_base_ = './decoupled-solo_r50_fpn_3x_coco.py' # model settings model = dict( mask_head=dict( type='DecoupledSOLOLightHead', num_classes=80, in_channels=256, stacked_convs=4, feat_channels=256, strides=[8, 8, 16, 32, 32], scale_ranges=((1, 64), (32, 128), (64, 256), (128, 512), (256, 2048)), pos_scale=0.2, num_grids=[40, 36, 24, 16, 12], cls_down_index=0, loss_mask=dict( type='DiceLoss', use_sigmoid=True, activate=False, loss_weight=3.0), loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), norm_cfg=dict(type='GN', num_groups=32, requires_grad=True))) train_pipeline = [ dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict( type='RandomChoiceResize', scales=[(852, 512), (852, 480), (852, 448), (852, 416), (852, 384), (852, 352)], keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='PackDetInputs') ] test_pipeline = [ dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}), dict(type='Resize', scale=(852, 512), keep_ratio=True), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) val_dataloader = dict(dataset=dict(pipeline=test_pipeline)) test_dataloader = val_dataloader