Upload pose/vitpose_base_68kpt_config.py with huggingface_hub

pose/vitpose_base_68kpt_config.py

@@ -0,0 +1,403 @@
+default_scope = 'mmpose'
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        type='CheckpointHook',
+        interval=10,
+        save_best='NME',
+        rule='less',
+        max_keep_ckpts=2),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='PoseVisualizationHook', enable=False))
+custom_hooks = [dict(type='SyncBuffersHook')]
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'))
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='PoseLocalVisualizer',
+    vis_backends=[dict(type='LocalVisBackend')],
+    name='visualizer')
+log_processor = dict(
+    type='LogProcessor', window_size=50, by_epoch=True, num_digits=6)
+log_level = 'INFO'
+# load_from = 'Y:\\MacFace\\results\\coco_whface\\best_NME_epoch_20.pth'
+resume = False
+backend_args = dict(backend='local')
+train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+dataset_info = dict(
+    dataset_name='coco_wholebody_face',
+    paper_info=dict(
+        author=
+        'Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping',
+        title='Whole-Body Human Pose Estimation in the Wild',
+        container=
+        'Proceedings of the European Conference on Computer Vision (ECCV)',
+        year='2020',
+        homepage='https://github.com/jin-s13/COCO-WholeBody/'),
+    keypoint_info=dict({
+        0:
+        dict(name='face-0', id=0, color=[255, 0, 0], type='', swap='face-16'),
+        1:
+        dict(name='face-1', id=1, color=[255, 0, 0], type='', swap='face-15'),
+        2:
+        dict(name='face-2', id=2, color=[255, 0, 0], type='', swap='face-14'),
+        3:
+        dict(name='face-3', id=3, color=[255, 0, 0], type='', swap='face-13'),
+        4:
+        dict(name='face-4', id=4, color=[255, 0, 0], type='', swap='face-12'),
+        5:
+        dict(name='face-5', id=5, color=[255, 0, 0], type='', swap='face-11'),
+        6:
+        dict(name='face-6', id=6, color=[255, 0, 0], type='', swap='face-10'),
+        7:
+        dict(name='face-7', id=7, color=[255, 0, 0], type='', swap='face-9'),
+        8:
+        dict(name='face-8', id=8, color=[255, 0, 0], type='', swap=''),
+        9:
+        dict(name='face-9', id=9, color=[255, 0, 0], type='', swap='face-7'),
+        10:
+        dict(name='face-10', id=10, color=[255, 0, 0], type='', swap='face-6'),
+        11:
+        dict(name='face-11', id=11, color=[255, 0, 0], type='', swap='face-5'),
+        12:
+        dict(name='face-12', id=12, color=[255, 0, 0], type='', swap='face-4'),
+        13:
+        dict(name='face-13', id=13, color=[255, 0, 0], type='', swap='face-3'),
+        14:
+        dict(name='face-14', id=14, color=[255, 0, 0], type='', swap='face-2'),
+        15:
+        dict(name='face-15', id=15, color=[255, 0, 0], type='', swap='face-1'),
+        16:
+        dict(name='face-16', id=16, color=[255, 0, 0], type='', swap='face-0'),
+        17:
+        dict(
+            name='face-17', id=17, color=[255, 0, 0], type='', swap='face-26'),
+        18:
+        dict(
+            name='face-18', id=18, color=[255, 0, 0], type='', swap='face-25'),
+        19:
+        dict(
+            name='face-19', id=19, color=[255, 0, 0], type='', swap='face-24'),
+        20:
+        dict(
+            name='face-20', id=20, color=[255, 0, 0], type='', swap='face-23'),
+        21:
+        dict(
+            name='face-21', id=21, color=[255, 0, 0], type='', swap='face-22'),
+        22:
+        dict(
+            name='face-22', id=22, color=[255, 0, 0], type='', swap='face-21'),
+        23:
+        dict(
+            name='face-23', id=23, color=[255, 0, 0], type='', swap='face-20'),
+        24:
+        dict(
+            name='face-24', id=24, color=[255, 0, 0], type='', swap='face-19'),
+        25:
+        dict(
+            name='face-25', id=25, color=[255, 0, 0], type='', swap='face-18'),
+        26:
+        dict(
+            name='face-26', id=26, color=[255, 0, 0], type='', swap='face-17'),
+        27:
+        dict(name='face-27', id=27, color=[255, 0, 0], type='', swap=''),
+        28:
+        dict(name='face-28', id=28, color=[255, 0, 0], type='', swap=''),
+        29:
+        dict(name='face-29', id=29, color=[255, 0, 0], type='', swap=''),
+        30:
+        dict(name='face-30', id=30, color=[255, 0, 0], type='', swap=''),
+        31:
+        dict(
+            name='face-31', id=31, color=[255, 0, 0], type='', swap='face-35'),
+        32:
+        dict(
+            name='face-32', id=32, color=[255, 0, 0], type='', swap='face-34'),
+        33:
+        dict(name='face-33', id=33, color=[255, 0, 0], type='', swap=''),
