Upload 7 files

gd-ogc.py

@@ -0,0 +1,43 @@
+batch_size = 1
+modelname = "groundingdino"
+backbone = "swin_T_224_1k"
+position_embedding = "sine"
+pe_temperatureH = 20
+pe_temperatureW = 20
+return_interm_indices = [1, 2, 3]
+backbone_freeze_keywords = None
+enc_layers = 6
+dec_layers = 6
+pre_norm = False
+dim_feedforward = 2048
+hidden_dim = 256
+dropout = 0.0
+nheads = 8
+num_queries = 900
+query_dim = 4
+num_patterns = 0
+num_feature_levels = 4
+enc_n_points = 4
+dec_n_points = 4
+two_stage_type = "standard"
+two_stage_bbox_embed_share = False
+two_stage_class_embed_share = False
+transformer_activation = "relu"
+dec_pred_bbox_embed_share = True
+dn_box_noise_scale = 1.0
+dn_label_noise_ratio = 0.5
+dn_label_coef = 1.0
+dn_bbox_coef = 1.0
+embed_init_tgt = True
+dn_labelbook_size = 2000
+max_text_len = 256
+text_encoder_type = "bert-base-uncased"
+use_text_enhancer = True
+use_fusion_layer = True
+use_checkpoint = True
+use_transformer_ckpt = True
+use_text_cross_attention = True
+text_dropout = 0.0
+fusion_dropout = 0.0
+fusion_droppath = 0.1
+sub_sentence_present = True

rtmdet-l.py

@@ -0,0 +1,178 @@
+_base_ = [
+    'mmdet::_base_/default_runtime.py', 'mmdet::_base_/schedules/schedule_1x.py',
+    'mmdet::_base_/datasets/coco_detection.py', 'mmdet::rtmdet/rtmdet_tta.py'
+]
+model = dict(
+    type='RTMDet',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.53, 116.28, 123.675],
+        std=[57.375, 57.12, 58.395],
+        bgr_to_rgb=False,
+        batch_augments=None),
+    backbone=dict(
+        type='CSPNeXt',
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=1,
+        widen_factor=1,
+        channel_attention=True,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    neck=dict(
+        type='CSPNeXtPAFPN',
+        in_channels=[256, 512, 1024],
+        out_channels=256,
+        num_csp_blocks=3,
+        expand_ratio=0.5,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    bbox_head=dict(
+        type='RTMDetSepBNHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=2,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='MlvlPointGenerator', offset=0, strides=[8, 16, 32]),
+        bbox_coder=dict(type='DistancePointBBoxCoder'),
+        loss_cls=dict(
+            type='QualityFocalLoss',
+            use_sigmoid=True,
+            beta=2.0,
+            loss_weight=1.0),
+        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
+        with_objectness=False,
+        exp_on_reg=True,
+        share_conv=True,
+        pred_kernel_size=1,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    train_cfg=dict(
+        assigner=dict(type='DynamicSoftLabelAssigner', topk=13),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=30000,
+        min_bbox_size=0,
+        score_thr=0.001,
+        nms=dict(type='nms', iou_threshold=0.65),
+        max_per_img=300),
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='CachedMosaic', img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type='RandomResize',
+        scale=(1280, 1280),
+        ratio_range=(0.1, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='CachedMixUp',
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type='mmdet.PackDetInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=(640, 640),
+        ratio_range=(0.1, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type='mmdet.PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='Resize', scale=(640, 640), keep_ratio=True),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=32,
+    num_workers=10,
+    batch_sampler=None,
+    pin_memory=True,
+    dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=5, num_workers=10, dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+max_epochs = 300
+stage2_num_epochs = 20
+base_lr = 0.004
+interval = 10
+
+train_cfg = dict(
+    max_epochs=max_epochs,
+    val_interval=interval,
+    dynamic_intervals=[(max_epochs - stage2_num_epochs, 1)])
+
+val_evaluator = dict(proposal_nums=(100, 1, 10))
+test_evaluator = val_evaluator
+
+# optimizer
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        # use cosine lr from 150 to 300 epoch
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# hooks
+default_hooks = dict(
+    checkpoint=dict(
+        interval=interval,
+        max_keep_ckpts=3  # only keep latest 3 checkpoints
+    ))
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='PipelineSwitchHook',
+        switch_epoch=max_epochs - stage2_num_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]

