des

cascade-rcnn_x101-32x4d_fpn_1x_ct/20240412_192400/vis_data/config.py

@@ -0,0 +1,439 @@
+auto_scale_lr = dict(base_batch_size=16, enable=False)
+backend_args = None
+data_root = '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/'
+dataset_type = 'CocoCTDataset'
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='CheckpointHook'),
+    logger=dict(interval=50, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='DetVisualizationHook'))
+default_scope = 'mmdet'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+launcher = 'pytorch'
+load_from = 'ckpt/cascade_rcnn_x101_32x4d_fpn_1x_coco_20200316-95c2deb6.pth'
+log_level = 'INFO'
+log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
+model = dict(
+    backbone=dict(
+        base_width=4,
+        depth=101,
+        frozen_stages=1,
+        groups=32,
+        init_cfg=dict(
+            checkpoint='open-mmlab://resnext101_32x4d', type='Pretrained'),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        norm_eval=True,
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        style='pytorch',
+        type='ResNeXt'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_size_divisor=32,
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='DetDataPreprocessor'),
+    neck=dict(
+        in_channels=[
+            256,
+            512,
+            1024,
+            2048,
+        ],
+        num_outs=5,
+        out_channels=256,
+        type='FPN'),
+    roi_head=dict(
+        bbox_head=[
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.1,
+                        0.1,
+                        0.2,
+                        0.2,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.05,
+                        0.05,
+                        0.1,
+                        0.1,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.033,
+                        0.033,
+                        0.067,
+                        0.067,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+        ],
+        bbox_roi_extractor=dict(
+            featmap_strides=[
+                4,
+                8,
+                16,
+                32,
+            ],
+            out_channels=256,
+            roi_layer=dict(output_size=7, sampling_ratio=0, type='RoIAlign'),
+            type='SingleRoIExtractor'),
+        num_stages=3,
+        stage_loss_weights=[
+            1,
+            0.5,
+            0.25,
+        ],
+        type='CascadeRoIHead'),
+    rpn_head=dict(
+        anchor_generator=dict(
+            ratios=[
+                0.5,
+                1.0,
+                2.0,
+            ],
+            scales=[
+                8,
+            ],
+            strides=[
+                4,
+                8,
+                16,
+                32,
+                64,
+            ],
+            type='AnchorGenerator'),
+        bbox_coder=dict(
+            target_means=[
+                0.0,
+                0.0,
+                0.0,
+                0.0,
+            ],
+            target_stds=[
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+            ],
+            type='DeltaXYWHBBoxCoder'),
+        feat_channels=256,
+        in_channels=256,
+        loss_bbox=dict(
+            beta=0.1111111111111111, loss_weight=1.0, type='SmoothL1Loss'),
+        loss_cls=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=True),
+        type='RPNHead'),
+    test_cfg=dict(
+        rcnn=dict(
+            max_per_img=100,
+            nms=dict(iou_threshold=0.5, type='nms'),
+            score_thr=0.05),
+        rpn=dict(
+            max_per_img=1000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=1000)),
+    train_cfg=dict(
+        rcnn=[
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.5,
+                    neg_iou_thr=0.5,
+                    pos_iou_thr=0.5,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.6,
+                    neg_iou_thr=0.6,
+                    pos_iou_thr=0.6,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.7,
+                    neg_iou_thr=0.7,
+                    pos_iou_thr=0.7,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+        ],
+        rpn=dict(
+            allowed_border=0,
+            assigner=dict(
+                ignore_iof_thr=-1,
+                match_low_quality=True,
+                min_pos_iou=0.3,
+                neg_iou_thr=0.3,
+                pos_iou_thr=0.7,
+                type='MaxIoUAssigner'),
+            debug=False,
+            pos_weight=-1,
+            sampler=dict(
+                add_gt_as_proposals=False,
+                neg_pos_ub=-1,
+                num=256,
+                pos_fraction=0.5,
+                type='RandomSampler')),
+        rpn_proposal=dict(
+            max_per_img=2000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=2000)),
+    type='CascadeRCNN')
+optim_wrapper = dict(
+    optimizer=dict(lr=0.02, momentum=0.9, type='SGD', weight_decay=0.0001),
+    type='OptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=500, start_factor=0.001, type='LinearLR'),
+    dict(
+        begin=0,
+        by_epoch=True,
+        end=12,
+        gamma=0.1,
+        milestones=[
+            8,
+            11,
+        ],
+        type='MultiStepLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+test_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        meta_keys=(
+            'img_id',
+            'img_path',
+            'ori_shape',
+            'img_shape',
+            'scale_factor',
+        ),
+        type='PackDetInputs'),
+]
+train_cfg = dict(max_epochs=12, type='EpochBasedTrainLoop', val_interval=1)
+train_dataloader = dict(
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/train_wsyn.json',
+        backend_args=None,
+        data_prefix=dict(img='images/train/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PackDetInputs'),
+        ],
+        type='CocoCTDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PackDetInputs'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='DetLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = 'work_dirs/cascade-rcnn_x101-32x4d_fpn_1x_ct'

