diff --git a/configs/_base_/models/cascade_mask_rcnn_swin_fpn.py b/configs/_base_/models/cascade_mask_rcnn_swin_fpn.py
new file mode 100644
index 0000000000000000000000000000000000000000..c8ae9235d0cf1e1fdc1781a253ea43d110dcfa35
--- /dev/null
+++ b/configs/_base_/models/cascade_mask_rcnn_swin_fpn.py
@@ -0,0 +1,207 @@
+# model settings
+model = dict(
+ type='CascadeRCNN',
+ pretrained=None,
+ backbone=dict(
+ type='SwinTransformer',
+ embed_dim=96,
+ depths=[2, 2, 6, 2],
+ num_heads=[3, 6, 12, 24],
+ window_size=7,
+ mlp_ratio=4.,
+ qkv_bias=True,
+ qk_scale=None,
+ drop_rate=0.,
+ attn_drop_rate=0.,
+ drop_path_rate=0.2,
+ ape=False,
+ patch_norm=True,
+ out_indices=(0, 1, 2, 3),
+ use_checkpoint=False),
+ neck=dict(
+ type='FPN',
+ in_channels=[96, 192, 384, 768],
+ out_channels=256,
+ num_outs=5),
+ rpn_head=dict(
+ type='RPNHead',
+ in_channels=256,
+ feat_channels=256,
+ anchor_generator=dict(
+ type='AnchorGenerator',
+ scales=[8],
+ ratios=[0.5, 1.0, 2.0],
+ strides=[4, 8, 16, 32, 64]),
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[.0, .0, .0, .0],
+ target_stds=[1.0, 1.0, 1.0, 1.0]),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+ roi_head=dict(
+ type='CascadeRoIHead',
+ num_stages=3,
+ stage_loss_weights=[1, 0.5, 0.25],
+ bbox_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ bbox_head=[
+ dict(
+ type='Shared2FCBBoxHead',
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2]),
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+ loss_weight=1.0)),
+ dict(
+ type='Shared2FCBBoxHead',
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1]),
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+ loss_weight=1.0)),
+ dict(
+ type='Shared2FCBBoxHead',
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067]),
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+ ],
+ mask_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ mask_head=dict(
+ type='FCNMaskHead',
+ num_convs=4,
+ in_channels=256,
+ conv_out_channels=256,
+ num_classes=80,
+ loss_mask=dict(
+ type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+ # model training and testing settings
+ train_cfg = dict(
+ rpn=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ match_low_quality=True,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False),
+ allowed_border=0,
+ pos_weight=-1,
+ debug=False),
+ rpn_proposal=dict(
+ nms_across_levels=False,
+ nms_pre=2000,
+ nms_post=2000,
+ max_per_img=2000,
+ nms=dict(type='nms', iou_threshold=0.7),
+ min_bbox_size=0),
+ rcnn=[
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ match_low_quality=False,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.6,
+ min_pos_iou=0.6,
+ match_low_quality=False,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.7,
+ min_pos_iou=0.7,
+ match_low_quality=False,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False)
+ ]),
+ test_cfg = dict(
+ rpn=dict(
+ nms_across_levels=False,
+ nms_pre=1000,
+ nms_post=1000,
+ max_per_img=1000,
+ nms=dict(type='nms', iou_threshold=0.7),
+ min_bbox_size=0),
+ rcnn=dict(
+ score_thr=0.05,
+ nms=dict(type='nms', iou_threshold=0.5),
+ max_per_img=100,
+ mask_thr_binary=0.5)))
diff --git a/configs/_base_/models/mask_rcnn_swin_fpn.py b/configs/_base_/models/mask_rcnn_swin_fpn.py
new file mode 100644
index 0000000000000000000000000000000000000000..e3d42197f4646cd9ecafac2095d3f8e079f0a729
--- /dev/null
+++ b/configs/_base_/models/mask_rcnn_swin_fpn.py
@@ -0,0 +1,127 @@
+# model settings
+model = dict(
+ type='MaskRCNN',
+ pretrained=None,
+ backbone=dict(
+ type='SwinTransformer',
+ embed_dim=96,
+ depths=[2, 2, 6, 2],
+ num_heads=[3, 6, 12, 24],
+ window_size=7,
+ mlp_ratio=4.,
+ qkv_bias=True,
+ qk_scale=None,
+ drop_rate=0.,
+ attn_drop_rate=0.,
+ drop_path_rate=0.2,
+ ape=False,
+ patch_norm=True,
+ out_indices=(0, 1, 2, 3),
+ use_checkpoint=False),
+ neck=dict(
+ type='FPN',
+ in_channels=[96, 192, 384, 768],
+ out_channels=256,
+ num_outs=5),
+ rpn_head=dict(
+ type='RPNHead',
+ in_channels=256,
+ feat_channels=256,
+ anchor_generator=dict(
+ type='AnchorGenerator',
+ scales=[8],
+ ratios=[0.5, 1.0, 2.0],
+ strides=[4, 8, 16, 32, 64]),
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[.0, .0, .0, .0],
+ target_stds=[1.0, 1.0, 1.0, 1.0]),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+ roi_head=dict(
+ type='StandardRoIHead',
+ bbox_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ bbox_head=dict(
