rztdl.dl.components.layers.convolutional package

Submodules

rztdl.dl.components.layers.convolutional.conv1d module

@created on: 2020-01-06,
@author: shubham,
@version: v0.0.1

Description:

Sphinx Documentation Status:

class rztdl.dl.components.layers.convolutional.conv1d.Conv1D(name: str, filters: int, kernel_size: int = 1, strides: int = 1, padding: rztdl.dl.constants.string_constants.Padding = <Padding.VALID: 'VALID'>, data_format: rztdl.dl.constants.string_constants.DataFormat = <DataFormat.CHANNELS_LAST: 'CHANNELS_LAST'>, dilation_rate: int = 1, activation: rztdl.dl.helpers.activations.Activation = <rztdl.dl.helpers.activations.Linear object>, use_bias: bool = True, kernel_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, bias_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.Zeros object>, kernel_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, bias_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, activity_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, kernel_constraint: rztdl.dl.helpers.constraints.Constraint = None, bias_constraint: rztdl.dl.helpers.constraints.Constraint = None, dropout_rate: float = 0.0, inputs: typing.Union[str, tensorflow.python.framework.ops.Tensor] = None, outputs: str = None, scopes: typing.Union[str, typing.List[str]] = None, trainable: bool = True, normalization: rztdl.dl.helpers.normalizers.Normalizer = None)[source]

Bases: tensorflow.python.keras.layers.convolutional.Conv1D, rztdl.dl.components.layers.layer.Layer

Convolution 1D layer

Parameters:
  • name (str) – name of component
  • filters (int) – the number of output filters in the convolution
  • kernel_size (int) – height and width of the 2D convolution window
  • strides (int) – specifies the strides of the convolution along the height and width
  • padding (Padding) – VALID/SAME
  • data_format (DataFormat) – ordering of the dimensions in the inputs. “channels_last”: (batch, height, width, channels) “channels_first”: (batch, channels, height, width)
  • dilation_rate (int) – an integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution.
  • activation (Activation) – Activation function to use. If you don’t specify anything, no activation is applied
  • use_bias (bool) – Boolean, whether the layer uses a bias vector
  • kernel_initializer (Initializer) – Initializer for the kernel weights matrix
  • bias_initializer (Initializer) – Initializer for the bias vector
  • kernel_regularizer (Optional[Regularizer]) – Regularizer function applied to the kernel weights matrix
  • bias_regularizer (Optional[Regularizer]) – Regularizer function applied to the bias vector
  • activity_regularizer (Optional[Regularizer]) – Regularizer function applied to the output of the layer (its “activation”)
  • kernel_constraint (Optional[Constraint]) – Constraint function applied to the kernel matrix
  • bias_constraint (Optional[Constraint]) – Constraint function applied to the bias vector.
  • inputs (Union[str, Tensor, None]) – Input Tensor
  • outputs (Optional[str]) – Output Tensor
  • dropout_rate (float) – Dropout rate
  • scopes (Union[str, List[str], None]) – list of Tags which can be used to train only specific layers during train
  • trainable (bool) – Indicates if layer should to be trained or not
  • normalization (Optional[Normalizer]) – Normalization to be used
create(inputs)[source]
parameter_validation(filters, kernel_size, strides, dilation_rate, padding, kernel_constraint, bias_constraint)[source]
validate(inputs)[source]

rztdl.dl.components.layers.convolutional.conv2d module

@created on: 12/28/19,
@author: Shubham,
@version: v0.0.1

Description:

Sphinx Documentation Status:

class rztdl.dl.components.layers.convolutional.conv2d.Conv2D(name: str, filters: int, kernel_size: typing.Union[int, typing.List[int]] = (1, 1), strides: typing.Union[int, typing.List[int]] = (1, 1), padding: rztdl.dl.constants.string_constants.Padding = <Padding.VALID: 'VALID'>, data_format: rztdl.dl.constants.string_constants.DataFormat = <DataFormat.CHANNELS_LAST: 'CHANNELS_LAST'>, dilation_rate: typing.Union[int, typing.List[int]] = (1, 1), activation: rztdl.dl.helpers.activations.Activation = <rztdl.dl.helpers.activations.Linear object>, use_bias: bool = True, kernel_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, bias_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.Zeros object>, kernel_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, bias_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, activity_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, kernel_constraint: rztdl.dl.helpers.constraints.Constraint = None, bias_constraint: rztdl.dl.helpers.constraints.Constraint = None, dropout_rate: float = 0.0, inputs: typing.Union[str, tensorflow.python.framework.ops.Tensor] = None, outputs: str = None, scopes: typing.Union[str, typing.List[str]] = None, trainable: bool = True, normalization: rztdl.dl.helpers.normalizers.Normalizer = None)[source]