+        34:
+        dict(
+            name='face-34', id=34, color=[255, 0, 0], type='', swap='face-32'),
+        35:
+        dict(
+            name='face-35', id=35, color=[255, 0, 0], type='', swap='face-31'),
+        36:
+        dict(
+            name='face-36', id=36, color=[255, 0, 0], type='', swap='face-45'),
+        37:
+        dict(
+            name='face-37', id=37, color=[255, 0, 0], type='', swap='face-44'),
+        38:
+        dict(
+            name='face-38', id=38, color=[255, 0, 0], type='', swap='face-43'),
+        39:
+        dict(
+            name='face-39', id=39, color=[255, 0, 0], type='', swap='face-42'),
+        40:
+        dict(
+            name='face-40', id=40, color=[255, 0, 0], type='', swap='face-47'),
+        41:
+        dict(
+            name='face-41', id=41, color=[255, 0, 0], type='', swap='face-46'),
+        42:
+        dict(
+            name='face-42', id=42, color=[255, 0, 0], type='', swap='face-39'),
+        43:
+        dict(
+            name='face-43', id=43, color=[255, 0, 0], type='', swap='face-38'),
+        44:
+        dict(
+            name='face-44', id=44, color=[255, 0, 0], type='', swap='face-37'),
+        45:
+        dict(
+            name='face-45', id=45, color=[255, 0, 0], type='', swap='face-36'),
+        46:
+        dict(
+            name='face-46', id=46, color=[255, 0, 0], type='', swap='face-41'),
+        47:
+        dict(
+            name='face-47', id=47, color=[255, 0, 0], type='', swap='face-40'),
+        48:
+        dict(
+            name='face-48', id=48, color=[255, 0, 0], type='', swap='face-54'),
+        49:
+        dict(
+            name='face-49', id=49, color=[255, 0, 0], type='', swap='face-53'),
+        50:
+        dict(
+            name='face-50', id=50, color=[255, 0, 0], type='', swap='face-52'),
+        51:
+        dict(name='face-51', id=52, color=[255, 0, 0], type='', swap=''),
+        52:
+        dict(
+            name='face-52', id=52, color=[255, 0, 0], type='', swap='face-50'),
+        53:
+        dict(
+            name='face-53', id=53, color=[255, 0, 0], type='', swap='face-49'),
+        54:
+        dict(
+            name='face-54', id=54, color=[255, 0, 0], type='', swap='face-48'),
+        55:
+        dict(
+            name='face-55', id=55, color=[255, 0, 0], type='', swap='face-59'),
+        56:
+        dict(
+            name='face-56', id=56, color=[255, 0, 0], type='', swap='face-58'),
+        57:
+        dict(name='face-57', id=57, color=[255, 0, 0], type='', swap=''),
+        58:
+        dict(
+            name='face-58', id=58, color=[255, 0, 0], type='', swap='face-56'),
+        59:
+        dict(
+            name='face-59', id=59, color=[255, 0, 0], type='', swap='face-55'),
+        60:
+        dict(
+            name='face-60', id=60, color=[255, 0, 0], type='', swap='face-64'),
+        61:
+        dict(
+            name='face-61', id=61, color=[255, 0, 0], type='', swap='face-63'),
+        62:
+        dict(name='face-62', id=62, color=[255, 0, 0], type='', swap=''),
+        63:
+        dict(
+            name='face-63', id=63, color=[255, 0, 0], type='', swap='face-61'),
+        64:
+        dict(
+            name='face-64', id=64, color=[255, 0, 0], type='', swap='face-60'),
+        65:
+        dict(
+            name='face-65', id=65, color=[255, 0, 0], type='', swap='face-67'),
+        66:
+        dict(name='face-66', id=66, color=[255, 0, 0], type='', swap=''),
+        67:
+        dict(
+            name='face-67', id=67, color=[255, 0, 0], type='', swap='face-65')
+    }),
+    skeleton_info=dict(),
+    joint_weights=[
+        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
+        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
+        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
+        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
+        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0
+    ],
+    sigmas=[
+        0.042, 0.043, 0.044, 0.043, 0.04, 0.035, 0.031, 0.025, 0.02, 0.023,
+        0.029, 0.032, 0.037, 0.038, 0.043, 0.041, 0.045, 0.013, 0.012, 0.011,
+        0.011, 0.012, 0.012, 0.011, 0.011, 0.013, 0.015, 0.009, 0.007, 0.007,
+        0.007, 0.012, 0.009, 0.008, 0.016, 0.01, 0.017, 0.011, 0.009, 0.011,
+        0.009, 0.007, 0.013, 0.008, 0.011, 0.012, 0.01, 0.034, 0.008, 0.008,
+        0.009, 0.008, 0.008, 0.007, 0.01, 0.008, 0.009, 0.009, 0.009, 0.007,
+        0.007, 0.008, 0.011, 0.008, 0.008, 0.008, 0.01, 0.008
+    ])
+custom_imports = dict(
+    imports=['mmpose.engine.optim_wrappers.layer_decay_optim_wrapper'],
+    allow_failed_imports=False)