+ type='Shared2FCBBoxHead',
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2]),
+ reg_class_agnostic=False,
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+ mask_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ mask_head=dict(
+ type='FCNMaskHead',
+ num_convs=4,
+ in_channels=256,
+ conv_out_channels=256,
+ num_classes=80,
+ loss_mask=dict(
+ type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
+ # model training and testing settings
+ train_cfg=dict(
+ rpn=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ match_low_quality=True,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False),
+ allowed_border=-1,
+ pos_weight=-1,
+ debug=False),
+ rpn_proposal=dict(
+ nms_pre=2000,
+ max_per_img=1000,
+ nms=dict(type='nms', iou_threshold=0.7),
+ min_bbox_size=0),
+ rcnn=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ match_low_quality=True,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False)),
+ test_cfg=dict(
+ rpn=dict(
+ nms_pre=1000,
+ max_per_img=1000,
+ nms=dict(type='nms', iou_threshold=0.7),
+ min_bbox_size=0),
+ rcnn=dict(
+ score_thr=0.05,
+ nms=dict(type='nms', iou_threshold=0.5),
+ max_per_img=100,
+ mask_thr_binary=0.5)))
diff --git a/configs/swin/cascade_mask_rcnn_swin_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py b/configs/swin/cascade_mask_rcnn_swin_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..e3e44ee6121f3c8b5f83f263303bbcd4370eea71
--- /dev/null
+++ b/configs/swin/cascade_mask_rcnn_swin_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py
@@ -0,0 +1,140 @@
+_base_ = [
+ '../_base_/models/cascade_mask_rcnn_swin_fpn.py',
+ '../_base_/datasets/coco_instance.py',
+ '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+model = dict(
+ backbone=dict(
+ embed_dim=128,
+ depths=[2, 2, 18, 2],
+ num_heads=[4, 8, 16, 32],
+ window_size=7,
+ ape=False,
+ drop_path_rate=0.3,
+ patch_norm=True,
+ use_checkpoint=False
+ ),
+ neck=dict(in_channels=[128, 256, 512, 1024]),
+ roi_head=dict(
+ bbox_head=[
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0))
+ ]))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# augmentation strategy originates from DETR / Sparse RCNN
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='AutoAugment',
+ policies=[
+ [
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
+ (608, 1333), (640, 1333), (672, 1333), (704, 1333),
+ (736, 1333), (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True)
+ ],
+ [
+ dict(type='Resize',
+ img_scale=[(400, 1333), (500, 1333), (600, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomCrop',
+ crop_type='absolute_range',
+ crop_size=(384, 600),
+ allow_negative_crop=True),
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333),
+ (576, 1333), (608, 1333), (640, 1333),
+ (672, 1333), (704, 1333), (736, 1333),
+ (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ override=True,
+ keep_ratio=True)
+ ]
+ ]),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+data = dict(train=dict(pipeline=train_pipeline))
+
+optimizer = dict(_delete_=True, type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
+ paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
+ 'relative_position_bias_table': dict(decay_mult=0.),
+ 'norm': dict(decay_mult=0.)}))
+lr_config = dict(step=[27, 33])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
+
+# do not use mmdet version fp16
+fp16 = None
+optimizer_config = dict(
+ type="DistOptimizerHook",
+ update_interval=1,
+ grad_clip=None,
+ coalesce=True,
+ bucket_size_mb=-1,
+ use_fp16=True,
+)
diff --git a/configs/swin/cascade_mask_rcnn_swin_small_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py b/configs/swin/cascade_mask_rcnn_swin_small_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..816d206f5735c008cd6bca6e3cbf7a81fdd9b619
--- /dev/null
+++ b/configs/swin/cascade_mask_rcnn_swin_small_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py
@@ -0,0 +1,140 @@
+_base_ = [
+ '../_base_/models/cascade_mask_rcnn_swin_fpn.py',
+ '../_base_/datasets/coco_instance.py',
+ '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+model = dict(
+ backbone=dict(
+ embed_dim=96,
+ depths=[2, 2, 18, 2],
+ num_heads=[3, 6, 12, 24],
+ window_size=7,
+ ape=False,
+ drop_path_rate=0.2,
+ patch_norm=True,
+ use_checkpoint=False
+ ),
+ neck=dict(in_channels=[96, 192, 384, 768]),
+ roi_head=dict(