Bases: tensorflow.python.keras.layers.convolutional.Conv2D, rztdl.dl.components.layers.layer.Layer

Convolution 2D layer

Parameters:
  • name (str) – name of component
  • filters (int) – the number of output filters in the convolution
  • kernel_size (Union[int, List[int]]) – height and width of the 2D convolution window
  • strides (Union[int, List[int]]) – specifies the strides of the convolution along the height and width
  • padding (Padding) – “VALID” or “SAME”
  • data_format (DataFormat) – ordering of the dimensions in the inputs. “CHANNELS_LAST”: (batch, height, width, channels) “CHANNELS_FIRST”: (batch, channels, height, width)
  • dilation_rate (Union[int, List[int]]) – an integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution.
  • activation (Activation) – Activation function to use. If you don’t specify anything, no activation is applied
  • use_bias (bool) – Boolean, whether the layer uses a bias vector
  • kernel_initializer (Initializer) – Initializer for the kernel weights matrix
  • bias_initializer (Initializer) – Initializer for the bias vector
  • kernel_regularizer (Optional[Regularizer]) – Regularizer function applied to the kernel weights matrix
  • bias_regularizer (Optional[Regularizer]) – Regularizer function applied to the bias vector
  • activity_regularizer (Optional[Regularizer]) – Regularizer function applied to the output of the layer (its “activation”)
  • kernel_constraint (Optional[Constraint]) – Constraint function applied to the kernel matrix
  • bias_constraint (Optional[Constraint]) – Constraint function applied to the bias vector.
  • dropout_rate (float) – Rate of Dropout apply on output
  • scopes (Union[str, List[str], None]) – list of Tags which can be used to train only specific layers during train
  • inputs (Union[str, Tensor, None]) – Input Tensor
  • outputs (Optional[str]) – Output Tensor
  • trainable (bool) – Indicates if layer should to be trained or not
  • normalization (Optional[Normalizer]) – Normalization to be used
create(inputs)[source]
parameter_validation(filters, kernel_size, strides, dilation_rate, padding, kernel_constraint, bias_constraint)[source]
validate(inputs)[source]

rztdl.dl.components.layers.convolutional.conv2d_transpose module

@created on: 1/14/20, @author: Vivek A Gupta,

Description:

..todo:

.. py:class:: Conv2DTranspose(name: str, filters: int, kernel_size: typing.Union[int, typing.List[int]] = (1, 1), strides: typing.Union[int, typing.List[int]] = (1, 1), padding: rztdl.dl.constants.string_constants.Padding = <Padding.VALID: 'VALID'>, output_padding: typing.Union[int, typing.List[int]] = None, data_format: rztdl.dl.constants.string_constants.DataFormat = <DataFormat.CHANNELS_LAST: 'CHANNELS_LAST'>, dilation_rate: typing.Union[int, typing.List[int]] = (1, 1), activation: rztdl.dl.helpers.activations.Activation = <rztdl.dl.helpers.activations.Linear object>, use_bias: bool = True, kernel_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, bias_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.Zeros object>, kernel_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, bias_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, activity_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, kernel_constraint: rztdl.dl.helpers.constraints.Constraint = None, bias_constraint: rztdl.dl.helpers.constraints.Constraint = None, dropout_rate: float = 0.0, inputs: typing.Union[str, tensorflow.python.framework.ops.Tensor] = None, outputs: str = None, scopes: typing.Union[str, typing.List[str]] = None, normalization: rztdl.dl.helpers.normalizers.Normalizer = None)
module:rztdl.dl.components.layers.convolutional.conv2d_transpose

Bases: tensorflow.python.keras.layers.convolutional.Conv2DTranspose, rztdl.dl.components.layers.layer.Layer