rtmdet-m.py

@@ -0,0 +1,7 @@
+_base_ = "./rtmdet-l.py"
+
+model = dict(
+    backbone=dict(deepen_factor=0.67, widen_factor=0.75),
+    neck=dict(in_channels=[192, 384, 768], out_channels=192, num_csp_blocks=2),
+    bbox_head=dict(in_channels=192, feat_channels=192),
+)

rtmdet-s.py

@@ -0,0 +1,62 @@
+_base_ = 'mmdet::rtmdet/rtmdet_l_8xb32-300e_coco.py'
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth'  # noqa
+model = dict(
+    backbone=dict(
+        deepen_factor=0.33,
+        widen_factor=0.5,
+        init_cfg=dict(
+            type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+    neck=dict(in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1),
+    bbox_head=dict(in_channels=128, feat_channels=128, exp_on_reg=False))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='CachedMosaic', img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type='RandomResize',
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='CachedMixUp',
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type='PackDetInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=(640, 640),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type='PackDetInputs')
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='PipelineSwitchHook',
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]

rtmpose-l.py

@@ -0,0 +1,232 @@
+_base_ = ['mmpose::_base_/default_runtime.py']
+
+# runtime
+max_epochs = 420
+stage2_num_epochs = 30
+base_lr = 4e-3
+
+train_cfg = dict(max_epochs=max_epochs, val_interval=10)
+randomness = dict(seed=21)
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        # use cosine lr from 210 to 420 epoch
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# automatically scaling LR based on the actual training batch size
+auto_scale_lr = dict(base_batch_size=1024)
+
+# codec settings
+codec = dict(
+    type='SimCCLabel',
+    input_size=(192, 256),
+    sigma=(4.9, 5.66),
+    simcc_split_ratio=2.0,
+    normalize=False,
+    use_dark=False)
+
+# model settings
+model = dict(
+    type='TopdownPoseEstimator',
+    data_preprocessor=dict(
+        type='PoseDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True),
+    backbone=dict(
+        _scope_='mmdet',
+        type='CSPNeXt',
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=1.,
+        widen_factor=1.,
+        out_indices=(4, ),
+        channel_attention=True,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU'),
+        init_cfg=dict(
+            type='Pretrained',
+            prefix='backbone.',
+            checkpoint='https://download.openmmlab.com/mmpose/v1/projects/'
+            'rtmposev1/cspnext-l_udp-aic-coco_210e-256x192-273b7631_20230130.pth'  # noqa
+        )),
+    head=dict(
+        type='RTMCCHead',
+        in_channels=1024,
+        out_channels=17,
+        input_size=codec['input_size'],
+        in_featuremap_size=(6, 8),
+        simcc_split_ratio=codec['simcc_split_ratio'],
+        final_layer_kernel_size=7,
+        gau_cfg=dict(
+            hidden_dims=256,
+            s=128,
+            expansion_factor=2,
+            dropout_rate=0.,
+            drop_path=0.,
+            act_fn='SiLU',
+            use_rel_bias=False,
+            pos_enc=False),
+        loss=dict(
+            type='KLDiscretLoss',
