Python tensorflow.keras.initializers.serialize() Examples

The following are 26 code examples of tensorflow.keras.initializers.serialize(). 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.keras.initializers , or try the search function .
Example #1
Source File: FRN.py    From TF.Keras-Commonly-used-models with Apache License 2.0 6 votes vote down vote up 
def get_config(self):
        config = {
            'axis': self.axis,
            'epsilon': self.epsilon,
            'beta_initializer': initializers.serialize(self.beta_initializer),
            'tau_initializer': initializers.serialize(self.tau_initializer),
            'gamma_initializer': initializers.serialize(self.gamma_initializer),
            'beta_regularizer': regularizers.serialize(self.beta_regularizer),
            'tau_regularizer': regularizers.serialize(self.tau_regularizer),
            'gamma_regularizer': regularizers.serialize(self.gamma_regularizer),
            'beta_constraint': constraints.serialize(self.beta_constraint),
            'gamma_constraint': constraints.serialize(self.gamma_constraint),
            'tau_constraint': constraints.serialize(self.tau_constraint)
        }
        base_config = super(FRN, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #2
Source File: group_convolution.py    From Basic_CNNs_TensorFlow2 with MIT License 6 votes vote down vote up 
def get_config(self):
        config = {
            "input_channels": self.input_channels,
            "output_channels": self.output_channels,
            "kernel_size": self.kernel_size,
            "strides": self.strides,
            "padding": self.padding,
            "output_padding": self.output_padding,
            "data_format": self.data_format,
            "dilation_rate": self.dilation_rate,
            "activation": activations.serialize(self.activation),
            "groups": self.groups,
            "use_bias": self.use_bias,
            "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.activity_regularizer),
            "kernel_constraint": constraints.serialize(self.kernel_constraint),
            "bias_constraint": constraints.serialize(self.bias_constraint)
        }
        base_config = super(GroupConv2DTranspose, self).get_config()
        return {**base_config, **config}
Example #3
Source File: groupnorm.py    From bcnn with MIT License 6 votes vote down vote up 
def get_config(self):
        config = {
            "groups": self.groups,
            "axis": self.axis,
            "epsilon": self.epsilon,
            "center": self.center,
            "scale": self.scale,
            "beta_initializer": initializers.serialize(self.beta_initializer),
            "gamma_initializer": initializers.serialize(self.gamma_initializer),
            "beta_regularizer": regularizers.serialize(self.beta_regularizer),
            "gamma_regularizer": regularizers.serialize(self.gamma_regularizer),
            "beta_constraint": constraints.serialize(self.beta_constraint),
            "gamma_constraint": constraints.serialize(self.gamma_constraint)
        }
        base_config = super(GroupNormalization, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #4
Source File: group_convolution.py    From Basic_CNNs_TensorFlow2 with MIT License 6 votes vote down vote up 
def get_config(self):
        config = {
            "input_channels": self.input_channels,
            "output_channels": self.output_channels,
            "kernel_size": self.kernel_size,
            "strides": self.strides,
            "padding": self.padding,
            "data_format": self.data_format,
            "dilation_rate": self.dilation_rate,
            "activation": activations.serialize(self.activation),
            "groups": self.groups,
            "use_bias": self.use_bias,
            "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.activity_regularizer),
            "kernel_constraint": constraints.serialize(self.kernel_constraint),
            "bias_constraint": constraints.serialize(self.bias_constraint)
        }
        base_config = super(GroupConv2D, self).get_config()
        return {**base_config, **config}
Example #5
Source File: layers.py    From neuron with GNU General Public License v3.0 6 votes vote down vote up 
def get_config(self):
        config = {
            'filters': self.filters,
            'kernel_size': self.kernel_size,
            'strides': self.strides,
            'padding': self.padding,
            'data_format': self.data_format,
            'activation': activations.serialize(self.activation),
            'use_bias': self.use_bias,
            '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.activity_regularizer),
            'kernel_constraint': constraints.serialize(self.kernel_constraint),
            'bias_constraint': constraints.serialize(self.bias_constraint)
        }
        base_config = super(
            LocallyConnected3D, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #6
Source File: group_norm.py    From 3d-brain-tumor-segmentation with Apache License 2.0 6 votes vote down vote up 
def get_config(self):
        config = {
            'groups': self.groups,
            'axis': self.axis,
            'epsilon': self.epsilon,
            'center': self.center,
            'scale': self.scale,
            'beta_initializer': initializers.serialize(self.beta_initializer),
            'gamma_initializer': initializers.serialize(self.gamma_initializer),
            'beta_regularizer': regularizers.serialize(self.beta_regularizer),
