def __init__(self, cfg):
self.cls_loss_func = SigmoidFocalLoss(cfg.MODEL.FCOS.LOSS_GAMMA,
cfg.MODEL.FCOS.LOSS_ALPHA)
# we make use of IOU Loss for bounding boxes regression,
# but we found that L1 in log scale can yield a similar performance
self.box_reg_loss_func = IOULoss()
self.centerness_loss_func = nn.BCEWithLogitsLoss()
def __init__(self, cfg):
self.cls_loss_func = SigmoidFocalLoss(cfg.MODEL.FCOS.LOSS_GAMMA,
cfg.MODEL.FCOS.LOSS_ALPHA)
self.fpn_strides = cfg.MODEL.FCOS.FPN_STRIDES
self.center_sampling_radius = cfg.MODEL.FCOS.CENTER_SAMPLING_RADIUS
self.iou_loss_type = cfg.MODEL.FCOS.IOU_LOSS_TYPE
self.norm_reg_targets = cfg.MODEL.FCOS.NORM_REG_TARGETS
# we make use of IOU Loss for bounding boxes regression,
# but we found that L1 in log scale can yield a similar performance
self.box_reg_loss_func = IOULoss(self.iou_loss_type)
self.centerness_loss_func = nn.BCEWithLogitsLoss(reduction="sum")
def __init__(self, cfg):
self.cls_loss_func = SigmoidFocalLoss(
cfg.MODEL.FCOS.LOSS_GAMMA,
cfg.MODEL.FCOS.LOSS_ALPHA
)
# class_weights = torch.ones(cfg.MODEL.FCOS.NUM_CLASSES).cuda()
# class_weights[1] = 0.4
# self.cls_loss_func_ce = nn.CrossEntropyLoss(reduction="sum")
self.fpn_strides = cfg.MODEL.FCOS.FPN_STRIDES
self.center_sampling_radius = cfg.MODEL.FCOS.CENTER_SAMPLING_RADIUS
self.iou_loss_type = cfg.MODEL.FCOS.IOU_LOSS_TYPE
self.norm_reg_targets = cfg.MODEL.FCOS.NORM_REG_TARGETS
# we make use of IOU Loss for bounding boxes regression,
# but we found that L1 in log scale can yield a similar performance
self.box_reg_loss_func = IOULoss(self.iou_loss_type)
self.f1_loss = F1_Loss(num_classes=cfg.MODEL.FCOS.NUM_CLASSES)
def __init__(self, cfg, proposal_matcher, fg_bg_sampler, box_coder,
generate_labels_func):
"""
Arguments:
proposal_matcher (Matcher)
fg_bg_sampler (BalancedPositiveNegativeSampler)
box_coder (BoxCoder)
"""
# self.target_preparator = target_preparator
self.proposal_matcher = proposal_matcher
self.fg_bg_sampler = fg_bg_sampler
self.box_coder = box_coder
self.copied_fields = []
self.iou_loss_type = cfg.MODEL.FCOS.IOU_LOSS_TYPE
self.generate_labels_func = generate_labels_func
self.discard_cases = ['not_visibility', 'between_thresholds']
self.box_reg_loss_func = IOULoss(self.iou_loss_type)
def __init__(self, cfg):
self.cls_loss_func = SigmoidFocalLoss(cfg.MODEL.EMBED_MASK.LOSS_GAMMA,
cfg.MODEL.EMBED_MASK.LOSS_ALPHA)
self.fpn_strides = cfg.MODEL.EMBED_MASK.FPN_STRIDES
self.center_on = cfg.MODEL.EMBED_MASK.CENTER_ON
self.center_sampling_radius = cfg.MODEL.EMBED_MASK.CENTER_POS_RADIOS
self.iou_loss_type = cfg.MODEL.EMBED_MASK.IOU_LOSS_TYPE
self.norm_reg_targets = cfg.MODEL.EMBED_MASK.NORM_REG_TARGETS
self.box_reg_loss_func = IOULoss(self.iou_loss_type)
self.centerness_loss_func = nn.BCEWithLogitsLoss(reduction="sum")
########## mask prediction ############
self.mask_loss_func = LovaszHinge(reduction='none')
self.mask_scale_factor = cfg.MODEL.EMBED_MASK.MASK_SCALE_FACTOR
self.object_sizes_of_interest = [
[-1, cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[0]],
[
cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[0],
cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[1]
],
[
cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[1],
cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[2]
],
[
cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[2],
cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[3]
], [cfg.MODEL.EMBED_MASK.FPN_INTEREST_SPLIT[3], INF]
]
self.sample_in_mask = cfg.MODEL.EMBED_MASK.SAMPLE_IN_MASK
self.sample_pos_iou_th = cfg.MODEL.EMBED_MASK.SAMPLE_POS_IOU_TH
self.box_padding = cfg.MODEL.EMBED_MASK.BOX_PADDING
self.fix_margin = cfg.MODEL.EMBED_MASK.FIX_MARGIN
prior_margin = cfg.MODEL.EMBED_MASK.PRIOR_MARGIN
self.init_margin = -math.log(0.5) / (prior_margin**2)
self.loss_mask_alpha = cfg.MODEL.EMBED_MASK.LOSS_MASK_ALPHA
self.loss_smooth_alpha = cfg.MODEL.EMBED_MASK.LOSS_SMOOTH_ALPHA