+            use_target_weight=True,
+            beta=10.,
+            label_softmax=True),
+        decoder=codec),
+    test_cfg=dict(flip_test=True))
+
+# base dataset settings
+dataset_type = 'CocoDataset'
+data_mode = 'topdown'
+data_root = 'data/coco/'
+
+backend_args = dict(backend='local')
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         f'{data_root}': 's3://openmmlab/datasets/detection/coco/',
+#         f'{data_root}': 's3://openmmlab/datasets/detection/coco/'
+#     }))
+
+# pipelines
+train_pipeline = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(
+        type='RandomBBoxTransform', scale_factor=[0.6, 1.4], rotate_factor=80),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='mmdet.YOLOXHSVRandomAug'),
+    dict(
+        type='Albumentation',
+        transforms=[
+            dict(type='Blur', p=0.1),
+            dict(type='MedianBlur', p=0.1),
+            dict(
+                type='CoarseDropout',
+                max_holes=1,
+                max_height=0.4,
+                max_width=0.4,
+                min_holes=1,
+                min_height=0.2,
+                min_width=0.2,
+                p=1.),
+        ]),
+    dict(type='GenerateTarget', encoder=codec),
+    dict(type='PackPoseInputs')
+]
+val_pipeline = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='PackPoseInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(
+        type='RandomBBoxTransform',
+        shift_factor=0.,
+        scale_factor=[0.75, 1.25],
+        rotate_factor=60),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='mmdet.YOLOXHSVRandomAug'),
+    dict(
+        type='Albumentation',
+        transforms=[
+            dict(type='Blur', p=0.1),
+            dict(type='MedianBlur', p=0.1),
+            dict(
+                type='CoarseDropout',
+                max_holes=1,
+                max_height=0.4,
+                max_width=0.4,
+                min_holes=1,
+                min_height=0.2,
+                min_width=0.2,
+                p=0.5),
+        ]),
+    dict(type='GenerateTarget', encoder=codec),
+    dict(type='PackPoseInputs')
+]
+
+# data loaders
+train_dataloader = dict(
+    batch_size=256,
+    num_workers=10,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_mode=data_mode,
+        ann_file='annotations/person_keypoints_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        pipeline=train_pipeline,
+    ))
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=10,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_mode=data_mode,
+        ann_file='annotations/person_keypoints_val2017.json',
+        # bbox_file=f'{data_root}person_detection_results/'
+        # 'COCO_val2017_detections_AP_H_56_person.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+    ))
+test_dataloader = val_dataloader
+
+# hooks
+default_hooks = dict(
+    checkpoint=dict(save_best='coco/AP', rule='greater', max_keep_ckpts=1))
+
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='mmdet.PipelineSwitchHook',
+        switch_epoch=max_epochs - stage2_num_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]
+
+# evaluators
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/person_keypoints_val2017.json')
+test_evaluator = val_evaluator