            'gamma_regularizer': regularizers.serialize(self.gamma_regularizer),
            'beta_constraint': constraints.serialize(self.beta_constraint),
            'gamma_constraint': constraints.serialize(self.gamma_constraint)
        }
        base_config = super(GroupNormalization, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #7
Source File: conv2d_mpo.py    From TensorNetwork with Apache License 2.0 6 votes vote down vote up 
def get_config(self) -> dict:
    config = {
        'filters': self.filters,
        'kernel_size': self.kernel_size,
        'num_nodes': self.num_nodes,
        'bond_dim': self.bond_dim,
        'strides': self.strides,
        'padding': self.padding,
        'data_format': self.data_format,
        'dilation_rate': self.dilation_rate,
        'activation': activations.serialize(self.activation),
        'use_bias': self.use_bias,
        '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),
    }
    base_config = super(Conv2DMPO, self).get_config()
    config.update(base_config)
    return config
Example #8
Source File: qconvolutional.py    From qkeras with Apache License 2.0 6 votes vote down vote up 
def get_config(self):
    config = super(QDepthwiseConv2D, self).get_config()
    config.pop("filters", None)
    config.pop("kernel_initializer", None)
    config.pop("kernel_regularizer", None)
    config.pop("kernel_constraint", None)
    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)
    config["depthwise_quantizer"] = constraints.serialize(
        self.depthwise_quantizer_internal)
    config["bias_quantizer"] = constraints.serialize(
        self.bias_quantizer_internal)
    config["depthwise_range"] = self.depthwise_range
    config["bias_range"] = self.bias_range
    return config
Example #9
Source File: conv_mod.py    From StyleGAN2-Tensorflow-2.0 with MIT License 6 votes vote down vote up 
def get_config(self):
        config = {
            'filters': self.filters,
            'kernel_size': self.kernel_size,
            'strides': self.strides,
            'padding': self.padding,
            'dilation_rate': self.dilation_rate,
            'kernel_initializer': initializers.serialize(self.kernel_initializer),
            'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
            'activity_regularizer':
                regularizers.serialize(self.activity_regularizer),
            'kernel_constraint': constraints.serialize(self.kernel_constraint),
            'demod': self.demod
        }
        base_config = super(Conv2DMod, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #10
Source File: qnormalization.py    From qkeras with Apache License 2.0 5 votes vote down vote up 
def get_config(self):
    config = {
        'axis': self.axis,
        'momentum': self.momentum,
        'epsilon': self.epsilon,
        'center': self.center,
        'scale': self.scale,
        'beta_quantizer':
            constraints.serialize(self.beta_quantizer_internal),
        'gamma_quantizer':
            constraints.serialize(self.gamma_quantizer_internal),
        'mean_quantizer':
            constraints.serialize(self.mean_quantizer_internal),
        'variance_quantizer':
            constraints.serialize(self.variance_quantizer_internal),
        'beta_initializer': initializers.serialize(self.beta_initializer),
        'gamma_initializer': initializers.serialize(self.gamma_initializer),
        'moving_mean_initializer':
            initializers.serialize(self.moving_mean_initializer),
        'moving_variance_initializer':
            initializers.serialize(self.moving_variance_initializer),
        'beta_regularizer': regularizers.serialize(self.beta_regularizer),
        'gamma_regularizer': regularizers.serialize(self.gamma_regularizer),
        'beta_constraint': constraints.serialize(self.beta_constraint),
        'gamma_constraint': constraints.serialize(self.gamma_constraint),
        'beta_range': self.beta_range,
        'gamma_range': self.gamma_range,
    }
    base_config = super(BatchNormalization, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #11
Source File: custom_activation.py    From Echo with MIT License 5 votes vote down vote up 
def get_config(self):
        config = {
            "alpha_initializer": initializers.serialize(self.b_initializer),
            "alpha_regularizer": regularizers.serialize(self.b_regularizer),
            "alpha_constraint": constraints.serialize(self.b_constraint),
            "b_initializer": initializers.serialize(self.b_initializer),
            "b_regularizer": regularizers.serialize(self.b_regularizer),
            "b_constraint": constraints.serialize(self.b_constraint),
            "shared_axes": self.shared_axes,
        }
        base_config = super(APL, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #12
Source File: base.py    From megnet with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def get_config(self) -> Dict:
        """
        Part of keras layer interface, where the signature is converted into a dict
        Returns:
            configurational dictionary
        """
        config = {
            'activation': activations.serialize(self.activation),
            'use_bias': self.use_bias,
            '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.activity_regularizer),
            'kernel_constraint': constraints.serialize(
                self.kernel_constraint),
            'bias_constraint': constraints.serialize(self.bias_constraint)
        }