Conv 2D Transpose

type name:str
param name:name of component
type filters:int
param filters:the number of output filters in the convolution
type kernel_size:
 Union[int, List[int]]
param kernel_size:
 height and width of the 2D convolution window
type strides:Union[int, List[int]]
param strides:specifies the strides of the convolution along the height and width
type padding:Padding
param padding:“valid” or “same”
type output_padding:
 Union[int, List[int], None]
param output_padding:
 an integer or tuple/list of 2 integers, specifying the amount of padding along the height and width of the output tensor
type data_format:
 DataFormat
param data_format:
 ordering of the dimensions in the inputs. “channels_last”: (batch, height, width, channels) “channels_first”: (batch, channels, height, width)
type dilation_rate:
 Union[int, List[int]]
param dilation_rate:
 an integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution.
type activation:
 Activation
param activation:
 Activation function to use. If you don’t specify anything, no activation is applied
type use_bias:bool
param use_bias:Boolean, whether the layer uses a bias vector
type kernel_initializer:
 Initializer
param kernel_initializer:
 Initializer for the kernel weights matrix
type bias_initializer:
 Initializer
param bias_initializer:
 Initializer for the bias vector
type kernel_regularizer:
 Optional[Regularizer]
param kernel_regularizer:
 Regularizer function applied to the kernel weights matrix
type bias_regularizer:
 Optional[Regularizer]
param bias_regularizer:
 Regularizer function applied to the bias vector
type activity_regularizer:
 Optional[Regularizer]
param activity_regularizer:
 Regularizer function applied to the output of the layer (its “activation”)
type kernel_constraint:
 Optional[Constraint]
param kernel_constraint:
 Constraint function applied to the kernel matrix
type bias_constraint:
 Optional[Constraint]
param bias_constraint:
 Constraint function applied to the bias vector.
type inputs:Union[str, Tensor, None]
param inputs:Layer input
type outputs:Optional[str]
param outputs:Layer output
type dropout_rate:
 float
param dropout_rate:
 Dropout rate
type scopes:Union[str, List[str], None]
param scopes:list of Tags which can be used to train only specific layers during train
type normalization:
 Optional[Normalizer]
param normalization:
 Normalization to be used
Conv2DTranspose.create(inputs)[source]
Conv2DTranspose.parameter_validation(filters, kernel_size, strides, dilation_rate, padding)[source]
Conv2DTranspose.validate(inputs)[source]

rztdl.dl.components.layers.convolutional.conv3d module

@created on: 2020-01-28,
@author: shubham,
@version: v0.0.1

Description:

Sphinx Documentation Status: Complete

class rztdl.dl.components.layers.convolutional.conv3d.Conv3D(name: str, filters: int, kernel_size: typing.Union[int, typing.List[int]] = (1, 1, 1), strides: typing.Union[int, typing.List[int]] = (1, 1, 1), padding: rztdl.dl.constants.string_constants.Padding = <Padding.VALID: 'VALID'>, data_format: rztdl.dl.constants.string_constants.DataFormat = <DataFormat.CHANNELS_LAST: 'CHANNELS_LAST'>, dilation_rate: typing.Union[int, typing.List[int]] = (1, 1, 1), activation: rztdl.dl.helpers.activations.Activation = <rztdl.dl.helpers.activations.Linear object>, use_bias: bool = True, kernel_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, bias_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.Zeros object>, kernel_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, bias_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, activity_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, kernel_constraint: rztdl.dl.helpers.constraints.Constraint = None, bias_constraint: rztdl.dl.helpers.constraints.Constraint = None, trainable: bool = True, inputs: typing.Union[str, tensorflow.python.framework.ops.Tensor] = None, scopes: typing.Union[str, typing.List[str]] = None, dropout_rate: float = 0.0, outputs: str = None, normalization: rztdl.dl.helpers.normalizers.Normalizer = None)[source]

Bases: tensorflow.python.keras.layers.convolutional.Conv3D, rztdl.dl.components.layers.layer.Layer

3D convolution layer (e.g. spatial convolution over volumes).

Parameters:
  • name (str) – name of component
  • filters (int) – Dimensionality of the output space
  • kernel_size (Union[int, List[int]]) – int/list of 3 integers, specifying the depth, height and width of the 3D convolution window
  • strides (Union[int, List[int]]) – int/list of 3 integers, specifying the strides of the convolution along each spatial dimension
  • padding (Padding) – “VALID” or “SAME”
  • data_format (DataFormat) – ordering of the dimensions in the inputs. “channels_last”: (batch, spatial_dim1, spatial_dim2, spatial_dim3, channels) “channels_first”: (batch, channels, spatial_dim1, spatial_dim2, spatial_dim3)
  • dilation_rate (Union[int, List[int]]) – int/list of 3 integers, specifying the dilation rate to use for dilated convolution.
  • activation (Activation) – Activation function to use. If you don’t specify anything, no activation is applied (ie. “Linear” activation: a(x) = x
  • use_bias (bool) – Boolean, whether the layer uses a bias vector
  • kernel_initializer (Initializer) – Initializer for the kernel weights matrix
  • bias_initializer (Initializer) – Initializer for the bias vector
  • kernel_regularizer (Optional[Regularizer]) – Regularizer function applied to the kernel weights matrix
  • bias_regularizer (Optional[Regularizer]) – Regularizer function applied to the bias vector
  • activity_regularizer (Optional[Regularizer]) – Regularizer function applied to the output of the layer (its “activation”)
  • kernel_constraint (Optional[Constraint]) – Constraint function applied to the kernel matrix.
  • bias_constraint (Optional[Constraint]) – Constraint function applied to the bias vector.
  • dropout_rate (float) – Rate of Dropout apply on output.
  • scopes (Union[str, List[str], None]) – list of Tags which can be used to train only specific layers during train.
  • trainable (bool) – Indicates if layer should to be trained or not.
  • inputs (Union[str, Tensor, None]) – Input tensor/component name.
  • outputs (Optional[str]) – Output name.
  • normalization (Optional[Normalizer]) – Normalization to be used
create(inputs)[source]
parameter_validation(filters, kernel_size, strides, dilation_rate, padding, kernel_constraint, bias_constraint)[source]
validate(inputs)[source]