rtmpose-m.py

@@ -0,0 +1,232 @@
+_base_ = ['mmpose::_base_/default_runtime.py']
+
+# runtime
+max_epochs = 420
+stage2_num_epochs = 30
+base_lr = 4e-3
+
+train_cfg = dict(max_epochs=max_epochs, val_interval=10)
+randomness = dict(seed=21)
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        # use cosine lr from 210 to 420 epoch
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# automatically scaling LR based on the actual training batch size
+auto_scale_lr = dict(base_batch_size=1024)
+
+# codec settings
+codec = dict(
+    type='SimCCLabel',
+    input_size=(192, 256),
+    sigma=(4.9, 5.66),
+    simcc_split_ratio=2.0,
+    normalize=False,
+    use_dark=False)
+
+# model settings
+model = dict(
+    type='TopdownPoseEstimator',
+    data_preprocessor=dict(
+        type='PoseDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True),
+    backbone=dict(
+        _scope_='mmdet',
+        type='CSPNeXt',
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=0.67,
+        widen_factor=0.75,
+        out_indices=(4, ),
+        channel_attention=True,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU'),
+        init_cfg=dict(
+            type='Pretrained',
+            prefix='backbone.',
+            checkpoint='https://download.openmmlab.com/mmpose/v1/projects/'
+            'rtmposev1/cspnext-m_udp-aic-coco_210e-256x192-f2f7d6f6_20230130.pth'  # noqa
+        )),
+    head=dict(
+        type='RTMCCHead',
+        in_channels=768,
+        out_channels=17,
+        input_size=codec['input_size'],
+        in_featuremap_size=(6, 8),
+        simcc_split_ratio=codec['simcc_split_ratio'],
+        final_layer_kernel_size=7,
+        gau_cfg=dict(
+            hidden_dims=256,
+            s=128,
+            expansion_factor=2,
+            dropout_rate=0.,
+            drop_path=0.,
+            act_fn='SiLU',
+            use_rel_bias=False,
+            pos_enc=False),
+        loss=dict(
+            type='KLDiscretLoss',
+            use_target_weight=True,
+            beta=10.,
+            label_softmax=True),
+        decoder=codec),
+    test_cfg=dict(flip_test=True))
+
+# base dataset settings
+dataset_type = 'CocoDataset'
+data_mode = 'topdown'
+data_root = 'data/coco/'
+
+backend_args = dict(backend='local')
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         f'{data_root}': 's3://openmmlab/datasets/detection/coco/',
+#         f'{data_root}': 's3://openmmlab/datasets/detection/coco/'
+#     }))
+
+# pipelines
+train_pipeline = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(
+        type='RandomBBoxTransform', scale_factor=[0.6, 1.4], rotate_factor=80),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='mmdet.YOLOXHSVRandomAug'),
+    dict(
+        type='Albumentation',
+        transforms=[
+            dict(type='Blur', p=0.1),
+            dict(type='MedianBlur', p=0.1),
+            dict(
+                type='CoarseDropout',
+                max_holes=1,
+                max_height=0.4,
+                max_width=0.4,
+                min_holes=1,
+                min_height=0.2,
+                min_width=0.2,
+                p=1.),
+        ]),
+    dict(type='GenerateTarget', encoder=codec),
+    dict(type='PackPoseInputs')
+]
+val_pipeline = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='PackPoseInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(
+        type='RandomBBoxTransform',
+        shift_factor=0.,
+        scale_factor=[0.75, 1.25],
+        rotate_factor=60),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='mmdet.YOLOXHSVRandomAug'),
+    dict(
+        type='Albumentation',
+        transforms=[
+            dict(type='Blur', p=0.1),
+            dict(type='MedianBlur', p=0.1),
+            dict(
+                type='CoarseDropout',
+                max_holes=1,
+                max_height=0.4,
+                max_width=0.4,
+                min_holes=1,
+                min_height=0.2,
+                min_width=0.2,
+                p=0.5),
+        ]),
+    dict(type='GenerateTarget', encoder=codec),
+    dict(type='PackPoseInputs')
+]
+
+# data loaders
+train_dataloader = dict(
+    batch_size=256,
+    num_workers=10,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_mode=data_mode,
+        ann_file='annotations/person_keypoints_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        pipeline=train_pipeline,
+    ))
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=10,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_mode=data_mode,
+        ann_file='annotations/person_keypoints_val2017.json',
+        # bbox_file=f'{data_root}person_detection_results/'
+        # 'COCO_val2017_detections_AP_H_56_person.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+    ))
+test_dataloader = val_dataloader
+
+# hooks
+default_hooks = dict(
+    checkpoint=dict(save_best='coco/AP', rule='greater', max_keep_ckpts=1))
+
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='mmdet.PipelineSwitchHook',
+        switch_epoch=max_epochs - stage2_num_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]
+
+# evaluators
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/person_keypoints_val2017.json')
+test_evaluator = val_evaluator

