Add 1x configs; Load MoBY model

configs/swin/cascade_mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_1x_coco.py

+_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=[8, 11])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=12)
+
+# 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,
+)

configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco.py

+_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=[8, 11])
+runner = dict(type='EpochBasedRunnerAmp', max_epochs=12)
+
+# 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,
+)

mmcv_custom/checkpoint.py

@@ -319,6 +319,10 @@ def load_checkpoint(model,
     if list(state_dict.keys())[0].startswith('module.'):
         state_dict = {k[7:]: v for k, v in state_dict.items()}
 
+    # for MoBY, load model of online branch
+    if sorted(list(state_dict.keys()))[0].startswith('encoder'):
+        state_dict = {k.replace('encoder.', ''): v for k, v in state_dict.items() if k.startswith('encoder.')}
+
     # reshape absolute position embedding
     if state_dict.get('absolute_pos_embed') is not None:
         absolute_pos_embed = state_dict['absolute_pos_embed']