def __init__(self, cfg):
super(RPNModule, self).__init__()
self.cfg = cfg.clone()
anchor_generator = make_anchor_generator(cfg)
in_channels = cfg.MODEL.BACKBONE.OUT_CHANNELS
rpn_head = registry.RPN_HEADS[cfg.MODEL.RPN.RPN_HEAD]
head = rpn_head(cfg, in_channels,
anchor_generator.num_anchors_per_location())
rpn_box_coder = BoxCoder3D()
box_selector_train = make_rpn_postprocessor(cfg,
rpn_box_coder,
is_train=True)
box_selector_test = make_rpn_postprocessor(cfg,
rpn_box_coder,
is_train=False)
loss_evaluator = make_rpn_loss_evaluator(cfg, rpn_box_coder)
self.seperate_classifier = SeperateClassifier(
cfg.MODEL.SEPARATE_CLASSES_ID, len(cfg.INPUT.CLASSES))
self.box_coder = rpn_box_coder
self.anchor_generator = anchor_generator
self.head = head
self.box_selector_train = box_selector_train
self.box_selector_test = box_selector_test
self.loss_evaluator = loss_evaluator
self.add_gt_proposals = cfg.MODEL.RPN.ADD_GT_PROPOSALS
def __init__(self, cfg):
super(RPNModule, self).__init__()
self.cfg = cfg.clone()
anchor_generator = make_anchor_generator(cfg)
in_channels = cfg.SPARSE3D.nPlaneMap
rpn_head = registry.RPN_HEADS[cfg.MODEL.RPN.RPN_HEAD]
head = rpn_head(cfg, in_channels,
anchor_generator.num_anchors_per_location())
rpn_box_coder = BoxCoder3D(is_corner_roi=False, weights=None)
box_selector_train = make_rpn_postprocessor(cfg,
rpn_box_coder,
is_train=True)
box_selector_test = make_rpn_postprocessor(cfg,
rpn_box_coder,
is_train=False)
loss_evaluator = make_rpn_loss_evaluator(cfg, rpn_box_coder)
class_specific = cfg.MODEL.CLASS_SPECIFIC
self.seperate_classifier = SeperateClassifier(
cfg.MODEL.SEPARATE_CLASSES_ID, len(cfg.INPUT.CLASSES),
class_specific, 'RPN')
self.box_coder = rpn_box_coder
self.anchor_generator = anchor_generator
self.head = head
self.box_selector_train = box_selector_train
self.box_selector_test = box_selector_test
self.loss_evaluator = loss_evaluator
self.add_gt_proposals = cfg.MODEL.RPN.ADD_GT_PROPOSALS
def make_roi_box_post_processor(cfg):
use_fpn = cfg.MODEL.ROI_HEADS.USE_FPN
bbox_reg_weights = cfg.MODEL.ROI_HEADS.BBOX_REG_WEIGHTS
box_coder = BoxCoder3D(weights=bbox_reg_weights)
score_thresh = cfg.MODEL.ROI_HEADS.SCORE_THRESH
nms_thresh = cfg.MODEL.ROI_HEADS.NMS
nms_aug_thickness = cfg.MODEL.ROI_HEADS.NMS_AUG_THICKNESS_Y_Z
detections_per_img = cfg.MODEL.ROI_HEADS.DETECTIONS_PER_IMG
postprocessor = PostProcessor(score_thresh,
nms_thresh,
nms_aug_thickness=nms_aug_thickness,
detections_per_img=detections_per_img,
box_coder=box_coder)
return postprocessor
def make_roi_box_loss_evaluator(cfg):
matcher = Matcher(
cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD,
cfg.MODEL.ROI_HEADS.BG_IOU_THRESHOLD,
allow_low_quality_matches=False,
)
bbox_reg_weights = cfg.MODEL.ROI_HEADS.BBOX_REG_WEIGHTS
box_coder = BoxCoder3D(is_corner_roi=cfg.MODEL.CORNER_ROI,
weights=bbox_reg_weights)
fg_bg_sampler = BalancedPositiveNegativeSampler(
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE,
cfg.MODEL.ROI_HEADS.POSITIVE_FRACTION)
yaw_loss_mode = cfg.MODEL.LOSS.YAW_MODE
add_gt_proposals = cfg.MODEL.RPN.ADD_GT_PROPOSALS
ay = cfg.MODEL.ROI_HEADS.LABEL_AUG_THICKNESS_Y_TAR_ANC
az = cfg.MODEL.ROI_HEADS.LABEL_AUG_THICKNESS_Z_TAR_ANC
aug_thickness = {
'target_Y': ay[0],
'anchor_Y': ay[1],
'target_Z': az[0],
'anchor_Z': az[1]
}
in_classes = cfg.INPUT.CLASSES
num_input_classes = len(in_classes)
seperate_classes = cfg.MODEL.SEPARATE_CLASSES_ID
class_specific = cfg.MODEL.CLASS_SPECIFIC
seperate_classifier = SeperateClassifier(seperate_classes,
num_input_classes, class_specific,
'ROI_LOSS')
loss_evaluator = FastRCNNLossComputation(matcher,
fg_bg_sampler,
box_coder,
yaw_loss_mode,
add_gt_proposals,
aug_thickness,
seperate_classifier,
class_specific=class_specific)
return loss_evaluator, seperate_classifier
def __init__(self,
score_thresh=0.05,
nms=0.5,
nms_aug_thickness=None,
detections_per_img=100,
box_coder=None):
"""
Arguments:
score_thresh (float)
nms (float)
detections_per_img (int)
box_coder (BoxCoder3D)
"""
super(PostProcessor, self).__init__()
self.score_thresh = score_thresh
self.nms = nms
self.detections_per_img = detections_per_img
if box_coder is None:
box_coder = BoxCoder3D(weights=(10., 10., 5., 5.))
self.box_coder = box_coder
self.nms_aug_thickness = nms_aug_thickness