cascade-rcnn_x101-32x4d_fpn_1x_ct/cascade-rcnn_x101-32x4d_fpn_1x_ct.py

@@ -0,0 +1,439 @@
+auto_scale_lr = dict(base_batch_size=16, enable=False)
+backend_args = None
+data_root = '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/'
+dataset_type = 'CocoCTDataset'
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='CheckpointHook'),
+    logger=dict(interval=50, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='DetVisualizationHook'))
+default_scope = 'mmdet'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+launcher = 'pytorch'
+load_from = 'ckpt/cascade_rcnn_x101_32x4d_fpn_1x_coco_20200316-95c2deb6.pth'
+log_level = 'INFO'
+log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
+model = dict(
+    backbone=dict(
+        base_width=4,
+        depth=101,
+        frozen_stages=1,
+        groups=32,
+        init_cfg=dict(
+            checkpoint='open-mmlab://resnext101_32x4d', type='Pretrained'),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        norm_eval=True,
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        style='pytorch',
+        type='ResNeXt'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_size_divisor=32,
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='DetDataPreprocessor'),
+    neck=dict(
+        in_channels=[
+            256,
+            512,
+            1024,
+            2048,
+        ],
+        num_outs=5,
+        out_channels=256,
+        type='FPN'),
+    roi_head=dict(
+        bbox_head=[
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.1,
+                        0.1,
+                        0.2,
+                        0.2,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.05,
+                        0.05,
+                        0.1,
+                        0.1,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.033,
+                        0.033,
+                        0.067,
+                        0.067,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+        ],
+        bbox_roi_extractor=dict(
+            featmap_strides=[
+                4,
+                8,
+                16,
+                32,
+            ],
+            out_channels=256,
+            roi_layer=dict(output_size=7, sampling_ratio=0, type='RoIAlign'),
+            type='SingleRoIExtractor'),
+        num_stages=3,
+        stage_loss_weights=[
+            1,
+            0.5,
+            0.25,
+        ],
+        type='CascadeRoIHead'),
+    rpn_head=dict(
+        anchor_generator=dict(
+            ratios=[
+                0.5,
+                1.0,
+                2.0,
+            ],
+            scales=[
+                8,
+            ],
+            strides=[
+                4,
+                8,
+                16,
+                32,
+                64,
+            ],
+            type='AnchorGenerator'),
+        bbox_coder=dict(
+            target_means=[
+                0.0,
+                0.0,
+                0.0,
+                0.0,
+            ],
+            target_stds=[
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+            ],
+            type='DeltaXYWHBBoxCoder'),
+        feat_channels=256,
+        in_channels=256,
+        loss_bbox=dict(
+            beta=0.1111111111111111, loss_weight=1.0, type='SmoothL1Loss'),
+        loss_cls=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=True),
+        type='RPNHead'),
+    test_cfg=dict(
+        rcnn=dict(
+            max_per_img=100,
+            nms=dict(iou_threshold=0.5, type='nms'),
+            score_thr=0.05),
+        rpn=dict(
+            max_per_img=1000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=1000)),
+    train_cfg=dict(
+        rcnn=[
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.5,
+                    neg_iou_thr=0.5,
+                    pos_iou_thr=0.5,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.6,
+                    neg_iou_thr=0.6,
+                    pos_iou_thr=0.6,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.7,
+                    neg_iou_thr=0.7,
+                    pos_iou_thr=0.7,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+        ],
+        rpn=dict(
+            allowed_border=0,
+            assigner=dict(
+                ignore_iof_thr=-1,
+                match_low_quality=True,
+                min_pos_iou=0.3,
+                neg_iou_thr=0.3,
+                pos_iou_thr=0.7,
+                type='MaxIoUAssigner'),
+            debug=False,
+            pos_weight=-1,
+            sampler=dict(
+                add_gt_as_proposals=False,
+                neg_pos_ub=-1,
+                num=256,
+                pos_fraction=0.5,
+                type='RandomSampler')),
+        rpn_proposal=dict(
+            max_per_img=2000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=2000)),
+    type='CascadeRCNN')
+optim_wrapper = dict(
+    optimizer=dict(lr=0.02, momentum=0.9, type='SGD', weight_decay=0.0001),
+    type='OptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=500, start_factor=0.001, type='LinearLR'),
+    dict(
+        begin=0,
+        by_epoch=True,
+        end=12,
+        gamma=0.1,
+        milestones=[
+            8,
+            11,
+        ],
+        type='MultiStepLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+test_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        meta_keys=(
+            'img_id',
+            'img_path',
+            'ori_shape',
+            'img_shape',
+            'scale_factor',
+        ),
+        type='PackDetInputs'),
+]
+train_cfg = dict(max_epochs=12, type='EpochBasedTrainLoop', val_interval=1)
+train_dataloader = dict(
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/train_wsyn.json',
+        backend_args=None,
+        data_prefix=dict(img='images/train/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PackDetInputs'),
+        ],
+        type='CocoCTDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PackDetInputs'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='DetLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = 'work_dirs/cascade-rcnn_x101-32x4d_fpn_1x_ct'

cascade-rcnn_x101-32x4d_fpn_1x_ct/epoch_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf7e7b96b6cd52aff250301b864a09d798e2a55cc55cfb25403e449645e633f
+size 705747963

