dlpy.layers.FastRCNN

class dlpy.layers.FastRCNN(name=None, act='AUTO', class_number=20, detection_threshold=0.5, max_label_per_image=200, max_object_num=50, nms_iou_threshold=0.3, src_layers=None, **kwargs)

Bases: dlpy.layers.Layer

FastRCNN layer

Parameters:
name : string, optional

Specifies the name of the layer.

act : string, optional

Specifies the activation function.
Valid Values: AUTO, IDENTITY,
Default: AUTO

class_number : int, optional

Specifies the number of categories for the objects in the layer
Default: 20

detection_threshold : float, optional

Specifies the threshold for object detection.
Default: 0.5

max_label_per_image : int, optional

Specifies the maximum number of labels per training image.
Default: 200

max_object_num : int, optional

Specifies the maximum number of object to detect
Default: 50

nms_iou_threshold : float, optional

Specifies the IOU threshold of maximum suppression in object detection
Default: 0.3

src_layers : iter-of-Layers, optional

Specifies the layers directed to this layer.

Returns:
FastRCNN
__init__(name=None, act='AUTO', class_number=20, detection_threshold=0.5, max_label_per_image=200, max_object_num=50, nms_iou_threshold=0.3, src_layers=None, **kwargs)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([name, act, class_number, …]) 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