizer = regularizers.get(depthwise_regularizer)
self.depthwise_constraint = constraints.get(depthwise_constraint)
self.bias_initializer = initializers.get(bias_initializer)
self._padding = padding.upper()
if K.image_data_format() == 'channels_last':
self._strides = (1,) + strides + (1,)
else:
self._strides = (1, 1,) + strides
if self.data_format == 'channels_last':
self._data_format = "NHWC"
else:
self._data_format = "NCHW"
def __init__(self, a_initializer='ones',
k_initializer='ones',
n_initializer='ones',
z_initializer='zeros',
a_regularizer=None,
a_constraint=constraints.NonNeg(),
k_regularizer=None,
k_constraint=constraints.NonNeg(),
n_regularizer=None,
n_constraint=constraints.NonNeg(),
z_regularizer=None,
z_constraint=constraints.NonNeg(),
shared_axes=None,
a_shared=True,
k_shared=True,
n_shared=True,
z_shared=True,
z_one=False,
**kwargs):
super(Hill, self).__init__(**kwargs)
self.supports_masking = True
self.a_initializer = initializers.get(a_initializer)
self.a_regularizer = regularizers.get(a_regularizer)
self.a_constraint = constraints.get(a_constraint)
self.k_initializer = initializers.get(a_initializer)
self.k_regularizer = regularizers.get(a_regularizer)
self.k_constraint = constraints.get(a_constraint)
self.n_initializer = initializers.get(a_initializer)
self.n_regularizer = regularizers.get(a_regularizer)
self.n_constraint = constraints.get(a_constraint)
self.z_initializer = initializers.get(a_initializer)
self.z_regularizer = regularizers.get(a_regularizer)
self.z_constraint = constraints.get(a_constraint)
self.a_shared = a_shared
self.k_shared = k_shared
self.n_shared = n_shared
self.z_shared = z_shared
self.z_one = z_one
if shared_axes is None:
self.shared_axes = None
elif not isinstance(shared_axes, (list, tuple)):
self.shared_axes = [shared_axes]
else:
self.shared_axes = list(shared_axes)
def __init__(self, units, output_dim,
activation='tanh',
return_probabilities=False,
name='AttentionDecoder',
kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
"""
Implements an AttentionDecoder that takes in a sequence encoded by an
encoder and outputs the decoded states
:param units: dimension of the hidden state and the attention matrices
:param output_dim: the number of labels in the output space
references:
Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio.
"Neural machine translation by jointly learning to align and translate."
arXiv preprint arXiv:1409.0473 (2014).
"""
self.units = units
self.output_dim = output_dim
self.return_probabilities = return_probabilities
self.activation = activations.get(activation)
self.kernel_initializer = initializers.get(kernel_initializer)
self.recurrent_initializer = initializers.get(recurrent_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.recurrent_regularizer = regularizers.get(kernel_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.recurrent_constraint = constraints.get(kernel_constraint)
self.bias_constraint = constraints.get(bias_constraint)
super(AttentionDecoder, self).__init__(**kwargs)
self.name = name
self.return_sequences = True # must return sequences
def __init__(self, nb_filter, nb_row, nb_col,
init='glorot_uniform', activation=None, weights=None,
border_mode='valid', subsample=(1, 1), dim_ordering='default',
W_regularizer=None, b_regularizer=None, activity_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, epsilon=1e-3, momentum=0.99,
beta_init='zero', gamma_init='one',
gamma_regularizer=None, beta_regularizer=None, **kwargs):
if dim_ordering == 'default':
dim_ordering = K.image_dim_ordering()
if border_mode not in {'valid', 'same', 'full'}:
raise ValueError('Invalid border mode for Convolution2D:', border_mode)
self.nb_filter = nb_filter
self.nb_row = nb_row
self.nb_col = nb_col
self.init = initializations.get(init)
self.activation = activations.get(activation)
self.border_mode = border_mode
self.subsample = tuple(subsample)
if dim_ordering not in {'tf', 'th'}:
raise ValueError('dim_ordering must be in {tf, th}.')
self.dim_ordering = dim_ordering
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
self.input_spec = [InputSpec(ndim=4)]
self.initial_weights = weights
# added for BatchNormalization
self.supports_masking = True
self.beta_init = initializations.get(beta_init)
self.gamma_init = initializations.get(gamma_init)
self.epsilon = epsilon
self.momentum = momentum
self.gamma_regularizer = regularizers.get(gamma_regularizer)
self.beta_regularizer = regularizers.get(beta_regularizer)
self.initial_weights = weights
self.uses_learning_phase = True
super(YOLOConvolution2D, self).__init__(**kwargs)