rztdl.dl.components.layers.convolutional.separable_conv1d module

@created on: 2020-02-03,
@author: shubham,
@version: v0.0.1

Description:

Sphinx Documentation Status: Complete

class rztdl.dl.components.layers.convolutional.separable_conv1d.SeparableConv1D(name: str, filters: int, kernel_size: int = 1, strides: int = 1, padding: rztdl.dl.constants.string_constants.Padding = <Padding.VALID: 'VALID'>, data_format: rztdl.dl.constants.string_constants.DataFormat = <DataFormat.CHANNELS_LAST: 'CHANNELS_LAST'>, dilation_rate: int = 1, depth_multiplier: int = 1, activation: rztdl.dl.helpers.activations.Activation = <rztdl.dl.helpers.activations.Linear object>, use_bias: bool = True, depthwise_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, pointwise_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, bias_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.Zeros object>, depthwise_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, pointwise_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, bias_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, activity_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, depthwise_constraint: rztdl.dl.helpers.constraints.Constraint = None, pointwise_constraint: rztdl.dl.helpers.constraints.Constraint = None, bias_constraint: rztdl.dl.helpers.constraints.Constraint = None, dropout_rate: float = 0.0, inputs: typing.Union[str, tensorflow.python.framework.ops.Tensor] = None, outputs: str = None, scopes: typing.Union[str, typing.List[str]] = None, trainable: bool = True)[source]

Bases: tensorflow.python.keras.layers.convolutional.SeparableConv1D, rztdl.dl.components.layers.layer.Layer

Depthwise separable 1D convolution.

Parameters:
  • name (str) – Name of Component
  • filters (int) – Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).
  • kernel_size (int) – A single integer specifying the spatial dimensions of the filters
  • strides (int) – A single integer specifying the strides of the convolution
  • padding (Padding) – VALID/SAME
  • data_format (DataFormat) – Ordering of the dimensions in the inputs. “channels_last”: (batch, height, width, channels) “channels_first”: (batch, channels, height, width)
  • dilation_rate (int) – A single integer, specifying the dilation rate to use for dilated convolution
  • depth_multiplier (int) – The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to num_filters_in * depth_multiplier
  • activation (Activation) – Activation function
  • use_bias (bool) – Boolean, whether the layer uses a bias
  • depthwise_initializer (Initializer) – An initializer for the depthwise convolution kernel
  • pointwise_initializer (Initializer) – An initializer for the pointwise convolution kernel
  • bias_initializer (Initializer) – An initializer for the bias vector
  • depthwise_regularizer (Optional[Regularizer]) – Optional regularizer for the depthwise convolution kerne
  • pointwise_regularizer (Optional[Regularizer]) – Optional regularizer for the pointwise convolution kernel
  • bias_regularizer (Optional[Regularizer]) – Optional regularizer for the bias vector
  • activity_regularizer (Optional[Regularizer]) – Optional regularizer function for the output
  • depthwise_constraint (Optional[Constraint]) – Optional projection function to be applied to the depthwise kernel after being updated by an Optimizer
  • pointwise_constraint (Optional[Constraint]) – Optional projection function to be applied to the pointwise kernel after being updated by an Optimizer
  • bias_constraint (Optional[Constraint]) – Optional projection function to be applied to the bias after being updated by an Optimizer
  • dropout_rate (float) – Dropout rate
  • inputs (Union[str, Tensor, None]) – Input Tensor
  • outputs (Optional[str]) – Output Tensor
  • scopes (Union[str, List[str], None]) – list of Tags which can be used to train only specific layers during train
  • trainable (bool) – Boolean, if True the weights of this layer will be marked as trainable
create(inputs)[source]
parameter_validation(filters, kernel_size, strides, dilation_rate, bias_constraint)[source]
validate(inputs)[source]

rztdl.dl.components.layers.convolutional.separable_conv2d module

@created on: 2020-02-03,
@author: shubham,
@version: v0.0.1

Description:

Sphinx Documentation Status: Complete

class rztdl.dl.components.layers.convolutional.separable_conv2d.SeparableConv2D(name: str, filters: int, kernel_size: typing.Union[int, typing.List[int]] = (1, 1), strides: typing.Union[int, typing.List[int]] = (1, 1), padding: rztdl.dl.constants.string_constants.Padding = <Padding.VALID: 'VALID'>, data_format: rztdl.dl.constants.string_constants.DataFormat = <DataFormat.CHANNELS_LAST: 'CHANNELS_LAST'>, dilation_rate: typing.Union[int, typing.List[int]] = (1, 1), depth_multiplier: int = 1, activation: rztdl.dl.helpers.activations.Activation = <rztdl.dl.helpers.activations.Linear object>, use_bias: bool = True, depthwise_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, pointwise_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.GlorotUniform object>, bias_initializer: rztdl.dl.helpers.initializers.Initializer = <rztdl.dl.helpers.initializers.Zeros object>, depthwise_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, pointwise_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, bias_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, activity_regularizer: rztdl.dl.helpers.regularizers.Regularizer = None, depthwise_constraint: rztdl.dl.helpers.constraints.Constraint = None, pointwise_constraint: rztdl.dl.helpers.constraints.Constraint = None, bias_constraint: rztdl.dl.helpers.constraints.Constraint = None, dropout_rate: float = 0.0, inputs: typing.Union[str, tensorflow.python.framework.ops.Tensor] = None, outputs: str = None, trainable: bool = True, scopes: typing.Union[str, typing.List[str]] = None)[source]

Bases: tensorflow.python.keras.layers.convolutional.SeparableConv2D, rztdl.dl.components.layers.layer.Layer

Depthwise separable 2D convolution.

Parameters:
  • name (str) – Name of the component
  • filters (int) – Integer, the dimensionality of the output space
  • kernel_size (Union[int, List[int]]) – Specifies the height and width of the 2D convolution window.
  • strides (Union[int, List[int]]) – Specifies the strides of the convolution along the height and width.
  • padding (Padding) – VALID/SAME
  • data_format (DataFormat) – ordering of the dimensions in the inputs. “channels_last”: (batch, height, width, channels) “channels_first”: (batch, channels, height, width)
  • dilation_rate (Union[int, List[int]]) – An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution.
  • depth_multiplier (int) – The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to filters_in * depth_multiplier.
  • activation (Activation) – Acivation function
  • use_bias (bool) – Boolean, whether the layer uses a bias vector.
  • depthwise_initializer (Initializer) – Initializer for the depthwise kernel matrix.
  • pointwise_initializer (Initializer) – Initializer for the pointwise kernel matrix.
  • bias_initializer (Initializer) – Initializer for the bias vector.
  • depthwise_regularizer (Optional[Regularizer]) – Regularizer function applied to the depthwise kernel matrix.
  • pointwise_regularizer (Optional[Regularizer]) – Regularizer function applied to the pointwise kernel matrix.
  • bias_regularizer (Optional[Regularizer]) – Regularizer function applied to the bias vector.
  • activity_regularizer (Optional[Regularizer]) – Regularizer function applied to the output of the layer (its “activation”)..
  • depthwise_constraint (Optional[Constraint]) – Constraint function applied to the depthwise kernel matrix.
  • pointwise_constraint (Optional[Constraint]) – Constraint function applied to the pointwise kernel matrix.
  • bias_constraint (Optional[Constraint]) – Constraint function applied to the bias vector.
  • dropout_rate (float) – Rate of Dropout apply on output
  • inputs (Union[str, Tensor, None]) – Input Tensor
  • outputs (Optional[str]) – Output Tensor
  • trainable (bool) – Indicates if layer should to be trained or not
  • scopes (Union[str, List[str], None]) – list of Tags which can be used to train only specific layers during train
create(inputs)[source]
parameter_validation(filters, kernel_size, strides, dilation_rate, padding, bias_constraint)[source]
validate(inputs)[source]

Module contents

@created on: 2019-12-03, @author: Himaprasoon, @version: v0.0.1

Description:

Sphinx Documentation Status: