dlpy.layers.GroupConv2d¶
-
class
dlpy.layers.
GroupConv2d
(n_filters, n_groups=1, width=None, height=None, stride=1, name=None, stride_horizontal=None, stride_vertical=None, padding=None, padding_width=None, padding_height=None, act='relu', fcmp_act=None, init=None, std=None, mean=None, truncation_factor=None, init_bias=None, dropout=None, include_bias=True, src_layers=None, **kwargs)¶ Group Convolution layer in 2D
- Parameters
- n_filtersint
Specifies the number of filters for the layer.
- n_groupsint
Specifies the number of groups for the layer.
- widthint
Specifies the width of the kernel.
- heightint
Specifies the height of the kernel.
- strideint, optional
Specifies the step size for the moving window of the kernel over the input data. Default: 1
- namestring, optional
Specifies the name of the convolution layer.
- stride_horizontalint, optional
Specifies the horizontal stride.
- stride_verticalint, optional
Specifies the vertical stride.
- paddingint, optional
Specifies the padding size, assuming equal padding vertically and horizontally.
- padding_widthint, optional
Specifies the length of the horizontal padding.
- padding_heightint, optional
Specifies the length of the vertical padding.
- actstring, optional
Specifies the activation function. Valid Values: AUTO, IDENTITY, LOGISTIC, SIGMOID, TANH, RECTIFIER, RELU, SOFPLUS, ELU, LEAKY, FCMP Default: RELU
- fcmp_actstring, optional
Specifies the FCMP activation function for the layer.
- initstring, optional
Specifies the initialization scheme for the layer. Valid Values: XAVIER, UNIFORM, NORMAL, CAUCHY, XAVIER1, XAVIER2, MSRA, MSRA1, MSRA2 Default: XAVIER
- stdfloat, optional
Specifies the standard deviation value when the
init
parameter is set to NORMAL.- meanfloat, optional
Specifies the mean value when the
init
parameter is set to NORMAL.- truncation_factorfloat, optional
Specifies the truncation threshold (truncationFactor x std), when the
init
parameter is set to NORMAL- init_biasfloat, optional
Specifies the initial bias for the layer.
- dropoutfloat, optional
Specifies the dropout rate. Default: 0
- include_biasbool, optional
Includes bias neurons (default).
- src_layersiter-of-Layers, optional
Specifies the layers directed to this layer.
- Returns
-
__init__
(n_filters, n_groups=1, width=None, height=None, stride=1, name=None, stride_horizontal=None, stride_vertical=None, padding=None, padding_width=None, padding_height=None, act='relu', fcmp_act=None, init=None, std=None, mean=None, truncation_factor=None, init_bias=None, dropout=None, include_bias=True, src_layers=None, **kwargs)¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__
(n_filters[, n_groups, width, …])Initialize self.
count_instances
()format_name
([block_num, local_count])Format the name of the layer
get_number_of_instances
()to_model_params
()Convert the model configuration to CAS action parameters
Attributes
can_be_last_layer
kernel_size
layer_id
num_bias
num_weights
number_of_instances
output_size
rnn_summary
Return a DataFrame containing the layer information for rnn models
summary
Return a DataFrame containing the layer information
type
type_desc
type_label