cascade-rcnn_x101-64x4d_fpn_1x_ct/20240412_193331/vis_data/config.py

@@ -0,0 +1,439 @@
+auto_scale_lr = dict(base_batch_size=16, enable=False)
+backend_args = None
+data_root = '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/'
+dataset_type = 'CocoCTDataset'
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='CheckpointHook'),
+    logger=dict(interval=50, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='DetVisualizationHook'))
+default_scope = 'mmdet'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+launcher = 'pytorch'
+load_from = 'ckpt/cascade_rcnn_x101_64x4d_fpn_1x_coco_20200515_075702-43ce6a30.pth'
+log_level = 'INFO'
+log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
+model = dict(
+    backbone=dict(
+        base_width=4,
+        depth=101,
+        frozen_stages=1,
+        groups=64,
+        init_cfg=dict(
+            checkpoint='open-mmlab://resnext101_64x4d', type='Pretrained'),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        norm_eval=True,
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        style='pytorch',
+        type='ResNeXt'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_size_divisor=32,
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='DetDataPreprocessor'),
+    neck=dict(
+        in_channels=[
+            256,
+            512,
+            1024,
+            2048,
+        ],
+        num_outs=5,
+        out_channels=256,
+        type='FPN'),
+    roi_head=dict(
+        bbox_head=[
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.1,
+                        0.1,
+                        0.2,
+                        0.2,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.05,
+                        0.05,
+                        0.1,
+                        0.1,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.033,
+                        0.033,
+                        0.067,
+                        0.067,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+        ],
+        bbox_roi_extractor=dict(
+            featmap_strides=[
+                4,
+                8,
+                16,
+                32,
+            ],
+            out_channels=256,
+            roi_layer=dict(output_size=7, sampling_ratio=0, type='RoIAlign'),
+            type='SingleRoIExtractor'),
+        num_stages=3,
+        stage_loss_weights=[
+            1,
+            0.5,
+            0.25,
+        ],
+        type='CascadeRoIHead'),
+    rpn_head=dict(
+        anchor_generator=dict(
+            ratios=[
+                0.5,
+                1.0,
+                2.0,
+            ],
+            scales=[
+                8,
+            ],
+            strides=[
+                4,
+                8,
+                16,
+                32,
+                64,
+            ],
+            type='AnchorGenerator'),
+        bbox_coder=dict(
+            target_means=[
+                0.0,
+                0.0,
+                0.0,
+                0.0,
+            ],
+            target_stds=[
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+            ],
+            type='DeltaXYWHBBoxCoder'),
+        feat_channels=256,
+        in_channels=256,
+        loss_bbox=dict(
+            beta=0.1111111111111111, loss_weight=1.0, type='SmoothL1Loss'),
+        loss_cls=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=True),
+        type='RPNHead'),
+    test_cfg=dict(
+        rcnn=dict(
+            max_per_img=100,
+            nms=dict(iou_threshold=0.5, type='nms'),
+            score_thr=0.05),
+        rpn=dict(
+            max_per_img=1000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=1000)),
+    train_cfg=dict(
+        rcnn=[
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.5,
+                    neg_iou_thr=0.5,
+                    pos_iou_thr=0.5,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.6,
+                    neg_iou_thr=0.6,
+                    pos_iou_thr=0.6,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.7,
+                    neg_iou_thr=0.7,
+                    pos_iou_thr=0.7,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+        ],
+        rpn=dict(
+            allowed_border=0,
+            assigner=dict(
+                ignore_iof_thr=-1,
+                match_low_quality=True,
+                min_pos_iou=0.3,
+                neg_iou_thr=0.3,
+                pos_iou_thr=0.7,
+                type='MaxIoUAssigner'),
+            debug=False,
+            pos_weight=-1,
+            sampler=dict(
+                add_gt_as_proposals=False,
+                neg_pos_ub=-1,
+                num=256,
+                pos_fraction=0.5,
+                type='RandomSampler')),
+        rpn_proposal=dict(
+            max_per_img=2000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=2000)),
+    type='CascadeRCNN')
+optim_wrapper = dict(
+    optimizer=dict(lr=0.02, momentum=0.9, type='SGD', weight_decay=0.0001),
+    type='OptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=500, start_factor=0.001, type='LinearLR'),
+    dict(
+        begin=0,
+        by_epoch=True,
+        end=12,
+        gamma=0.1,
+        milestones=[
+            8,
+            11,
+        ],
+        type='MultiStepLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+test_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        meta_keys=(
+            'img_id',
+            'img_path',
+            'ori_shape',
+            'img_shape',
+            'scale_factor',
+        ),
+        type='PackDetInputs'),
+]
+train_cfg = dict(max_epochs=12, type='EpochBasedTrainLoop', val_interval=1)
+train_dataloader = dict(
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/train_wsyn.json',
+        backend_args=None,
+        data_prefix=dict(img='images/train/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PackDetInputs'),
+        ],
+        type='CocoCTDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PackDetInputs'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='DetLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = 'work_dirs/cascade-rcnn_x101-64x4d_fpn_1x_ct'