        base_config = super().get_config()
        return dict(list(base_config.items()) + list(config.items()))  # noqa
Example #13
Source File: set2set.py    From megnet with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def get_config(self):
        config = {"T": self.T,
                  "n_hidden": self.n_hidden,
                  "activation": activations.serialize(self.activation),
                  "activation_lstm": activations.serialize(
                      self.activation_lstm),
                  "recurrent_activation": activations.serialize(
                      self.recurrent_activation),
                  "kernel_initializer": initializers.serialize(
                      self.kernel_initializer),
                  "recurrent_initializer": initializers.serialize(
                      self.recurrent_initializer),
                  "bias_initializer": initializers.serialize(
                      self.bias_initializer),
                  "use_bias": self.use_bias,
                  "unit_forget_bias": self.unit_forget_bias,
                  "kernel_regularizer": regularizers.serialize(
                      self.kernel_regularizer),
                  "recurrent_regularizer": regularizers.serialize(
                      self.recurrent_regularizer),
                  "bias_regularizer": regularizers.serialize(
                      self.bias_regularizer),
                  "kernel_constraint": constraints.serialize(
                      self.kernel_constraint),
                  "recurrent_constraint": constraints.serialize(
                      self.recurrent_constraint),
                  "bias_constraint": constraints.serialize(self.bias_constraint)

                  }
        base_config = super().get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #14
Source File: condenser.py    From TensorNetwork with Apache License 2.0 5 votes vote down vote up 
def get_config(self) -> dict:
    """Returns the config of the layer.

    The same layer can be reinstantiated later
    (without its trained weights) from this configuration.

    Returns:
      Python dictionary containing the configuration of the layer.
    """
    config = {}

    # Include the Condenser-specific arguments
    args = ['exp_base', 'num_nodes', 'use_bias']
    for arg in args:
      config[arg] = getattr(self, arg)

    # Serialize the activation
    config['activation'] = activations.serialize(getattr(self, 'activation'))

    # Serialize the initializers
    initializers_list = ['kernel_initializer', 'bias_initializer']
    for initializer_arg in initializers_list:
      config[initializer_arg] = initializers.serialize(
          getattr(self, initializer_arg))

    # Get base config
    base_config = super(DenseCondenser, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #15
Source File: mpo.py    From TensorNetwork with Apache License 2.0 5 votes vote down vote up 
def get_config(self) -> dict:
    """Returns the config of the layer.

    The same layer can be reinstantiated later
    (without its trained weights) from this configuration.

    Returns:
      Python dictionary containing the configuration of the layer.
    """
    config = {}

    # Include the MPO-specific arguments
    args = ['output_dim', 'num_nodes', 'bond_dim', 'use_bias']
    for arg in args:
      config[arg] = getattr(self, arg)

    # Serialize the activation
    config['activation'] = activations.serialize(getattr(self, 'activation'))

    # Serialize the initializers
    custom_initializers = ['kernel_initializer', 'bias_initializer']
    for initializer_arg in custom_initializers:
      config[initializer_arg] = initializers.serialize(
          getattr(self, initializer_arg))

    # Get base config
    base_config = super(DenseMPO, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #16
Source File: dense.py    From TensorNetwork with Apache License 2.0 5 votes vote down vote up 
def get_config(self) -> dict:
    """Returns the config of the layer.

    The same layer can be reinstantiated later
    (without its trained weights) from this configuration.

    Returns:
      Python dictionary containing the configuration of the layer.
    """
    config = {}

    # Include the DenseDecomp-specific arguments
    decomp_args = ['output_dim', 'decomp_size', 'use_bias']
    for arg in decomp_args:
      config[arg] = getattr(self, arg)

    # Serialize the activation
    config['activation'] = activations.serialize(getattr(self, 'activation'))

    # Serialize the initializers
    decomp_initializers = ['kernel_initializer', 'bias_initializer']
    for initializer_arg in decomp_initializers:
      config[initializer_arg] = initializers.serialize(
          getattr(self, initializer_arg))

    # Get base config
    base_config = super(DenseDecomp, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #17
Source File: entangler.py    From TensorNetwork with Apache License 2.0 5 votes vote down vote up 
def get_config(self) -> dict:
    """Returns the config of the layer.

    The same layer can be reinstantiated later
    (without its trained weights) from this configuration.

