Python keras.regularizers 模块,serialize() 实例源码
我们从Python开源项目中,提取了以下37个代码示例,用于说明如何使用keras.regularizers.serialize()。
def get_config(self):
config = {'output_dim': self.output_dim,
'window_size': self.window_size,
'init': self.init.get_config(),
'stride': self.strides[0],
'activation': activations.serialize(self.activation),
'kernel_initializer': initializers.serialize(self.kernel_initializer),
'bias_initializer': initializers.serialize(self.bias_initializer),
'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
'bias_regularizer': regularizers.serialize(self.bias_regularizer),
'activity_regularizer': regularizers.serialize(self.activy_regularizer),
'kernel_constraint': constraints.serialize(self.kernel_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint),
'use_bias': self.use_bias,
'input_dim': self.input_dim,
'input_length': self.input_length}
base_config = super(GCNN, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'units': self.units,
'return_sequences': self.return_sequences,
'go_backwards': self.go_backwards,
'stateful': self.stateful,
'unroll': self.unroll,
'dropout': self.dropout,
'activity_regularizer': regularizers.serialize(self.activity_regularizer),
'input_length': self.input_length}
base_config = super(QRNN, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'units': self.units,
'recurrent_activation': activations.serialize(self.recurrent_activation),
'recurrent_initializer': initializers.serialize(self.recurrent_initializer),
'unit_forget_bias': self.unit_forget_bias,
'recurrent_regularizer': regularizers.serialize(self.recurrent_regularizer),
'recurrent_constraint': constraints.serialize(self.recurrent_constraint),
'recurrent_dropout': self.recurrent_dropout}
base_config = super(MultiplicativeLSTM, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'filters': self.filters,
'kernel_size': self.kernel_size,
'padding': self.padding,
'strides': self.strides,
'data_format': self.data_format,
'use_bias': self.use_bias}
base_config = super(CosineConvolution2D, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'filters_simple': self.filters_simple,
'filters_complex': self.filters_complex,
'activation': self.activation.__name__,
'dilation_rate': self.dilation_rate,
'kernel_regularizer': self.kernel_regularizer.get_config() if self.kernel_regularizer else None,
'bias_regularizer': self.bias_regularizer.get_config() if self.bias_regularizer else None,
'activity_regularizer': self.activity_regularizer.get_config() if self.activity_regularizer else None,
'kernel_constraint': self.kernel_constraint.get_config() if self.kernel_constraint else None,
'bias_constraint': self.bias_constraint.get_config() if self.bias_constraint else None,
'use_bias': self.use_bias}
base_config = super(Convolution2DEnergy_Scatter, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
# separate biases per channel
def get_config(self):
config = {'filters_simple': self.filters_simple,
'kernel_constraint': self.W_constraint.get_config() if self.W_constraint else None,
'use_bias': self.bias}
base_config = super(Convolution2DEnergy_Scatter2, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'rank': self.rank,
'kernel_size': self.kernel_size,
'padding': self.padding,
'data_format': self.data_format,
'kernel_initializer': initializers.serialize(self.kernel_initializer),
'bias_initializer': initializers.serialize(self.kernel_initializer),
'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
'bias_regularizer': regularizers.serialize(self.bias_regularizer),
'activity_regularizer': regularizers.serialize(self.activity_regularizer),
'kernel_constraint': constraints.serialize(self.kernel_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(_ConvGDN, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'alpha_pos_initializer': initializers.serialize(self.alpha_pos_initializer),
'alpha_neg_initializer': initializers.serialize(self.alpha_neg_initializer),
'beta_pos_initializer': initializers.serialize(self.beta_pos_initializer),
