loss_bbox=dict(type='RotatedIoULoss', mode='linear', loss_weight=2.0), with_objectness=False, exp_on_reg=True, share_conv=True, pred_kernel_size=1, use_hbbox_loss=False, scale_angle=False, loss_angle=None, norm_cfg=dict(type='SyncBN'), act_cfg=dict(type='SiLU')), train_cfg...
type='mmdet.MlvlPointGenerator'), angle_version='le90', bbox_coder=dict( angle_version='le90', type='DistanceAnglePointCoder'), exp_on_reg=True, feat_channels=256, in_channels=256, loss_angle=None, loss_bbox=dict( loss_weight=2.0, mode='linear', type='RotatedIoULoss'), loss_cls...
( beta=2.0, loss_weight=1.0, type='mmdet.QualityFocalLoss', use_sigmoid=True), norm_cfg=dict(type='SyncBN'), num_classes=3, pred_kernel_size=1, scale_angle=False, share_conv=True, stacked_convs=2, type='RotatedRTMDetSepBNHead', use_hbbox_loss=False, with_objectness=False), ...
通过组合use_hbbox_loss和loss_angle可以控制旋转框训练时的回归损失计算方式,共有三种组合方式: use_hbbox_loss=False且loss_angle为 None. 此时框预测和角度预测进行合并,直接对旋转框预测进行回归,此时loss_bbox应当设定为旋转框损失,例如RotatedIoULoss。 这种方案和水平检测模型的回归方式基本一致,只是多了额外...
The spray sprinklers 360 degree rotate Alloy stainless steel 22 24 26 28 30 32 mm diameter nozzles has the characteristics of uniform rotation, small pressure loss, stable and reliable rotation, etc. The spray gun is made of brass, aluminum...
angle_range='oc', # The angle version of box coder. norm_factor=None, # The norm factor of box coder. edge_swap=False, # The edge swap flag of box coder. proj_xy=False, # The project flag of box coder. target_means=(0.0, 0.0, 0.0, 0.0, 0.0), # The target means used to ...
https://github.com/open-mmlab/mmrotate/blob/dev-1.x/mmrotate/models/task_modules/coders/distance_angle_point_coder.py utils part 1 https://github.com/open-mmlab/mmrotate/blob/dev-1.x/mmrotate/models/utils/enn.py https://github.com/open-mmlab/mmrotate/blob/dev-1.x/mmrotate/models/uti...
angle_version=angle_version, norm_factor=2, edge_swap=True, target_means=(.0, .0, .0, .0, .0), target_stds=(0.1, 0.1, 0.2, 0.2, 0.1)), reg_class_agnostic=True, loss_cls=dict( type='mmdet.CrossEntropyLoss', use_sigmoid=False, ...
angle_range='oc', norm_factor=None, edge_swap=False, proj_xy=False, target_means=(0.0, 0.0, 0.0, 0.0, 0.0), target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)), loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, ...
angle_version=angle_version, norm_factor=None, edge_swap=True, proj_xy=True, target_means=(.0, .0, .0, .0, .0), target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)), loss_cls=dict( type='mmdet.FocalLoss', use_sigmoid=True, gamma=2.0, ...