dlpy.layers.RegionProposal

class dlpy.layers.RegionProposal(anchor_ratio, anchor_scale, name=None, act='AUTO', anchor_num_to_sample=256, base_anchor_size=16, coord_type='COCO', do_RPN_only=False, max_label_per_image=200, proposed_roi_num_score=300, proposed_roi_num_train=2000, roi_train_sample_num=128, src_layers=None, **kwargs)

Bases: dlpy.layers.Layer

Region proposal layer

Parameters:
name : string, optional

Specifies the name of the layer.

anchor_ratio : iter-of-float

Specifies the anchor height and width ratios (h/w) used.

anchor_scale : iter-of-float

Specifies the anchor scales used based on base_anchor_size

act : string, optional

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

anchor_num_to_sample : int, optional

Specifies the number of anchors to sample for training the region proposal network
Default: 256

base_anchor_size : int, optional

Specifies the basic anchor size in width and height (in pixels) in the original input image dimension
Default: 16

coord_type : int, optional

Specifies the coordinates format type in the input label and detection result.
Valid Values: RECT, COCO, YOLO
Default: COCO

do_RPN_only : Boolean, optional

Specifies that in the model, only Region Proposal task is to be done in the model, not including the Fast RCNN task
Default: FALSE

max_label_per_image: int, optional

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

proposed_roi_num_score: int, optional

Specifies the number of ROI (Region of Interest) to propose in the scoring phase
Default: 300

proposed_roi_num_train: int, optional

Specifies the number of ROI (Region of Interest) to propose used for RPN training, and also the pool to sample from for FastRCNN Training in the training phase
Default: 2000

roi_train_sample_num: int, optional

Specifies the number of ROIs(Regions of Interests) to sample after NMS(Non-maximum Suppression) is performed in the training phase.
Default: 128

src_layers : iter-of-Layers, optional

Specifies the layers directed to this layer.

Returns:
RegionProposal
__init__(anchor_ratio, anchor_scale, name=None, act='AUTO', anchor_num_to_sample=256, base_anchor_size=16, coord_type='COCO', do_RPN_only=False, max_label_per_image=200, proposed_roi_num_score=300, proposed_roi_num_train=2000, roi_train_sample_num=128, src_layers=None, **kwargs)

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

Methods

__init__(anchor_ratio, anchor_scale[, name, …]) 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