search

open-mmlab / mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.
https://mmpose.readthedocs.io/en/latest/
Apache License 2.0
5.91k stars 1.26k forks source link

RuntimeError: mean(): input dtype should be either floating point or complex dtypes. Got Long instead. #2138

Closed vansinhu closed 1 year ago

vansinhu commented 1 year ago 
(rtmpose) PS D:\users\moons\code\mmpose> python .\tools\train.py .\configs\body_2d_keypoint\rtmpose\coco\rtmpose-m_8xb256-420e_coco-256x192.py                           04/01 11:21:15 - mmengine - INFO - 
------------------------------------------------------------
System environment:
    sys.platform: win32
    Python: 3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]
    CUDA available: True
    numpy_random_seed: 21
    GPU 0: NVIDIA GeForce GTX 1660 Ti
    CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
    NVCC: Cuda compilation tools, release 11.8, V11.8.89
    MSVC: 用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.29.30148 版
    GCC: n/a
    PyTorch: 1.10.1+cu113
    PyTorch compiling details: PyTorch built with:
  - C++ Version: 199711
  - MSVC 192829337
  - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  - OpenMP 2019
  - LAPACK is enabled (usually provided by MKL)
  - CPU capability usage: AVX512
  - CUDA Runtime 11.3
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.2
  - Magma 2.5.4
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=C:/w/b/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -IC:/w/b/windows/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON,

    TorchVision: 0.11.2+cu113
    OpenCV: 4.7.0
    MMEngine: 0.7.0

Runtime environment:
    cudnn_benchmark: False
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: 21
    Distributed launcher: none
    Distributed training: False
    GPU number: 1
------------------------------------------------------------