cascade-rcnn_x101-64x4d_fpn_1x_ct/cascade-rcnn_x101-64x4d_fpn_1x_ct.py

@@ -0,0 +1,439 @@
+auto_scale_lr = dict(base_batch_size=16, enable=False)
+backend_args = None
+data_root = '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/'
+dataset_type = 'CocoCTDataset'
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='CheckpointHook'),
+    logger=dict(interval=50, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(type='DetVisualizationHook'))
+default_scope = 'mmdet'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+launcher = 'pytorch'
+load_from = 'ckpt/cascade_rcnn_x101_64x4d_fpn_1x_coco_20200515_075702-43ce6a30.pth'
+log_level = 'INFO'
+log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
+model = dict(
+    backbone=dict(
+        base_width=4,
+        depth=101,
+        frozen_stages=1,
+        groups=64,
+        init_cfg=dict(
+            checkpoint='open-mmlab://resnext101_64x4d', type='Pretrained'),
+        norm_cfg=dict(requires_grad=True, type='BN'),
+        norm_eval=True,
+        num_stages=4,
+        out_indices=(
+            0,
+            1,
+            2,
+            3,
+        ),
+        style='pytorch',
+        type='ResNeXt'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        pad_size_divisor=32,
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='DetDataPreprocessor'),
+    neck=dict(
+        in_channels=[
+            256,
+            512,
+            1024,
+            2048,
+        ],
+        num_outs=5,
+        out_channels=256,
+        type='FPN'),
+    roi_head=dict(
+        bbox_head=[
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.1,
+                        0.1,
+                        0.2,
+                        0.2,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.05,
+                        0.05,
+                        0.1,
+                        0.1,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+            dict(
+                bbox_coder=dict(
+                    target_means=[
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                    ],
+                    target_stds=[
+                        0.033,
+                        0.033,
+                        0.067,
+                        0.067,
+                    ],
+                    type='DeltaXYWHBBoxCoder'),
+                fc_out_channels=1024,
+                in_channels=256,
+                loss_bbox=dict(beta=1.0, loss_weight=1.0, type='SmoothL1Loss'),
+                loss_cls=dict(
+                    loss_weight=1.0,
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False),
+                num_classes=5,
+                reg_class_agnostic=True,
+                roi_feat_size=7,
+                type='Shared2FCBBoxHead'),
+        ],
+        bbox_roi_extractor=dict(
+            featmap_strides=[
+                4,
+                8,
+                16,
+                32,
+            ],
+            out_channels=256,
+            roi_layer=dict(output_size=7, sampling_ratio=0, type='RoIAlign'),
+            type='SingleRoIExtractor'),
+        num_stages=3,
+        stage_loss_weights=[
+            1,
+            0.5,
+            0.25,
+        ],
+        type='CascadeRoIHead'),
+    rpn_head=dict(
+        anchor_generator=dict(
+            ratios=[
+                0.5,
+                1.0,
+                2.0,
+            ],
+            scales=[
+                8,
+            ],
+            strides=[
+                4,
+                8,
+                16,
+                32,
+                64,
+            ],
+            type='AnchorGenerator'),
+        bbox_coder=dict(
+            target_means=[
+                0.0,
+                0.0,
+                0.0,
+                0.0,
+            ],
+            target_stds=[
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+            ],
+            type='DeltaXYWHBBoxCoder'),
+        feat_channels=256,
+        in_channels=256,
+        loss_bbox=dict(
+            beta=0.1111111111111111, loss_weight=1.0, type='SmoothL1Loss'),
+        loss_cls=dict(
+            loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=True),
+        type='RPNHead'),
+    test_cfg=dict(
+        rcnn=dict(
+            max_per_img=100,
+            nms=dict(iou_threshold=0.5, type='nms'),
+            score_thr=0.05),
+        rpn=dict(
+            max_per_img=1000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=1000)),
+    train_cfg=dict(
+        rcnn=[
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.5,
+                    neg_iou_thr=0.5,
+                    pos_iou_thr=0.5,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.6,
+                    neg_iou_thr=0.6,
+                    pos_iou_thr=0.6,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+            dict(
+                assigner=dict(
+                    ignore_iof_thr=-1,
+                    match_low_quality=False,
+                    min_pos_iou=0.7,
+                    neg_iou_thr=0.7,
+                    pos_iou_thr=0.7,
+                    type='MaxIoUAssigner'),
+                debug=False,
+                pos_weight=-1,
+                sampler=dict(
+                    add_gt_as_proposals=True,
+                    neg_pos_ub=-1,
+                    num=512,
+                    pos_fraction=0.25,
+                    type='RandomSampler')),
+        ],
+        rpn=dict(
+            allowed_border=0,
+            assigner=dict(
+                ignore_iof_thr=-1,
+                match_low_quality=True,
+                min_pos_iou=0.3,
+                neg_iou_thr=0.3,
+                pos_iou_thr=0.7,
+                type='MaxIoUAssigner'),
+            debug=False,
+            pos_weight=-1,
+            sampler=dict(
+                add_gt_as_proposals=False,
+                neg_pos_ub=-1,
+                num=256,
+                pos_fraction=0.5,
+                type='RandomSampler')),
+        rpn_proposal=dict(
+            max_per_img=2000,
+            min_bbox_size=0,
+            nms=dict(iou_threshold=0.7, type='nms'),
+            nms_pre=2000)),
+    type='CascadeRCNN')
+optim_wrapper = dict(
+    optimizer=dict(lr=0.02, momentum=0.9, type='SGD', weight_decay=0.0001),
+    type='OptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=500, start_factor=0.001, type='LinearLR'),
+    dict(
+        begin=0,
+        by_epoch=True,
+        end=12,
+        gamma=0.1,
+        milestones=[
+            8,
+            11,
+        ],
+        type='MultiStepLR'),
+]
+resume = False
+test_cfg = dict(type='TestLoop')
+test_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+test_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        meta_keys=(
+            'img_id',
+            'img_path',
+            'ori_shape',
+            'img_shape',
+            'scale_factor',
+        ),
+        type='PackDetInputs'),
+]
+train_cfg = dict(max_epochs=12, type='EpochBasedTrainLoop', val_interval=1)
+train_dataloader = dict(
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/train_wsyn.json',
+        backend_args=None,
+        data_prefix=dict(img='images/train/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(prob=0.5, type='RandomFlip'),
+            dict(type='PackDetInputs'),
+        ],
+        type='CocoCTDataset'),
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(backend_args=None, type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(keep_ratio=True, scale=(
+        512,
+        512,
+    ), type='Resize'),
+    dict(prob=0.5, type='RandomFlip'),
+    dict(type='PackDetInputs'),
+]
+val_cfg = dict(type='ValLoop')
+val_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        ann_file='annotations/test.json',
+        backend_args=None,
+        data_prefix=dict(img='images/test/'),
+        data_root='/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/',
+        pipeline=[
+            dict(backend_args=None, type='LoadImageFromFile'),
+            dict(keep_ratio=True, scale=(
+                512,
+                512,
+            ), type='Resize'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                meta_keys=(
+                    'img_id',
+                    'img_path',
+                    'ori_shape',
+                    'img_shape',
+                    'scale_factor',
+                ),
+                type='PackDetInputs'),
+        ],
+        test_mode=True,
+        type='CocoCTDataset'),
+    drop_last=False,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    ann_file=
+    '/mnt/bn/panxuran/Slice_Data/slice_dataset_maximum_0402/annotations/test.json',
+    backend_args=None,
+    format_only=False,
+    metric='bbox',
+    type='CocoMetric')
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='DetLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])
+work_dir = 'work_dirs/cascade-rcnn_x101-64x4d_fpn_1x_ct'

cascade-rcnn_x101-64x4d_fpn_1x_ct/epoch_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a735d734720fd3cc93d5b9401116b29c9e96c45b9679a0a0b52dabc94b34dea
+size 1019471931