+ bbox_head=[
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0))
+ ]))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# augmentation strategy originates from DETR / Sparse RCNN
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='AutoAugment',
+ policies=[
+ [
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
+ (608, 1333), (640, 1333), (672, 1333), (704, 1333),
+ (736, 1333), (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True)
+ ],
+ [
+ dict(type='Resize',
+ img_scale=[(400, 1333), (500, 1333), (600, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomCrop',
+ crop_type='absolute_range',
+ crop_size=(384, 600),
+ allow_negative_crop=True),
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333),
+ (576, 1333), (608, 1333), (640, 1333),
+ (672, 1333), (704, 1333), (736, 1333),
+ (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ override=True,
+ keep_ratio=True)
+ ]
+ ]),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+data = dict(train=dict(pipeline=train_pipeline))
+
+optimizer = dict(_delete_=True, type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
+ paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
+ 'relative_position_bias_table': dict(decay_mult=0.),
+ 'norm': dict(decay_mult=0.)}))
+lr_config = dict(step=[27, 33])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
+
+# do not use mmdet version fp16
+fp16 = None
+optimizer_config = dict(
+ type="DistOptimizerHook",
+ update_interval=1,
+ grad_clip=None,
+ coalesce=True,
+ bucket_size_mb=-1,
+ use_fp16=True,
+)
diff --git a/configs/swin/cascade_mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py b/configs/swin/cascade_mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..e01a9eff6197fb80e3a541910c9b94c00510323e
--- /dev/null
+++ b/configs/swin/cascade_mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py
@@ -0,0 +1,140 @@
+_base_ = [
+ '../_base_/models/cascade_mask_rcnn_swin_fpn.py',
+ '../_base_/datasets/coco_instance.py',
+ '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+model = dict(
+ backbone=dict(
+ embed_dim=96,
+ depths=[2, 2, 6, 2],
+ num_heads=[3, 6, 12, 24],
+ window_size=7,
+ ape=False,
+ drop_path_rate=0.2,
+ patch_norm=True,
+ use_checkpoint=False
+ ),
+ neck=dict(in_channels=[96, 192, 384, 768]),
+ roi_head=dict(
+ bbox_head=[
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
+ dict(
+ type='ConvFCBBoxHead',
+ num_shared_convs=4,
+ num_shared_fcs=1,
+ in_channels=256,
+ conv_out_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=80,
+ bbox_coder=dict(
+ type='DeltaXYWHBBoxCoder',
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067]),
+ reg_class_agnostic=False,
+ reg_decoded_bbox=True,
+ norm_cfg=dict(type='SyncBN', requires_grad=True),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='GIoULoss', loss_weight=10.0))
+ ]))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# augmentation strategy originates from DETR / Sparse RCNN
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='AutoAugment',
+ policies=[
+ [
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
+ (608, 1333), (640, 1333), (672, 1333), (704, 1333),
+ (736, 1333), (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True)
+ ],
+ [
+ dict(type='Resize',
+ img_scale=[(400, 1333), (500, 1333), (600, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomCrop',
+ crop_type='absolute_range',
+ crop_size=(384, 600),
+ allow_negative_crop=True),
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333),
+ (576, 1333), (608, 1333), (640, 1333),
+ (672, 1333), (704, 1333), (736, 1333),
+ (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ override=True,
+ keep_ratio=True)
+ ]
+ ]),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+data = dict(train=dict(pipeline=train_pipeline))
+
+optimizer = dict(_delete_=True, type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
+ paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
+ 'relative_position_bias_table': dict(decay_mult=0.),
+ 'norm': dict(decay_mult=0.)}))
+lr_config = dict(step=[27, 33])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
+
+# do not use mmdet version fp16
+fp16 = None
+optimizer_config = dict(
+ type="DistOptimizerHook",
+ update_interval=1,
+ grad_clip=None,
+ coalesce=True,
+ bucket_size_mb=-1,
+ use_fp16=True,
+)