rtmpose-s.py

@@ -0,0 +1,232 @@
+_base_ = ['mmpose::_base_/default_runtime.py']
+
+# runtime
+max_epochs = 420
+stage2_num_epochs = 30
+base_lr = 4e-3
+
+train_cfg = dict(max_epochs=max_epochs, val_interval=10)
+randomness = dict(seed=21)
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        # use cosine lr from 210 to 420 epoch
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# automatically scaling LR based on the actual training batch size
+auto_scale_lr = dict(base_batch_size=1024)
+
+# codec settings
+codec = dict(
+    type='SimCCLabel',
+    input_size=(192, 256),
+    sigma=(4.9, 5.66),
+    simcc_split_ratio=2.0,
+    normalize=False,
+    use_dark=False)
+
+# model settings
+model = dict(
+    type='TopdownPoseEstimator',
+    data_preprocessor=dict(
+        type='PoseDataPreprocessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True),
+    backbone=dict(
+        _scope_='mmdet',
+        type='CSPNeXt',
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=0.33,
+        widen_factor=0.5,
+        out_indices=(4, ),
+        channel_attention=True,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU'),
+        init_cfg=dict(
+            type='Pretrained',
+            prefix='backbone.',
+            checkpoint='https://download.openmmlab.com/mmpose/v1/projects/'
+            'rtmposev1/cspnext-s_udp-aic-coco_210e-256x192-92f5a029_20230130.pth'  # noqa
+        )),
+    head=dict(
+        type='RTMCCHead',
+        in_channels=512,
+        out_channels=17,
+        input_size=codec['input_size'],
+        in_featuremap_size=(6, 8),
+        simcc_split_ratio=codec['simcc_split_ratio'],
+        final_layer_kernel_size=7,
+        gau_cfg=dict(
+            hidden_dims=256,
+            s=128,
+            expansion_factor=2,
+            dropout_rate=0.,
+            drop_path=0.,
+            act_fn='SiLU',
+            use_rel_bias=False,
+            pos_enc=False),
+        loss=dict(
+            type='KLDiscretLoss',
+            use_target_weight=True,
+            beta=10.,
+            label_softmax=True),
+        decoder=codec),
+    test_cfg=dict(flip_test=True))
+
+# base dataset settings
+dataset_type = 'CocoDataset'
+data_mode = 'topdown'
+data_root = 'data/coco/'
+
+backend_args = dict(backend='local')
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         f'{data_root}': 's3://openmmlab/datasets/detection/coco/',
+#         f'{data_root}': 's3://openmmlab/datasets/detection/coco/'
+#     }))
+
+# pipelines
+train_pipeline = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(
+        type='RandomBBoxTransform', scale_factor=[0.6, 1.4], rotate_factor=80),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='mmdet.YOLOXHSVRandomAug'),
+    dict(
+        type='Albumentation',
+        transforms=[
+            dict(type='Blur', p=0.1),
+            dict(type='MedianBlur', p=0.1),
+            dict(
+                type='CoarseDropout',
+                max_holes=1,
+                max_height=0.4,
+                max_width=0.4,
+                min_holes=1,
+                min_height=0.2,
+                min_width=0.2,
+                p=1.),
+        ]),
+    dict(type='GenerateTarget', encoder=codec),
+    dict(type='PackPoseInputs')
+]
+val_pipeline = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='PackPoseInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImage', backend_args=backend_args),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(
+        type='RandomBBoxTransform',
+        shift_factor=0.,
+        scale_factor=[0.75, 1.25],
+        rotate_factor=60),
+    dict(type='TopdownAffine', input_size=codec['input_size']),
+    dict(type='mmdet.YOLOXHSVRandomAug'),
+    dict(
+        type='Albumentation',
+        transforms=[
+            dict(type='Blur', p=0.1),
+            dict(type='MedianBlur', p=0.1),
+            dict(
+                type='CoarseDropout',
+                max_holes=1,
+                max_height=0.4,
+                max_width=0.4,
+                min_holes=1,
+                min_height=0.2,
+                min_width=0.2,
+                p=0.5),
+        ]),
+    dict(type='GenerateTarget', encoder=codec),
+    dict(type='PackPoseInputs')
+]
+
+# data loaders
+train_dataloader = dict(
+    batch_size=256,
+    num_workers=10,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_mode=data_mode,
+        ann_file='annotations/person_keypoints_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        pipeline=train_pipeline,
+    ))
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=10,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_mode=data_mode,
+        ann_file='annotations/person_keypoints_val2017.json',
+        # bbox_file=f'{data_root}person_detection_results/'
+        # 'COCO_val2017_detections_AP_H_56_person.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=val_pipeline,
+    ))
+test_dataloader = val_dataloader
+
+# hooks
+default_hooks = dict(
+    checkpoint=dict(save_best='coco/AP', rule='greater', max_keep_ckpts=1))
+
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='mmdet.PipelineSwitchHook',
+        switch_epoch=max_epochs - stage2_num_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]
+
+# evaluators
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/person_keypoints_val2017.json')
+test_evaluator = val_evaluator