'beta_neg_initializer': initializers.serialize(self.beta_neg_initializer),
'rho_pos_initializer': initializers.serialize(self.rho_pos_initializer),
'rho_neg_initializer': initializers.serialize(self.rho_neg_initializer),
'alpha_pos_constraint': constraints.serialize(self.alpha_pos_constraint),
'alpha_neg_constraint': constraints.serialize(self.alpha_neg_constraint),
'beta_pos_constraint': constraints.serialize(self.beta_pos_constraint),
'beta_neg_constraint': constraints.serialize(self.beta_neg_constraint),
'rho_pos_constraint': constraints.serialize(self.rho_pos_constraint),
'rho_neg_constraint': constraints.serialize(self.rho_neg_constraint),
'alpha_pos_regularizer': regularizers.serialize(self.alpha_pos_regularizer),
'alpha_neg_regularizer': regularizers.serialize(self.alpha_neg_regularizer),
'beta_pos_regularizer': regularizers.serialize(self.beta_pos_regularizer),
'beta_neg_regularizer': regularizers.serialize(self.beta_neg_regularizer),
'rho_pos_regularizer': regularizers.serialize(self.rho_pos_regularizer),
'rho_neg_regularizer': regularizers.serialize(self.rho_neg_regularizer),
}
base_config = super(PowerPReLU, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'filters': self.filters,
'sum_axes': self.sum_axes,
'filter_axes': self.filter_axes,
'activation': activations.serialize(self.activation),
'kernel_activation': activations.serialize(self.kernel_activation),
'use_bias': self.use_bias,
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(FilterDims, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'units': self.units,
'learn_mode': self.learn_mode,
'test_mode': self.test_mode,
'use_boundary': self.use_boundary,
'sparse_target': self.sparse_target,
'chain_initializer': initializers.serialize(self.chain_initializer),
'boundary_initializer': initializers.serialize(self.boundary_initializer),
'chain_regularizer': regularizers.serialize(self.chain_regularizer),
'boundary_regularizer': regularizers.serialize(self.boundary_regularizer),
'chain_constraint': constraints.serialize(self.chain_constraint),
'boundary_constraint': constraints.serialize(self.boundary_constraint),
'unroll': self.unroll}
base_config = super(CRF, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'activation': activations.serialize(self.activation),
'recurrent_activation': activations.serialize(self.recurrent_activation),
'recurrent_initializer': initializers.serialize(self.recurrent_initializer),
'bias_initializer': initializers.serialize(self.bias_initializer),
'recurrent_regularizer': regularizers.serialize(self.recurrent_regularizer),
'recurrent_constraint': constraints.serialize(self.recurrent_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(ExtendedRNNCell, self).get_config()
config.update(base_config)
return config
def get_config(self):
config = {'epsilon': self.epsilon,
'axis': self.axis,
'gamma_init': initializers.serialize(self.gamma_init),
'beta_init': initializers.serialize(self.beta_init),
'gamma_regularizer': regularizers.serialize(self.gamma_regularizer),
'beta_regularizer': regularizers.serialize(self.gamma_regularizer)}
base_config = super(Layernormalization, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'kernel_initializer': initializers.serialize(self.kernel_initializer),
'bias_constraint': constraints.serialize(self.bias_constraint),
'context_initializer': initializers.serialize(self.context_initializer),
'context_regularizer': regularizers.serialize(self.context_regularizer),
'context_constraint': constraints.serialize(self.context_constraint)
}
base_config = super(AttentionLayer, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = super(DepthwiseConv2D, self).get_config()
config.pop('filters')
config.pop('kernel_initializer')
config.pop('kernel_regularizer')
config.pop('kernel_constraint')
config['depth_multiplier'] = self.depth_multiplier
config['depthwise_initializer'] = initializers.serialize(self.depthwise_initializer)
config['depthwise_regularizer'] = regularizers.serialize(self.depthwise_regularizer)
config['depthwise_constraint'] = constraints.serialize(self.depthwise_constraint)