diff --git a/configs/swin/mask_rcnn_swin_small_patch4_window7_mstrain_480-800_adamw_3x_coco.py b/configs/swin/mask_rcnn_swin_small_patch4_window7_mstrain_480-800_adamw_3x_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..ee15134ba3f0a0788cbf4eb69cf080d01e08ddab
--- /dev/null
+++ b/configs/swin/mask_rcnn_swin_small_patch4_window7_mstrain_480-800_adamw_3x_coco.py
@@ -0,0 +1,80 @@
+_base_ = [
+ '../_base_/models/mask_rcnn_swin_fpn.py',
+ '../_base_/datasets/coco_instance.py',
+ '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+model = dict(
+ backbone=dict(
+ embed_dim=96,
+ depths=[2, 2, 18, 2],
+ num_heads=[3, 6, 12, 24],
+ window_size=7,
+ ape=False,
+ drop_path_rate=0.2,
+ patch_norm=True,
+ use_checkpoint=False
+ ),
+ neck=dict(in_channels=[96, 192, 384, 768]))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# augmentation strategy originates from DETR / Sparse RCNN
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='AutoAugment',
+ policies=[
+ [
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
+ (608, 1333), (640, 1333), (672, 1333), (704, 1333),
+ (736, 1333), (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True)
+ ],
+ [
+ dict(type='Resize',
+ img_scale=[(400, 1333), (500, 1333), (600, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomCrop',
+ crop_type='absolute_range',
+ crop_size=(384, 600),
+ allow_negative_crop=True),
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333),
+ (576, 1333), (608, 1333), (640, 1333),
+ (672, 1333), (704, 1333), (736, 1333),
+ (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ override=True,
+ keep_ratio=True)
+ ]
+ ]),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+data = dict(train=dict(pipeline=train_pipeline))
+
+optimizer = dict(_delete_=True, type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
+ paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
+ 'relative_position_bias_table': dict(decay_mult=0.),
+ 'norm': dict(decay_mult=0.)}))
+lr_config = dict(step=[27, 33])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
+
+# do not use mmdet version fp16
+fp16 = None
+optimizer_config = dict(
+ type="DistOptimizerHook",
+ update_interval=1,
+ grad_clip=None,
+ coalesce=True,
+ bucket_size_mb=-1,
+ use_fp16=True,
+)
diff --git a/configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco.py b/configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..c58057747d7d922293b6838e6eb1e13aa520aa3a
--- /dev/null
+++ b/configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco.py
@@ -0,0 +1,80 @@
+_base_ = [
+ '../_base_/models/mask_rcnn_swin_fpn.py',
+ '../_base_/datasets/coco_instance.py',
+ '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
+
+model = dict(
+ backbone=dict(
+ embed_dim=96,
+ depths=[2, 2, 6, 2],
+ num_heads=[3, 6, 12, 24],
+ window_size=7,
+ ape=False,
+ drop_path_rate=0.2,
+ patch_norm=True,
+ use_checkpoint=False
+ ),
+ neck=dict(in_channels=[96, 192, 384, 768]))
+
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+
+# augmentation strategy originates from DETR / Sparse RCNN
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='AutoAugment',
+ policies=[
+ [
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
+ (608, 1333), (640, 1333), (672, 1333), (704, 1333),
+ (736, 1333), (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True)
+ ],
+ [
+ dict(type='Resize',
+ img_scale=[(400, 1333), (500, 1333), (600, 1333)],
+ multiscale_mode='value',
+ keep_ratio=True),
+ dict(type='RandomCrop',
+ crop_type='absolute_range',
+ crop_size=(384, 600),
+ allow_negative_crop=True),
+ dict(type='Resize',
+ img_scale=[(480, 1333), (512, 1333), (544, 1333),
+ (576, 1333), (608, 1333), (640, 1333),
+ (672, 1333), (704, 1333), (736, 1333),
+ (768, 1333), (800, 1333)],
+ multiscale_mode='value',
+ override=True,
+ keep_ratio=True)
+ ]
+ ]),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+]
+data = dict(train=dict(pipeline=train_pipeline))
+
+optimizer = dict(_delete_=True, type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05,
+ paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
+ 'relative_position_bias_table': dict(decay_mult=0.),
+ 'norm': dict(decay_mult=0.)}))
+lr_config = dict(step=[27, 33])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
+
+# do not use mmdet version fp16
+fp16 = None
+optimizer_config = dict(
+ type="DistOptimizerHook",
+ update_interval=1,
+ grad_clip=None,
+ coalesce=True,
+ bucket_size_mb=-1,
+ use_fp16=True,
+)