co_deformable_detr_r50_1x_ct/co_deformable_detr_r50_1x_ct.py

@@ -0,0 +1,407 @@
+dataset_type = 'CocoDataset'
+data_root = 'data/slice_dataset_maximum_0402/'
+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='RandomFlip', flip_ratio=0.5),
+    dict(
+        type='AutoAugment',
+        policies=[[{
+            'type': 'Resize',
+            'img_scale': [(512, 512)],
+            'multiscale_mode': 'value',
+            'keep_ratio': True
+        }],
+                  [{
+                      'type': 'Resize',
+                      'img_scale': [(512, 512)],
+                      'multiscale_mode': 'value',
+                      'keep_ratio': True
+                  }, {
+                      'type': 'RandomCrop',
+                      'crop_type': 'absolute_range',
+                      'crop_size': (512, 512),
+                      'allow_negative_crop': True
+                  }, {
+                      'type': 'Resize',
+                      'img_scale': [(512, 512)],
+                      'multiscale_mode': 'value',
+                      'override': True,
+                      'keep_ratio': True
+                  }]]),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=1),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(512, 512),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=1),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=4,
+    train=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/train.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/train/',
+        filter_empty_gt=False,
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(
+                type='AutoAugment',
+                policies=[[{
+                    'type': 'Resize',
+                    'img_scale': [(512, 512)],
+                    'multiscale_mode': 'value',
+                    'keep_ratio': True
+                }],
+                          [{
+                              'type': 'Resize',
+                              'img_scale': [(512, 512)],
+                              'multiscale_mode': 'value',
+                              'keep_ratio': True
+                          }, {
+                              'type': 'RandomCrop',
+                              'crop_type': 'absolute_range',
+                              'crop_size': (512, 512),
+                              'allow_negative_crop': True
+                          }, {
+                              'type': 'Resize',
+                              'img_scale': [(512, 512)],
+                              'multiscale_mode': 'value',
+                              'override': True,
+                              'keep_ratio': True
+                          }]]),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=1),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+        ]),
+    val=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/test.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/test/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(512, 512),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=1),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]),
+    test=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/test.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/test/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(512, 512),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=1),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]))
+evaluation = dict(interval=1, metric='bbox')
+checkpoint_config = dict(interval=1)
+log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
+custom_hooks = [dict(type='NumClassCheckHook')]
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = './ckpt/co_deformable_detr_r50_1x_coco.pth'
+resume_from = None
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=False, base_batch_size=16)
+num_dec_layer = 6
+lambda_2 = 2.0
+model = dict(
+    type='CoDETR',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='ChannelMapper',
+        in_channels=[512, 1024, 2048],
+        kernel_size=1,
+        out_channels=256,
+        act_cfg=None,
+        norm_cfg=dict(type='GN', num_groups=32),
+        num_outs=4),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            octave_base_scale=4,
+            scales_per_octave=3,
+            ratios=[0.5, 1.0, 2.0],
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[0.0, 0.0, 0.0, 0.0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=12.0)),
+    query_head=dict(
+        type='CoDeformDETRHead',
+        num_query=300,
+        num_classes=5,
+        in_channels=2048,
+        sync_cls_avg_factor=True,
+        with_box_refine=True,
+        as_two_stage=True,
+        mixed_selection=True,
+        transformer=dict(
+            type='CoDeformableDetrTransformer',
+            num_co_heads=2,
+            encoder=dict(
+                type='DetrTransformerEncoder',
+                num_layers=6,
+                transformerlayers=dict(
+                    type='BaseTransformerLayer',
+                    attn_cfgs=dict(
+                        type='MultiScaleDeformableAttention',
+                        embed_dims=256,
+                        dropout=0.0),
+                    feedforward_channels=2048,
+                    ffn_dropout=0.0,
+                    operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
+            decoder=dict(
+                type='CoDeformableDetrTransformerDecoder',
+                num_layers=6,
+                return_intermediate=True,
+                look_forward_twice=True,
+                transformerlayers=dict(
+                    type='DetrTransformerDecoderLayer',
+                    attn_cfgs=[
+                        dict(
+                            type='MultiheadAttention',
+                            embed_dims=256,
+                            num_heads=8,
+                            dropout=0.0),
+                        dict(
+                            type='MultiScaleDeformableAttention',
+                            embed_dims=256,
+                            dropout=0.0)
+                    ],
+                    feedforward_channels=2048,
+                    ffn_dropout=0.0,
+                    operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
+                                     'ffn', 'norm')))),
+        positional_encoding=dict(
+            type='SinePositionalEncoding',
+            num_feats=128,
+            normalize=True,
+            offset=-0.5),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=2.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=5.0),
+        loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
+    roi_head=[
+        dict(
+            type='CoStandardRoIHead',
+            bbox_roi_extractor=dict(
+                type='SingleRoIExtractor',
+                roi_layer=dict(
+                    type='RoIAlign', output_size=7, sampling_ratio=0),
+                out_channels=256,
+                featmap_strides=[8, 16, 32, 64],
+                finest_scale=112),
+            bbox_head=dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=5,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0.0, 0.0, 0.0, 0.0],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=False,
+                reg_decoded_bbox=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=12.0),
+                loss_bbox=dict(type='GIoULoss', loss_weight=120.0)))
+    ],
+    bbox_head=[
+        dict(
+            type='CoATSSHead',
+            num_classes=5,
+            in_channels=256,
+            stacked_convs=1,
+            feat_channels=256,
+            anchor_generator=dict(
+                type='AnchorGenerator',
+                ratios=[1.0],
+                octave_base_scale=8,
+                scales_per_octave=1,
+                strides=[8, 16, 32, 64, 128]),
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0.0, 0.0, 0.0, 0.0],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            loss_cls=dict(
+                type='FocalLoss',
+                use_sigmoid=True,
+                gamma=2.0,
+                alpha=0.25,
+                loss_weight=12.0),
+            loss_bbox=dict(type='GIoULoss', loss_weight=24.0),
+            loss_centerness=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0))
+    ],
+    train_cfg=[
+        dict(
+            assigner=dict(
+                type='HungarianAssigner',
+                cls_cost=dict(type='FocalLossCost', weight=2.0),
+                reg_cost=dict(
+                    type='BBoxL1Cost', weight=5.0, box_format='xywh'),
+                iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
+        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=4000,
+                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=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False)),
+        dict(
+            assigner=dict(type='ATSSAssigner', topk=9),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False)
+    ],
+    test_cfg=[
+        dict(max_per_img=100),
+        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=0.0,
+                nms=dict(type='nms', iou_threshold=0.5),
+                max_per_img=100)),
+        dict(
+            nms_pre=1000,
+            min_bbox_size=0,
+            score_thr=0.0,
+            nms=dict(type='nms', iou_threshold=0.6),
+            max_per_img=100)
+    ])
+optimizer = dict(
+    type='AdamW',
+    lr=0.0002,
+    weight_decay=0.0001,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            backbone=dict(lr_mult=0.1),
+            sampling_offsets=dict(lr_mult=0.1),
+            reference_points=dict(lr_mult=0.1))))
+optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
+lr_config = dict(policy='step', step=[11])
+runner = dict(type='EpochBasedRunner', max_epochs=200)
+pretrained = './ckpt/co_deformable_detr_r50_1x_coco.pth'
+resume = False
+work_dir = 'work_dirs/co_deformable_detr_r50_1x_ct'
+auto_resume = False
+gpu_ids = range(0, 8)

