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)¶ FastRCNN layer
- Parameters
- namestring, optional
Specifies the name of the layer.
- actstring, optional
Specifies the activation function. Valid Values: AUTO, IDENTITY, Default: AUTO
- class_numberint, optional
Specifies the number of categories for the objects in the layer Default: 20
- detection_thresholdfloat, optional
Specifies the threshold for object detection. Default: 0.5
- max_label_per_imageint, optional
Specifies the maximum number of labels per training image. Default: 200
- max_object_numint, optional
Specifies the maximum number of object to detect Default: 50
- nms_iou_thresholdfloat, optional
Specifies the IOU threshold of maximum suppression in object detection Default: 0.3
- src_layersiter-of-Layers, optional
Specifies the layers directed to this layer.
- Returns
-
__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
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