add new triplemu config

configs/triplemu/_base_/default_runtime.py

@@ -0,0 +1,39 @@
+default_scope = 'mmrotate'
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        type='CheckpointHook',
+        interval=1,
+        max_keep_ckpts=30,
+        save_best='dota/mAP',
+        rule='greater'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='mmdet.DetVisualizationHook'))
+
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='RotLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+
+log_level = 'INFO'
+load_from = None
+resume = False
+
+custom_hooks = [
+    dict(type='mmdet.NumClassCheckHook'),
+    dict(
+        type='EMAHook',
+        ema_type='mmdet.ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49)
+]

configs/triplemu/_base_/dota_rr.py

@@ -0,0 +1,112 @@
+# dataset settings
+dataset_type = 'DOTADataset'
+data_root = 'data/DOTA/'
+metainfo = {
+    'classes': ('A', 'B', 'C', 'D', 'E', 'F'),
+    'palette': [(165, 42, 42), (189, 183, 107), (0, 255, 0), (255, 0, 0),
+                (138, 43, 226), (255, 128, 0)]
+}
+
+
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(
+        type='RandomRotate',
+        prob=0.5,
+        angle_range=180,
+        rect_obj_labels=[9, 11]),
+    dict(
+        type='mmdet.Pad', size=(1024, 1024),
+        pad_val=dict(img=(114, 114, 114))),
+    dict(type='mmdet.PackDetInputs')
+]
+val_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    # avoid bboxes being resized
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(
+        type='mmdet.Pad', size=(1024, 1024),
+        pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+test_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.Pad', size=(1024, 1024),
+        pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=None,
+    pin_memory=False,
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        metainfo=metainfo,
+        ann_file='train/annfiles/',
+        data_prefix=dict(img_path='train/images/'),
+        filter_cfg=dict(filter_empty_gt=True),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        metainfo=metainfo,
+        ann_file='val/annfiles/',
+        data_prefix=dict(img_path='val/images/'),
+        test_mode=True,
+        pipeline=val_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='DOTAMetric',
+    iou_thrs=[0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95],
+    metric='mAP')
+test_evaluator = val_evaluator
+
+# inference on test dataset and format the output results
+# for submission. Note: the test set has no annotation.
+# test_dataloader = dict(
+#     batch_size=8,
+#     num_workers=8,
+#     persistent_workers=False,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         data_prefix=dict(img_path='test/images/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='DOTAMetric',
+#     format_only=True,
+#     merge_patches=True,
+#     outfile_prefix='./work_dirs/rtmdet_r/Task1')

configs/triplemu/_base_/schedule_3x.py

@@ -0,0 +1,33 @@
+max_epochs = 3 * 100
+base_lr = 0.004 / 16 # 2 * 4
+interval = 1
+
+train_cfg = dict(
+    type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=interval)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))

configs/triplemu/rotated_rtmdet_l.py

@@ -0,0 +1,78 @@
+_base_ = [
+    './_base_/default_runtime.py', './_base_/schedule_3x.py',
+    './_base_/dota_rr.py'
+]
+
+load_from = 'rotated_rtmdet_l-coco_pretrain-3x-dota_ms-06d248a2.pth'
+num_classes = 6
+angle_version = 'le90'
+model = dict(
+    type='mmdet.RTMDet',
+    data_preprocessor=dict(
+        type='mmdet.DetDataPreprocessor',
+        mean=[103.53, 116.28, 123.675],
+        std=[57.375, 57.12, 58.395],
+        bgr_to_rgb=False,
+        boxtype2tensor=False,
+        batch_augments=None),
+    backbone=dict(
+        type='mmdet.CSPNeXt',
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=1,
+        widen_factor=1,
+        channel_attention=True,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU')),
+    neck=dict(
+        type='mmdet.CSPNeXtPAFPN',
+        in_channels=[256, 512, 1024],
+        out_channels=256,
+        num_csp_blocks=3,
+        expand_ratio=0.5,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU')),
+    bbox_head=dict(
+        type='RotatedRTMDetSepBNHead',
+        num_classes=num_classes,
+        in_channels=256,
+        stacked_convs=2,
+        feat_channels=256,
+        angle_version=angle_version,
+        anchor_generator=dict(
+            type='mmdet.MlvlPointGenerator', offset=0, strides=[8, 16, 32]),
+        bbox_coder=dict(
+            type='DistanceAnglePointCoder', angle_version=angle_version),
+        loss_cls=dict(
+            type='mmdet.QualityFocalLoss',
+            use_sigmoid=True,
+            beta=2.0,
+            loss_weight=1.0),
+        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=dict(
+        assigner=dict(
+            type='mmdet.DynamicSoftLabelAssigner',
+            iou_calculator=dict(type='RBboxOverlaps2D'),
+            topk=13),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=2000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms_rotated', iou_threshold=0.1),
+        max_per_img=2000),
+)
+
+# batch_size = (2 GPUs) x (4 samples per GPU) = 8
+train_dataloader = dict(batch_size=4, num_workers=4)

configs/triplemu/rotated_rtmdet_l_ccp.py

@@ -0,0 +1,27 @@
+_base_ = ['./rotated_rtmdet_l.py']
+
+backend_args = None
+
+train_pipeline = [
+    dict(type='mmdet.LoadImageFromFile', backend_args=backend_args),
+    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
+    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
+    dict(type='CacheCopyPaste', num_copy_thres=20, max_capacity=1024),
+    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
+    dict(
+        type='mmdet.RandomFlip',
+        prob=0.75,
+        direction=['horizontal', 'vertical', 'diagonal']),
+    dict(
+        type='RandomRotate',
+        prob=0.5,
+        angle_range=180,
+        rect_obj_labels=[9, 11]),
+    dict(
+        type='mmdet.Pad', size=(1024, 1024),
+        pad_val=dict(img=(114, 114, 114))),
+    dict(type='mmdet.PackDetInputs')
+]
+
+# batch_size = (2 GPUs) x (4 samples per GPU) = 8
+train_dataloader = dict(batch_size=4, num_workers=4)