return config
def get_config(self):
config = {'epsilon': self.epsilon,
'mode': self.mode,
'beta_regularizer': regularizers.serialize(self.beta_regularizer),
'momentum': self.momentum,
'r_max_value': self.r_max_value,
'd_max_value': self.d_max_value,
't_delta': self.t_delta}
base_config = super(BatchRenormalization, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = super(DepthwiseConv2D, self).get_config()
config.pop('filters')
config.pop('kernel_initializer')
config.pop('kernel_regularizer')
config.pop('kernel_constraint')
config['depth_multiplier'] = self.depth_multiplier
config['depthwise_initializer'] = initializers.serialize(self.depthwise_initializer)
config['depthwise_regularizer'] = regularizers.serialize(self.depthwise_regularizer)
config['depthwise_constraint'] = constraints.serialize(self.depthwise_constraint)
return config
def get_config(self):
config = super(DepthwiseConv2D, self).get_config()
config.pop('filters')
config.pop('kernel_initializer')
config.pop('kernel_regularizer')
config.pop('kernel_constraint')
config['depth_multiplier'] = self.depth_multiplier
config['depthwise_initializer'] = initializers.serialize(self.depthwise_initializer)
config['depthwise_regularizer'] = regularizers.serialize(self.depthwise_regularizer)
config['depthwise_constraint'] = constraints.serialize(self.depthwise_constraint)
return config
def get_config(self):
config = {'filters_simple': self.filters_simple,
'filters_temporal': self.filters_temporal,
'spatial_kernel_size': self.spatial_kernel_size,
'temporal_frequencies': self.temporal_frequencies,
'temporal_frequencies_initial_max': self.temporal_frequencies_initial_max,
'temporal_frequencies_scaling': self.temporal_frequencies_scaling,
'spatial_kernel_initializer': initializers.serialize(self.spatial_kernel_initializer),
'temporal_kernel_initializer': initializers.serialize(self.temporal_kernel_initializer),
'temporal_frequencies_initializer': initializers.serialize(self.temporal_frequencies_initializer),
'spatial_kernel_regularizer': regularizers.serialize(self.spatial_kernel_regularizer),
'temporal_kernel_regularizer': regularizers.serialize(self.temporal_kernel_regularizer),
'temporal_frequencies_regularizer': regularizers.serialize(self.temporal_frequencies_regularizer),
'spatial_kernel_constraint': constraints.serialize(self.spatial_kernel_constraint),
'temporal_kernel_constraint': constraints.serialize(self.temporal_kernel_constraint),
'temporal_frequencies_constraint': constraints.serialize(self.temporal_frequencies_constraint),
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(Convolution2DEnergy_TemporalBasis, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
# separate temporal freqs per channel
def get_config(self):
config = {'filters_simple': self.filters_simple,
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(Convolution2DEnergy_TemporalBasis2,
'bias_constraint': constraints.serialize(self.bias_constraint)
}
base_config = super(Convolution2DEnergy_TemporalBasis3, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'units': self.units,
'k_initializer': initializers.serialize(self.k_initializer),
'k_regularizer': regularizers.serialize(self.k_regularizer),
'k_constraint': constraints.serialize(self.k_constraint)
}
base_config = super(Conv2DSoftMinMax, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'alpha_initializer': initializers.serialize(self.alpha_initializer),
'alpha_regularizer': regularizers.serialize(self.alpha_regularizer),
'alpha_constraint': constraints.serialize(self.alpha_constraint),
'beta_initializer': initializers.serialize(self.beta_initializer),
'beta_regularizer': regularizers.serialize(self.beta_regularizer),
'beta_constraint': constraints.serialize(self.beta_constraint),
'shared_axes': self.shared_axes
}
base_config = super(ParametricSoftplus, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'filters_simple': self.filters_simple,
'neurons': self.neurons,
'gauss_scale': self.gauss_scale,