co_deformable_detr_r50_1x_ct/epoch_40.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0367c20230c989c98a12957fdfb8346ada1fa020f879ff0f055ecabef6d0dd48
+size 771820693

co_deformable_detr_swin_large_1x_ct/co_deformable_detr_swin_large_1x_ct.py

@@ -0,0 +1,409 @@
+dataset_type = 'CocoDataset'
+data_root = 'data/slice_dataset_maximum_0402/'
+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='RandomFlip', flip_ratio=0.5),
+    dict(
+        type='AutoAugment',
+        policies=[[{
+            'type': 'Resize',
+            'img_scale': [(512, 512)],
+            'multiscale_mode': 'value',
+            'keep_ratio': True
+        }],
+                  [{
+                      'type': 'Resize',
+                      'img_scale': [(512, 512)],
+                      'multiscale_mode': 'value',
+                      'keep_ratio': True
+                  }, {
+                      'type': 'RandomCrop',
+                      'crop_type': 'absolute_range',
+                      'crop_size': (512, 512),
+                      'allow_negative_crop': True
+                  }, {
+                      'type': 'Resize',
+                      'img_scale': [(512, 512)],
+                      'multiscale_mode': 'value',
+                      'override': True,
+                      'keep_ratio': True
+                  }]]),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=1),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(512, 512),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=1),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/train.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/train/',
+        filter_empty_gt=False,
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(
+                type='AutoAugment',
+                policies=[[{
+                    'type': 'Resize',
+                    'img_scale': [(512, 512)],
+                    'multiscale_mode': 'value',
+                    'keep_ratio': True
+                }],
+                          [{
+                              'type': 'Resize',
+                              'img_scale': [(512, 512)],
+                              'multiscale_mode': 'value',
+                              'keep_ratio': True
+                          }, {
+                              'type': 'RandomCrop',
+                              'crop_type': 'absolute_range',
+                              'crop_size': (512, 512),
+                              'allow_negative_crop': True
+                          }, {
+                              'type': 'Resize',
+                              'img_scale': [(512, 512)],
+                              'multiscale_mode': 'value',
+                              'override': True,
+                              'keep_ratio': True
+                          }]]),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=1),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+        ]),
+    val=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/test.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/test/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(512, 512),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=1),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]),
+    test=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/test.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/test/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(512, 512),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=1),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]))
+evaluation = dict(interval=1, metric='bbox')
+checkpoint_config = dict(interval=1)
+log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
+custom_hooks = [dict(type='NumClassCheckHook')]
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = './ckpt/co_deformable_detr_swin_large_1x_coco.pth'
+resume_from = None
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=False, base_batch_size=16)
+num_dec_layer = 6
+lambda_2 = 2.0
+model = dict(
+    type='CoDETR',
+    backbone=dict(
+        type='SwinTransformerV1',
+        embed_dim=192,
+        depths=[2, 2, 18, 2],
+        num_heads=[6, 12, 24, 48],
+        out_indices=(1, 2, 3),
+        window_size=12,
+        ape=False,
+        drop_path_rate=0.3,
+        patch_norm=True,
+        use_checkpoint=False,
+        pretrained='./ckpt/co_deformable_detr_swin_large_1x_coco.pth'),
+    neck=dict(
+        type='ChannelMapper',
+        in_channels=[384, 768, 1536],
+        kernel_size=1,
+        out_channels=256,
+        act_cfg=None,
+        norm_cfg=dict(type='GN', num_groups=32),
+        num_outs=4),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            octave_base_scale=4,
+            scales_per_octave=3,
+            ratios=[0.5, 1.0, 2.0],
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[0.0, 0.0, 0.0, 0.0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=12.0)),
+    query_head=dict(
+        type='CoDeformDETRHead',
+        num_query=300,
+        num_classes=5,
+        in_channels=2048,
+        sync_cls_avg_factor=True,
+        with_box_refine=True,
+        as_two_stage=True,
+        mixed_selection=True,
+        transformer=dict(
+            type='CoDeformableDetrTransformer',
+            num_co_heads=2,
+            encoder=dict(
+                type='DetrTransformerEncoder',
+                num_layers=6,
+                transformerlayers=dict(
+                    type='BaseTransformerLayer',
+                    attn_cfgs=dict(
+                        type='MultiScaleDeformableAttention',
+                        embed_dims=256,
+                        dropout=0.0),
+                    feedforward_channels=2048,
+                    ffn_dropout=0.0,
+                    operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
+            decoder=dict(
+                type='CoDeformableDetrTransformerDecoder',
+                num_layers=6,
+                return_intermediate=True,
+                look_forward_twice=True,
+                transformerlayers=dict(
+                    type='DetrTransformerDecoderLayer',
+                    attn_cfgs=[
+                        dict(
+                            type='MultiheadAttention',
+                            embed_dims=256,
+                            num_heads=8,
+                            dropout=0.0),
+                        dict(
+                            type='MultiScaleDeformableAttention',
+                            embed_dims=256,
+                            dropout=0.0)
+                    ],
+                    feedforward_channels=2048,
+                    ffn_dropout=0.0,
+                    operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
+                                     'ffn', 'norm')))),
+        positional_encoding=dict(
+            type='SinePositionalEncoding',
+            num_feats=128,
+            normalize=True,
+            offset=-0.5),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=2.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=5.0),
+        loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
+    roi_head=[
+        dict(
+            type='CoStandardRoIHead',
+            bbox_roi_extractor=dict(
+                type='SingleRoIExtractor',
+                roi_layer=dict(
+                    type='RoIAlign', output_size=7, sampling_ratio=0),
+                out_channels=256,
+                featmap_strides=[8, 16, 32, 64],
+                finest_scale=112),
+            bbox_head=dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=5,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0.0, 0.0, 0.0, 0.0],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=False,
+                reg_decoded_bbox=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=12.0),
+                loss_bbox=dict(type='GIoULoss', loss_weight=120.0)))
+    ],
+    bbox_head=[
+        dict(
+            type='CoATSSHead',
+            num_classes=5,
+            in_channels=256,
+            stacked_convs=1,
+            feat_channels=256,
+            anchor_generator=dict(
+                type='AnchorGenerator',
+                ratios=[1.0],
+                octave_base_scale=8,
+                scales_per_octave=1,
+                strides=[8, 16, 32, 64, 128]),
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0.0, 0.0, 0.0, 0.0],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            loss_cls=dict(
+                type='FocalLoss',
+                use_sigmoid=True,
+                gamma=2.0,
+                alpha=0.25,
+                loss_weight=12.0),
+            loss_bbox=dict(type='GIoULoss', loss_weight=24.0),
+            loss_centerness=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0))
+    ],
+    train_cfg=[
+        dict(
+            assigner=dict(
+                type='HungarianAssigner',
+                cls_cost=dict(type='FocalLossCost', weight=2.0),
+                reg_cost=dict(
+                    type='BBoxL1Cost', weight=5.0, box_format='xywh'),
+                iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
+        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=4000,
+                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=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False)),
+        dict(
+            assigner=dict(type='ATSSAssigner', topk=9),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False)
+    ],
+    test_cfg=[
+        dict(max_per_img=100),
+        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=0.0,
+                nms=dict(type='nms', iou_threshold=0.5),
+                max_per_img=100)),
+        dict(
+            nms_pre=1000,
+            min_bbox_size=0,
+            score_thr=0.0,
+            nms=dict(type='nms', iou_threshold=0.6),
+            max_per_img=100)
+    ])
+optimizer = dict(
+    type='AdamW',
+    lr=0.0002,
+    weight_decay=0.05,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            backbone=dict(lr_mult=0.1),
+            sampling_offsets=dict(lr_mult=0.1),
+            reference_points=dict(lr_mult=0.1))))
+optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
+lr_config = dict(policy='step', step=[11])
+runner = dict(type='EpochBasedRunner', max_epochs=200)
+pretrained = './ckpt/co_deformable_detr_swin_large_1x_coco.pth'
+resume = False
+work_dir = 'work_dirs/co_deformable_detr_swin_large_1x_ct'
+auto_resume = False
+gpu_ids = range(0, 8)

