support psc, r3det, s2anet

configs/ars_detr/csl_detr_r50_1x_rsg.py

@@ -147,3 +147,4 @@
 
 checkpoint_config = dict(interval=1, max_keep_ckpts=1)
 evaluation = dict(interval=6, metric='mAP')
+find_unused_parameters=True

configs/cfa/cfa_r50_fpn_1x_rsg_le135.py

@@ -0,0 +1,6 @@
+_base_ = ['../rotated_reppoints/rotated_reppoints_r50_fpn_1x_rsg_le135.py']
+
+model = dict(
+ bbox_head=dict(use_reassign=True),
+ train_cfg=dict(
+ refine=dict(assigner=dict(pos_iou_thr=0.1, neg_iou_thr=0.1))))

configs/psc/rotated_fcos_psc_r50_fpn_1x_rsg_le90.py

@@ -0,0 +1,37 @@
+_base_ = '../rotated_fcos/rotated_fcos_sep_angle_r50_fpn_1x_rsg_le90.py'
+angle_version = 'le90'
+
+# model settings
+model = dict(
+ bbox_head=dict(
+ type='PSCRFCOSHead',
+ num_classes=48,
+ in_channels=256,
+ stacked_convs=4,
+ feat_channels=256,
+ strides=[8, 16, 32, 64, 128],
+ center_sampling=True,
+ center_sample_radius=1.5,
+ norm_on_bbox=True,
+ centerness_on_reg=True,
+ separate_angle=True,
+ scale_angle=True,
+ bbox_coder=dict(
+ type='DistanceAnglePointCoder', angle_version=angle_version),
+ h_bbox_coder=dict(type='DistancePointBBoxCoder'),
+ angle_coder=dict(
+ type='PSCCoder',
+ angle_version=angle_version,
+ dual_freq=True,
+ num_step=3),
+ loss_cls=dict(
+ type='FocalLoss',
+ use_sigmoid=True,
+ gamma=2.0,
+ alpha=0.25,
+ loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=1.0),
+ loss_centerness=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_angle=dict(
+ type='SmoothFocalLoss', gamma=2.0, alpha=0.25, loss_weight=0.2)), )

configs/r3det/r3det_r50_fpn_1x_rsg_oc.py

@@ -0,0 +1,149 @@
+_base_ = [
+ '../_base_/datasets/rsg.py', '../_base_/schedules/schedule_1x.py',
+ '../_base_/default_runtime.py'
+]
+
+angle_version = 'oc'
+model = dict(
+ type='R3DetCrop',
+ backbone=dict(
+ type='ResNet',
+ depth=50,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ zero_init_residual=False,
+ norm_cfg=dict(type='BN', requires_grad=True),
+ norm_eval=True,
+ style='pytorch',
+ init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ start_level=1,
+ add_extra_convs='on_input',
+ num_outs=5),
+ bbox_head=dict(
+ type='RotatedRetinaHead',
+ num_classes=48,
+ in_channels=256,
+ stacked_convs=4,
+ feat_channels=256,
+ anchor_generator=dict(
+ type='RotatedAnchorGenerator',
+ octave_base_scale=4,
+ scales_per_octave=3,
+ ratios=[1.0, 0.5, 2.0],
+ strides=[8, 16, 32, 64, 128]),
+ bbox_coder=dict(
+ type='DeltaXYWHAOBBoxCoder',
+ angle_range=angle_version,
+ norm_factor=None,
+ edge_swap=False,
+ proj_xy=False,
+ target_means=(.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,
+ loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
+ frm_cfgs=[dict(in_channels=256, featmap_strides=[8, 16, 32, 64, 128])],
+ num_refine_stages=1,
+ refine_heads=[
+ dict(
+ type='RotatedRetinaRefineHead',
+ num_classes=48,
+ in_channels=256,
+ stacked_convs=4,
+ feat_channels=256,
+ assign_by_circumhbbox=None,
+ anchor_generator=dict(
+ type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
+ bbox_coder=dict(
+ type='DeltaXYWHAOBBoxCoder',
+ angle_range=angle_version,
+ 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,
+ loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0))
+ ],
+ train_cfg=dict(
+ s0=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.4,
+ min_pos_iou=0,
+ ignore_iof_thr=-1,
+ iou_calculator=dict(type='RBboxOverlaps2D')),
+ allowed_border=-1,
+ pos_weight=-1,
+ debug=False),
+ sr=[
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.5,
+ min_pos_iou=0,
+ ignore_iof_thr=-1,
+ iou_calculator=dict(type='RBboxOverlaps2D')),
+ allowed_border=-1,
+ pos_weight=-1,
+ debug=False)
+ ],
+ stage_loss_weights=[1.0]),
+ test_cfg=dict(
+ nms_pre=2000,
+ min_bbox_size=0,
+ score_thr=0.05,
+ nms=dict(iou_thr=0.1),
+ max_per_img=2000))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='RResize', img_scale=(1024, 1024)),
+ dict(
+ type='RRandomFlip',
+ flip_ratio=[0.25, 0.25, 0.25],
+ direction=['horizontal', 'vertical', 'diagonal'],
+ version=angle_version),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+data = dict(
+ train=dict(pipeline=train_pipeline, version=angle_version),
+ val=dict(version=angle_version),
+ test=dict(version=angle_version))
+
+optimizer = dict(
+ _delete_=True,
+ type='AdamW',
+ lr=0.0001,
+ betas=(0.9, 0.999),
+ weight_decay=0.05,
+ paramwise_cfg=dict(
+ custom_keys=dict(
+ absolute_pos_embed=dict(decay_mult=0.0),
+ relative_position_bias_table=dict(decay_mult=0.0),
+ norm=dict(decay_mult=0.0))))
+
+checkpoint_config = dict(interval=1, max_keep_ckpts=1)
+evaluation = dict(interval=6, metric='mAP')