    Returns:
      Python dictionary containing the configuration of the layer.
    """
    config = {}

    # Include the Entangler-specific arguments
    args = ['output_dim', 'num_legs', 'num_levels', 'use_bias']
    for arg in args:
      config[arg] = getattr(self, arg)

    # Serialize the activation
    config['activation'] = activations.serialize(getattr(self, 'activation'))

    # Serialize the initializers
    layer_initializers = ['kernel_initializer', 'bias_initializer']
    for initializer_arg in layer_initializers:
      config[initializer_arg] = initializers.serialize(
          getattr(self, initializer_arg))

    # Get base config
    base_config = super(DenseEntangler, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #18
Source File: qconvolutional.py    From qkeras with Apache License 2.0 5 votes vote down vote up 
def get_config(self):
    config = {
        "kernel_quantizer":
            constraints.serialize(self.kernel_quantizer_internal),
        "bias_quantizer":
            constraints.serialize(self.bias_quantizer_internal),
        "kernel_range": self.kernel_range,
        "bias_range": self.bias_range
    }
    base_config = super(QConv2D, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #19
Source File: qconvolutional.py    From qkeras with Apache License 2.0 5 votes vote down vote up 
def get_config(self):
    config = {
        "kernel_quantizer":
            constraints.serialize(self.kernel_quantizer_internal),
        "bias_quantizer":
            constraints.serialize(self.bias_quantizer_internal),
        "kernel_range": self.kernel_range,
        "bias_range": self.bias_range
    }
    base_config = super(QConv1D, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #20
Source File: qlayers.py    From qkeras with Apache License 2.0 5 votes vote down vote up 
def get_config(self):
    config = {
        "units": self.units,
        "activation": activations.serialize(self.activation),
        "use_bias": self.use_bias,
        "kernel_quantizer":
            constraints.serialize(self.kernel_quantizer_internal),
        "bias_quantizer":
            constraints.serialize(self.bias_quantizer_internal),
        "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.activity_regularizer),
        "kernel_constraint":
            constraints.serialize(self.kernel_constraint),
        "bias_constraint":
            constraints.serialize(self.bias_constraint),
        "kernel_range": self.kernel_range,
        "bias_range": self.bias_range
    }
    base_config = super(QDense, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))
Example #21
Source File: se_mobilenets.py    From keras-squeeze-excite-network with MIT License 5 votes vote down vote up 
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
Example #22
Source File: graph_conv.py    From spektral with MIT License 5 votes vote down vote up 
def get_config(self):
        config = {
            'channels': self.channels,
            'activation': activations.serialize(self.activation),
            'use_bias': self.use_bias,
            '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),
            'kernel_constraint': constraints.serialize(self.kernel_constraint),
            'bias_constraint': constraints.serialize(self.bias_constraint)
        }
        base_config = super().get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #23
Source File: mincut_pool.py    From spektral with MIT License 5 votes vote down vote up 
def get_config(self):
        config = {
            'k': self.k,
            'mlp_hidden': self.mlp_hidden,
            'mlp_activation': self.mlp_activation,
            'return_mask': self.return_mask,
            '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),
            'kernel_constraint': constraints.serialize(self.kernel_constraint),
            'bias_constraint': constraints.serialize(self.bias_constraint)
        }
        base_config = super().get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #24
Source File: diff_pool.py    From spektral with MIT License 5 votes vote down vote up 
def get_config(self):
        config = {
            'k': self.k,
            'channels': self.channels,
            'return_mask': self.return_mask,
            'kernel_initializer': initializers.serialize(self.kernel_initializer),
            'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
            'kernel_constraint': constraints.serialize(self.kernel_constraint),
        }
        base_config = super().get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #25
Source File: topk_pool.py    From spektral with MIT License 5 votes vote down vote up 
def get_config(self):
        config = {
            'ratio': self.ratio,
            'return_mask': self.return_mask,
            'kernel_initializer': initializers.serialize(self.kernel_initializer),
            'kernel_regularizer': regularizers.serialize(self.kernel_regularizer),
            'kernel_constraint': constraints.serialize(self.kernel_constraint),
        }
        base_config = super().get_config()
        return dict(list(base_config.items()) + list(config.items()))
Example #26
Source File: keras.py    From spektral with MIT License 5 votes vote down vote up 
def serialize_kwarg(key, attr):
    if key.endswith('_initializer'):
        return initializers.serialize(attr)
    if key.endswith('_regularizer'):
        return regularizers.serialize(attr)
    if key.endswith('_constraint'):
        return constraints.serialize(attr)
    if key == 'activation':
        return activations.serialize(attr)
    if key == 'use_bias':
        return attr