'centers_initializer': initializers.serialize(self.centers_initializer),
'stds_initializer': initializers.serialize(self.stds_initializer),
'centers_regularizer': regularizers.serialize(self.centers_regularizer),
'stds_regularizer': regularizers.serialize(self.stds_regularizer),
'centers_constraint': constraints.serialize(self.centers_constraint),
'stds_constraint': constraints.serialize(self.stds_constraint),
}
base_config = super(Convolution2DEnergy_TemporalBasis_GaussianRF, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'quadratic_filters_ex': self.quadratic_filters_ex,
'quadratic_filters_sup': self.quadratic_filters_sup,
'W_quad_ex_initializer': initializers.serialize(self.W_quad_ex_initializer),
'W_quad_ex_regularizer': regularizers.serialize(self.W_quad_ex_regularizer),
'W_quad_ex_constraint': constraints.serialize(self.W_quad_ex_constraint),
'W_quad_sup_initializer': initializers.serialize(self.W_quad_sup_initializer),
'W_quad_sup_regularizer': regularizers.serialize(self.W_quad_sup_regularizer),
'W_lin_regularizer': constraints.serialize(self.W_lin_regularizer),
'W_lin_initializer': initializers.serialize(self.W_lin_initializer),
'W_lin_constraint': constraints.serialize(self.W_lin_constraint),
}
base_config = super(RustSTC, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'init': initializers.serialize(self.init),
'W_regularizer': regularizers.serialize(self.W_regularizer),
'b_regularizer': regularizers.serialize(self.b_regularizer),
'W_constraint': constraints.serialize(self.W_constraint),
'b_constraint': constraints.serialize(self.b_constraint),
'bias': self.bias,
'input_dim': self.input_dim}
base_config = super(Highway, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {
'init': initializers.serialize(self.init),
'U_regularizer': regularizers.serialize(self.U_regularizer),
'b_start_regularizer': regularizers.serialize(self.b_start_regularizer),
'b_end_regularizer': regularizers.serialize(self.b_end_regularizer),
'U_constraint': constraints.serialize(self.U_constraint),
'b_start_constraint': constraints.serialize(self.b_start_constraint),
'b_end_constraint': constraints.serialize(self.b_end_constraint)
}
base_config = super(ChainCRF, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = {'W_regularizer': regularizers.serialize(self.W_regularizer),
'u_regularizer': regularizers.serialize(self.u_regularizer),
'u_constraint': constraints.serialize(self.u_constraint),
'W_dropout': self.W_dropout,
'u_dropout': self.u_dropout,
'bias': self.bias}
base_config = super(AttentionWithContext, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_config(self):
config = super(DepthwiseConv2D,
'temporal_frequencies_initial_max':
self.temporal_frequencies_initial_max,
'temporal_frequencies_scaling':
self.temporal_frequencies_scaling,
'spatial_kernel_initializer':
initializers.serialize(
self.spatial_kernel_initializer),
'temporal_kernel_initializer':
initializers.serialize(
self.temporal_kernel_initializer),
'temporal_frequencies_initializer':
initializers.serialize(
self.temporal_frequencies_initializer),
'bias_initializer':
initializers.serialize(self.bias_initializer),
'spatial_kernel_regularizer':
regularizers.serialize(
self.spatial_kernel_regularizer),
'temporal_kernel_regularizer':
regularizers.serialize(
self.temporal_kernel_regularizer),
'temporal_frequencies_regularizer':
regularizers.serialize(
self.temporal_frequencies_regularizer),
'bias_regularizer':
regularizers.serialize(self.bias_regularizer),
'activity_regularizer':
regularizers.serialize(self.activity_regularizer),
'spatial_kernel_constraint':
constraints.serialize(self.spatial_kernel_constraint),
'temporal_kernel_constraint':
constraints.serialize(self.temporal_kernel_constraint),
'temporal_frequencies_constraint':
constraints.serialize(
self.temporal_frequencies_constraint),
'bias_constraint':
constraints.serialize(self.bias_constraint)
}
base_config = super(
Convolution2DEnergy_TemporalCorrelation, self).get_config()
return dict(list(base_config.items()) + list(config.items()))