configs/rotated_atss/rotated_atss_obb_r50_fpn_1x_rsg_le90.py

@@ -0,0 +1,20 @@
+_base_ = ['../rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90.py']
+
+angle_version = 'le90'
+model = dict(
+ bbox_head=dict(
+ type='RotatedATSSHead',
+ anchor_generator=dict(
+ type='RotatedAnchorGenerator',
+ octave_base_scale=4,
+ scales_per_octave=1,
+ ratios=[1.0],
+ strides=[8, 16, 32, 64, 128]),
+ ),
+ train_cfg=dict(
+ assigner=dict(
+ _delete_=True,
+ type='ATSSObbAssigner',
+ topk=9,
+ angle_version=angle_version,
+ iou_calculator=dict(type='RBboxOverlaps2D'))))

configs/rotated_fcos/rotated_fcos_csl_gaussian_r50_fpn_1x_rsg_le90.py

@@ -0,0 +1,30 @@
+_base_ = 'rotated_fcos_sep_angle_r50_fpn_1x_rsg_le90.py'
+angle_version = 'le90'
+
+# model settings
+model = dict(
+ bbox_head=dict(
+ type='CSLRFCOSHead',
+ center_sampling=True,
+ center_sample_radius=1.5,
+ norm_on_bbox=True,
+ centerness_on_reg=True,
+ separate_angle=True,
+ scale_angle=False,
+ angle_coder=dict(
+ type='CSLCoder',
+ angle_version=angle_version,
+ omega=1,
+ window='gaussian',
+ radius=1),
+ loss_cls=dict(
+ type='FocalLoss',
+ use_sigmoid=True,
+ gamma=2.0,
+ alpha=0.25,
+ loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=1.0),
+ loss_centerness=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_angle=dict(
+ type='SmoothFocalLoss', gamma=2.0, alpha=0.25, loss_weight=0.2)), )

configs/rotated_fcos/rotated_fcos_sep_angle_r50_fpn_1x_rsg_le90.py

@@ -0,0 +1,98 @@
+_base_ = [
+ '../_base_/datasets/rsg.py', '../_base_/schedules/schedule_1x.py',
+ '../_base_/default_runtime.py'
+]
+angle_version = 'le90'
+
+# model settings
+model = dict(
+ type='RotatedFCOS',
+ backbone=dict(
+ type='ResNet',
+ depth=50,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ zero_init_residual=False,
+ norm_cfg=dict(type='BN', requires_grad=True),
+ norm_eval=True,
+ style='pytorch',
+ init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ start_level=1,
+ add_extra_convs='on_output', # use P5
+ num_outs=5,
+ relu_before_extra_convs=True),
+ bbox_head=dict(
+ type='RotatedFCOSHead',
+ num_classes=48,
+ in_channels=256,
+ stacked_convs=4,
+ feat_channels=256,
+ strides=[8, 16, 32, 64, 128],
+ center_sampling=True,
+ center_sample_radius=1.5,
+ norm_on_bbox=True,
+ centerness_on_reg=True,
+ separate_angle=True,
+ scale_angle=True,
+ bbox_coder=dict(
+ type='DistanceAnglePointCoder', angle_version=angle_version),
+ h_bbox_coder=dict(type='DistancePointBBoxCoder'),
+ loss_cls=dict(
+ type='FocalLoss',
+ use_sigmoid=True,
+ gamma=2.0,
+ alpha=0.25,
+ loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=1.0),
+ loss_angle=dict(type='L1Loss', loss_weight=0.2),
+ loss_centerness=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+ # training and testing settings
+ train_cfg=None,
+ test_cfg=dict(
+ nms_pre=2000,
+ min_bbox_size=0,
+ score_thr=0.05,
+ nms=dict(iou_thr=0.1),
+ max_per_img=2000))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True),
+ dict(type='RResize', img_scale=(1024, 1024)),
+ dict(
+ type='RRandomFlip',
+ flip_ratio=[0.25, 0.25, 0.25],
+ direction=['horizontal', 'vertical', 'diagonal'],
+ version=angle_version),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+data = dict(
+ train=dict(pipeline=train_pipeline, version=angle_version),
+ val=dict(version=angle_version),
+ test=dict(version=angle_version))
+
+optimizer = dict(
+ _delete_=True,
+ type='AdamW',
+ lr=0.0001,
+ betas=(0.9, 0.999),
+ weight_decay=0.05,
+ paramwise_cfg=dict(
+ custom_keys=dict(
+ absolute_pos_embed=dict(decay_mult=0.0),
+ relative_position_bias_table=dict(decay_mult=0.0),
+ norm=dict(decay_mult=0.0))))
+
+checkpoint_config = dict(interval=1, max_keep_ckpts=1)
+evaluation = dict(interval=6, metric='mAP')