+optim_wrapper = dict(
+    optimizer=dict(
+        type='AdamW', lr=1e-05, betas=(0.9, 0.999), weight_decay=0.1),
+    paramwise_cfg=dict(
+        num_layers=24,
+        layer_decay_rate=0.8,
+        custom_keys=dict(
+            bias=dict(decay_multi=0.0),
+            pos_embed=dict(decay_mult=0.0),
+            relative_position_bias_table=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0))),
+    constructor='LayerDecayOptimWrapperConstructor',
+    clip_grad=dict(max_norm=1.0, norm_type=2),
+    type='AmpOptimWrapper',
+    loss_scale='dynamic')
+
+param_scheduler = [
+    dict(
+        type='LinearLR', begin=0, end=500, start_factor=0.0001,
+        by_epoch=False),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=210,
+        milestones=[170, 200],
+        gamma=0.1,
+        by_epoch=True)
+]
+
+auto_scale_lr = dict(base_batch_size=512)
+codec = dict(
+    type='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)
+
+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(
+        # type='mmcls.VisionTransformer',
+        type='mmpretrain.VisionTransformer',
+        arch='large',
+        img_size=(256, 192),
+        patch_size=16,
+        qkv_bias=True,
+        drop_path_rate=0.5,
+        with_cls_token=False,
+        out_type='featmap',
+        # output_cls_token=False,
+        patch_cfg=dict(padding=2),
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint=
+            r".\vitpose_cocowbf_pfv1_68kpts.pth"
+            )
+            ),
+    head=dict(
+        type='HeatmapHead',
+        in_channels=1024,
+        out_channels=68,
+        deconv_out_channels=(256, 256),
+        deconv_kernel_sizes=(4, 4),
+        loss=dict(type='KeypointMSELoss', use_target_weight=True),
+        decoder=dict(
+            type='UDPHeatmap',
+            input_size=(192, 256),
+            heatmap_size=(48, 64),
+            sigma=2)),
+    test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=False))
+
+
+data_root = r"."
+dataset_type = 'CocoWholeBodyFaceDataset'
+data_mode = 'topdown'
+train_pipeline = [
+    dict(type='LoadImage'),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='RandomFlip', direction='horizontal'),
+    dict(type='RandomHalfBody'),
+    dict(type='RandomBBoxTransform'),
+    dict(type='TopdownAffine', input_size=(192, 256), use_udp=True),
+    dict(
+        type='GenerateTarget',
+        encoder=dict(
+            type='UDPHeatmap',
+            input_size=(192, 256),
+            heatmap_size=(48, 64),
+            sigma=2)),
+    dict(type='PackPoseInputs')
+]
+val_pipeline = [
+    dict(type='LoadImage'),
+    dict(type='GetBBoxCenterScale'),
+    dict(type='TopdownAffine', input_size=(192, 256), use_udp=True),
+    dict(type='PackPoseInputs')
+]
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        data_mode='topdown',
+        ann_file=r".\train.json",
+        pipeline=[
+            dict(type='LoadImage'),
+            dict(type='GetBBoxCenterScale'),
+            dict(type='RandomFlip', direction='horizontal'),
+            dict(type='RandomHalfBody'),
+            dict(type='RandomBBoxTransform'),
+            dict(type='TopdownAffine', input_size=(192, 256), use_udp=True),
+            dict(
+                type='GenerateTarget',
+                encoder=dict(
+                    type='UDPHeatmap',
+                    input_size=(192, 256),
+                    heatmap_size=(48, 64),
+                    sigma=2)),
+            dict(type='PackPoseInputs')
+        ]))
+val_dataloader = dict(
+    batch_size=4,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    dataset=dict(
+        data_mode='topdown',
+        ann_file=r".\val.json",
+        bbox_file=None,
+        test_mode=True,
+        pipeline=[
+            dict(type='LoadImage'),
+            dict(type='GetBBoxCenterScale'),
+            dict(type='TopdownAffine', input_size=(192, 256), use_udp=True),
+            dict(type='PackPoseInputs')
+        ]))
+test_dataloader = dict(
+    batch_size=4,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
+    dataset=dict(
+        data_mode='topdown',
+        ann_file=r".\test.json",
+        bbox_file=None,
+        test_mode=True,
+        pipeline=[
+            dict(type='LoadImage'),
+            dict(type='GetBBoxCenterScale'),
+            dict(type='TopdownAffine', input_size=(192, 256), use_udp=True),
+            dict(type='PackPoseInputs')
+        ]))
+val_evaluator = dict(type='NME', norm_mode='keypoint_distance')
+test_evaluator = dict(type='NME', norm_mode='keypoint_distance')
+# model_wrapper_cfg = dict(type='MMFullyShardedDataParallel', cpu_offload=True)
+launcher = 'none'
+work_dir=r"./"