co_deformable_detr_swin_large_1x_ct/epoch_50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21211f7d4b3e34daa235cb2f5840093e1fe7653329e421f8668bee6958cf12b7
+size 2821415790

co_dino_5scale_r50_1x_ct/co_dino_5scale_r50_1x_ct.py

@@ -0,0 +1,411 @@
+dataset_type = 'CocoDataset'
+data_root = 'data/slice_dataset_maximum_0402/'
+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='RandomFlip', flip_ratio=0.5),
+    dict(
+        type='AutoAugment',
+        policies=[[{
+            'type': 'Resize',
+            'img_scale': [(512, 512)],
+            'multiscale_mode': 'value',
+            'keep_ratio': True
+        }],
+                  [{
+                      'type': 'Resize',
+                      'img_scale': [(512, 512)],
+                      'multiscale_mode': 'value',
+                      'keep_ratio': True
+                  }, {
+                      'type': 'RandomCrop',
+                      'crop_type': 'absolute_range',
+                      'crop_size': (512, 512),
+                      'allow_negative_crop': True
+                  }, {
+                      'type': 'Resize',
+                      'img_scale': [(512, 512)],
+                      'multiscale_mode': 'value',
+                      'override': True,
+                      'keep_ratio': True
+                  }]]),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=1),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(512, 512),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=1),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=4,
+    train=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/train.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/train/',
+        filter_empty_gt=False,
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(
+                type='AutoAugment',
+                policies=[[{
+                    'type': 'Resize',
+                    'img_scale': [(512, 512)],
+                    'multiscale_mode': 'value',
+                    'keep_ratio': True
+                }],
+                          [{
+                              'type': 'Resize',
+                              'img_scale': [(512, 512)],
+                              'multiscale_mode': 'value',
+                              'keep_ratio': True
+                          }, {
+                              'type': 'RandomCrop',
+                              'crop_type': 'absolute_range',
+                              'crop_size': (512, 512),
+                              'allow_negative_crop': True
+                          }, {
+                              'type': 'Resize',
+                              'img_scale': [(512, 512)],
+                              'multiscale_mode': 'value',
+                              'override': True,
+                              'keep_ratio': True
+                          }]]),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=1),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+        ]),
+    val=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/test.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/test/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(512, 512),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=1),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]),
+    test=dict(
+        type='CocoDataset',
+        ann_file='data/slice_dataset_maximum_0402/annotations/test.json',
+        img_prefix='data/slice_dataset_maximum_0402/images/test/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(512, 512),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=1),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]))
+evaluation = dict(interval=1, metric='bbox')
+checkpoint_config = dict(interval=1)
+log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
+custom_hooks = [dict(type='NumClassCheckHook')]
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = './ckpt/co_dino_5scale_r50_1x_coco.pth'
+resume_from = None
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=False, base_batch_size=16)
+num_dec_layer = 6
+lambda_2 = 2.0
+model = dict(
+    type='CoDETR',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=False),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='ChannelMapper',
+        in_channels=[256, 512, 1024, 2048],
+        kernel_size=1,
+        out_channels=256,
+        act_cfg=None,
+        norm_cfg=dict(type='GN', num_groups=32),
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            octave_base_scale=4,
+            scales_per_octave=3,
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[0.0, 0.0, 0.0, 0.0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=12.0)),
+    query_head=dict(
+        type='CoDINOHead',
+        num_query=900,
+        num_classes=5,
+        num_feature_levels=5,
+        in_channels=2048,
+        sync_cls_avg_factor=True,
+        as_two_stage=True,
+        with_box_refine=True,
+        mixed_selection=True,
+        dn_cfg=dict(
+            type='CdnQueryGenerator',
+            noise_scale=dict(label=0.5, box=1.0),
+            group_cfg=dict(dynamic=True, num_groups=None, num_dn_queries=100)),
+        transformer=dict(
+            type='CoDinoTransformer',
+            with_pos_coord=True,
+            with_coord_feat=False,
+            num_co_heads=2,
+            num_feature_levels=5,
+            encoder=dict(
+                type='DetrTransformerEncoder',
+                num_layers=6,
+                with_cp=4,
+                transformerlayers=dict(
+                    type='BaseTransformerLayer',
