def __init__(self, cfg, box_coder):
self.cfg = cfg
self.cls_loss_func = SigmoidFocalLoss(cfg.MODEL.ATSS.LOSS_GAMMA,
cfg.MODEL.ATSS.LOSS_ALPHA)
self.centerness_loss_func = nn.BCEWithLogitsLoss(reduction="sum")
self.matcher = Matcher(cfg.MODEL.ATSS.FG_IOU_THRESHOLD,
cfg.MODEL.ATSS.BG_IOU_THRESHOLD, True)
self.box_coder = box_coder
def make_roi_mask_loss_evaluator(cfg):
matcher = Matcher(
cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD,
cfg.MODEL.ROI_HEADS.BG_IOU_THRESHOLD,
allow_low_quality_matches=False,
)
loss_evaluator = MaskRCNNLossComputation(
matcher, cfg.MODEL.ROI_MASK_HEAD.RESOLUTION)
return loss_evaluator
def make_rpn_loss_evaluator(cfg, box_coder):
matcher = Matcher(
cfg.MODEL.RPN.FG_IOU_THRESHOLD,
cfg.MODEL.RPN.BG_IOU_THRESHOLD,
allow_low_quality_matches=True,
)
fg_bg_sampler = BalancedPositiveNegativeSampler(
cfg.MODEL.RPN.BATCH_SIZE_PER_IMAGE, cfg.MODEL.RPN.POSITIVE_FRACTION)
loss_evaluator = RPNLossComputation(matcher, fg_bg_sampler, box_coder,
generate_rpn_labels)
return loss_evaluator
def __init__(self, cfg, box_coder):
self.cfg = cfg
if cfg.MODEL.ATSS.CLS_LOSS == 'FOCAL':
self.cls_loss_func = SigmoidFocalLoss(cfg.MODEL.ATSS.LOSS_GAMMA,
cfg.MODEL.ATSS.LOSS_ALPHA)
else:
self.cls_loss_func = SigmoidWarpageLoss(cfg.MODEL.ATSS.LOSS_GAMMA,
cfg.MODEL.ATSS.LOSS_ALPHA,
cfg.MODEL.ATSS.LOSS_BETA)
#self.centerness_loss_func = nn.BCEWithLogitsLoss(reduction="sum")
self.matcher = Matcher(cfg.MODEL.ATSS.FG_IOU_THRESHOLD,
cfg.MODEL.ATSS.BG_IOU_THRESHOLD, True)
self.box_coder = box_coder
def make_roi_keypoint_loss_evaluator(cfg):
matcher = Matcher(
cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD,
cfg.MODEL.ROI_HEADS.BG_IOU_THRESHOLD,
allow_low_quality_matches=False,
)
fg_bg_sampler = BalancedPositiveNegativeSampler(
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE,
cfg.MODEL.ROI_HEADS.POSITIVE_FRACTION)
resolution = cfg.MODEL.ROI_KEYPOINT_HEAD.RESOLUTION
loss_evaluator = KeypointRCNNLossComputation(matcher, fg_bg_sampler,
resolution)
return loss_evaluator
def make_retinanet_loss_evaluator(cfg, box_coder):
matcher = Matcher(
cfg.MODEL.RETINANET.FG_IOU_THRESHOLD,
cfg.MODEL.RETINANET.BG_IOU_THRESHOLD,
allow_low_quality_matches=True,
)
sigmoid_focal_loss = SigmoidFocalLoss(cfg.MODEL.RETINANET.LOSS_GAMMA,
cfg.MODEL.RETINANET.LOSS_ALPHA)
loss_evaluator = RetinaNetLossComputation(
matcher,
box_coder,
generate_retinanet_labels,
sigmoid_focal_loss,
bbox_reg_beta=cfg.MODEL.RETINANET.BBOX_REG_BETA,
regress_norm=cfg.MODEL.RETINANET.BBOX_REG_WEIGHT,
)
return loss_evaluator
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 = BoxCoder(weights=bbox_reg_weights)
fg_bg_sampler = BalancedPositiveNegativeSampler(
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE,
cfg.MODEL.ROI_HEADS.POSITIVE_FRACTION)
cls_agnostic_bbox_reg = cfg.MODEL.CLS_AGNOSTIC_BBOX_REG
loss_evaluator = FastRCNNLossComputation(matcher, fg_bg_sampler, box_coder,
cls_agnostic_bbox_reg)
return loss_evaluator
def __init__(self, cfg, box_coder):
self.cfg = cfg
self.cls_loss_func = SigmoidFocalLoss(self.cfg.loss_gamma, self.cfg.loss_alpha)
self.centerness_loss_func = nn.BCEWithLogitsLoss(reduction="sum")
self.matcher = Matcher(self.cfg.pos_thre, self.cfg.neg_thre, True)
self.box_coder = box_coder