+                    attn_cfgs=dict(
+                        type='MultiScaleDeformableAttention',
+                        embed_dims=256,
+                        num_levels=5,
+                        dropout=0.0),
+                    feedforward_channels=2048,
+                    ffn_dropout=0.0,
+                    operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
+            decoder=dict(
+                type='DinoTransformerDecoder',
+                num_layers=6,
+                return_intermediate=True,
+                transformerlayers=dict(
+                    type='DetrTransformerDecoderLayer',
+                    attn_cfgs=[
+                        dict(
+                            type='MultiheadAttention',
+                            embed_dims=256,
+                            num_heads=8,
+                            dropout=0.0),
+                        dict(
+                            type='MultiScaleDeformableAttention',
+                            embed_dims=256,
+                            num_levels=5,
+                            dropout=0.0)
+                    ],
+                    feedforward_channels=2048,
+                    ffn_dropout=0.0,
+                    operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
+                                     'ffn', 'norm')))),
+        positional_encoding=dict(
+            type='SinePositionalEncoding',
+            num_feats=128,
+            temperature=20,
+            normalize=True),
+        loss_cls=dict(
+            type='QualityFocalLoss',
+            use_sigmoid=True,
+            beta=2.0,
+            loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=5.0),
+        loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
+    roi_head=[
+        dict(
+            type='CoStandardRoIHead',
+            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, 64],
+                finest_scale=56),
+            bbox_head=dict(
+                type='Shared2FCBBoxHead',
+                in_channels=256,
+                fc_out_channels=1024,
+                roi_feat_size=7,
+                num_classes=5,
+                bbox_coder=dict(
+                    type='DeltaXYWHBBoxCoder',
+                    target_means=[0.0, 0.0, 0.0, 0.0],
+                    target_stds=[0.1, 0.1, 0.2, 0.2]),
+                reg_class_agnostic=False,
+                reg_decoded_bbox=True,
+                loss_cls=dict(
+                    type='CrossEntropyLoss',
+                    use_sigmoid=False,
+                    loss_weight=12.0),
+                loss_bbox=dict(type='GIoULoss', loss_weight=120.0)))
+    ],
+    bbox_head=[
+        dict(
+            type='CoATSSHead',
+            num_classes=5,
+            in_channels=256,
+            stacked_convs=1,
+            feat_channels=256,
+            anchor_generator=dict(
+                type='AnchorGenerator',
+                ratios=[1.0],
+                octave_base_scale=8,
+                scales_per_octave=1,
+                strides=[4, 8, 16, 32, 64, 128]),
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0.0, 0.0, 0.0, 0.0],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            loss_cls=dict(
+                type='FocalLoss',
+                use_sigmoid=True,
+                gamma=2.0,
+                alpha=0.25,
+                loss_weight=12.0),
+            loss_bbox=dict(type='GIoULoss', loss_weight=24.0),
+            loss_centerness=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0))
+    ],
+    train_cfg=[
+        dict(
+            assigner=dict(
+                type='HungarianAssigner',
+                cls_cost=dict(type='FocalLossCost', weight=2.0),
+                reg_cost=dict(
+                    type='BBoxL1Cost', weight=5.0, box_format='xywh'),
+                iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
+        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=4000,
+                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=False,
+                    ignore_iof_thr=-1),
+                sampler=dict(
+                    type='RandomSampler',
+                    num=512,
+                    pos_fraction=0.25,
+                    neg_pos_ub=-1,
+                    add_gt_as_proposals=True),
+                pos_weight=-1,
+                debug=False)),
+        dict(
+            assigner=dict(type='ATSSAssigner', topk=9),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False)
+    ],
+    test_cfg=[
+        dict(max_per_img=300, nms=dict(type='soft_nms', iou_threshold=0.8)),
+        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=0.0,
+                nms=dict(type='nms', iou_threshold=0.5),
+                max_per_img=100)),
+        dict(
+            nms_pre=1000,
+            min_bbox_size=0,
+            score_thr=0.0,
+            nms=dict(type='nms', iou_threshold=0.6),
+            max_per_img=100)
+    ])
+optimizer = dict(
+    type='AdamW',
+    lr=0.0002,
+    weight_decay=0.0001,
+    paramwise_cfg=dict(custom_keys=dict(backbone=dict(lr_mult=0.1))))
+optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
+lr_config = dict(policy='step', step=[11])
+runner = dict(type='EpochBasedRunner', max_epochs=200)
+pretrained = './ckpt/co_dino_5scale_r50_1x_coco.pth'
+work_dir = 'work_dirs/co_dino_5scale_r50_1x_ct'
+auto_resume = False
+gpu_ids = range(0, 8)

co_dino_5scale_r50_1x_ct/epoch_50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f743702df7c27116b9cc6ad7492b54e0f8c6a2f7392de8600fcc6cf8481c7789
+size 772477915