04/01 11:21:16 - mmengine - INFO - Config:
default_scope = 'mmpose'
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=1),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(
        type='CheckpointHook',
        interval=10,
        save_best='coco/AP',
        rule='greater',
        max_keep_ckpts=1),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='PoseVisualizationHook', enable=False))
custom_hooks = [
    dict(
        type='EMAHook',
        ema_type='ExpMomentumEMA',
        momentum=0.0002,
        update_buffers=True,
        priority=49),
    dict(
        type='mmdet.PipelineSwitchHook',
        switch_epoch=390,
        switch_pipeline=[
            dict(type='LoadImage', backend_args=dict(backend='local')),
            dict(type='GetBBoxCenterScale'),
            dict(type='RandomFlip', direction='horizontal'),
            dict(type='RandomHalfBody'),
            dict(
                type='RandomBBoxTransform',
                shift_factor=0.0,
                scale_factor=[0.75, 1.25],
                rotate_factor=60),
            dict(type='TopdownAffine', input_size=(192, 256)),
            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=dict(
                    type='SimCCLabel',
                    input_size=(192, 256),
                    sigma=(4.9, 5.66),
                    simcc_split_ratio=2.0,
                    normalize=False,
                    use_dark=False)),
            dict(type='PackPoseInputs')
        ])
]
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 = None
resume = False
backend_args = dict(backend='local')
train_cfg = dict(by_epoch=True, max_epochs=420, val_interval=10)
val_cfg = dict()
test_cfg = dict()
max_epochs = 420
stage2_num_epochs = 30
base_lr = 0.004
randomness = dict(seed=21)
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='AdamW', lr=0.004, weight_decay=0.05),
    paramwise_cfg=dict(
        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
param_scheduler = [
    dict(
        type='LinearLR', start_factor=1e-05, by_epoch=False, begin=0,
        end=1000),
    dict(
        type='CosineAnnealingLR',
        eta_min=0.0002,
        begin=210,
        end=420,
        T_max=210,
        by_epoch=True,
        convert_to_iter_based=True)
]
auto_scale_lr = dict(base_batch_size=1024)
codec = dict(
    type='SimCCLabel',
    input_size=(192, 256),
    sigma=(4.9, 5.66),
    simcc_split_ratio=2.0,
    normalize=False,
    use_dark=False)
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/rtmpose/cspnext-m_udp-aic-coco_210e-256x192-f2f7d6f6_20230130.pth'
        )),
    head=dict(
        type='RTMCCHead',
        in_channels=768,
        out_channels=3,
        input_size=(192, 256),
        in_featuremap_size=(6, 8),
        simcc_split_ratio=2.0,
        final_layer_kernel_size=7,
        gau_cfg=dict(
            hidden_dims=256,
            s=128,
            expansion_factor=2,
            dropout_rate=0.0,
            drop_path=0.0,
            act_fn='SiLU',
            use_rel_bias=False,
            pos_enc=False),
        loss=dict(
            type='KLDiscretLoss',
            use_target_weight=True,
            beta=10.0,
            label_softmax=True),
        decoder=dict(
            type='SimCCLabel',
            input_size=(192, 256),
            sigma=(4.9, 5.66),
            simcc_split_ratio=2.0,
            normalize=False,
            use_dark=False)),
    test_cfg=dict(flip_test=True))
dataset_type = 'CocoDataset'
data_mode = 'topdown'
data_root = 'data/coco/'
train_pipeline = [
    dict(type='LoadImage', backend_args=dict(backend='local')),
    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=(192, 256)),
    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=1.0)
        ]),
    dict(
        type='GenerateTarget',
        encoder=dict(
            type='SimCCLabel',
            input_size=(192, 256),
            sigma=(4.9, 5.66),
            simcc_split_ratio=2.0,
            normalize=False,
            use_dark=False)),
    dict(type='PackPoseInputs')
]
val_pipeline = [
    dict(type='LoadImage', backend_args=dict(backend='local')),
    dict(type='GetBBoxCenterScale'),
    dict(type='TopdownAffine', input_size=(192, 256)),
    dict(type='PackPoseInputs')
]
train_pipeline_stage2 = [
    dict(type='LoadImage', backend_args=dict(backend='local')),
    dict(type='GetBBoxCenterScale'),
    dict(type='RandomFlip', direction='horizontal'),
    dict(type='RandomHalfBody'),
    dict(
        type='RandomBBoxTransform',
        shift_factor=0.0,
        scale_factor=[0.75, 1.25],
        rotate_factor=60),
    dict(type='TopdownAffine', input_size=(192, 256)),
    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=dict(
            type='SimCCLabel',
            input_size=(192, 256),
            sigma=(4.9, 5.66),
            simcc_split_ratio=2.0,
            normalize=False,
            use_dark=False)),
    dict(type='PackPoseInputs')
]
train_dataloader = dict(
    batch_size=2,
    num_workers=1,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type='CocoDataset',
        data_root='data/coco/',
        data_mode='topdown',
        ann_file='annotations/person_keypoints_train2017.json',
        data_prefix=dict(img='train2017/'),
        pipeline=[
            dict(type='LoadImage', backend_args=dict(backend='local')),
            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=(192, 256)),
            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=1.0)
                ]),
            dict(
                type='GenerateTarget',
                encoder=dict(
                    type='SimCCLabel',
                    input_size=(192, 256),
                    sigma=(4.9, 5.66),
                    simcc_split_ratio=2.0,
                    normalize=False,
                    use_dark=False)),
            dict(type='PackPoseInputs')
        ]))
val_dataloader = dict(
    batch_size=2,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
    dataset=dict(
        type='CocoDataset',
        data_root='data/coco/',
        data_mode='topdown',
        ann_file='annotations/person_keypoints_val2017.json',
        data_prefix=dict(img='val2017/'),
        test_mode=True,
        pipeline=[
            dict(type='LoadImage', backend_args=dict(backend='local')),
            dict(type='GetBBoxCenterScale'),
            dict(type='TopdownAffine', input_size=(192, 256)),
            dict(type='PackPoseInputs')
        ]))
test_dataloader = dict(
    batch_size=2,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
    dataset=dict(
        type='CocoDataset',
        data_root='data/coco/',
        data_mode='topdown',
        ann_file='annotations/person_keypoints_val2017.json',
        data_prefix=dict(img='val2017/'),
        test_mode=True,
        pipeline=[
            dict(type='LoadImage', backend_args=dict(backend='local')),
            dict(type='GetBBoxCenterScale'),
            dict(type='TopdownAffine', input_size=(192, 256)),
            dict(type='PackPoseInputs')
        ]))
val_evaluator = dict(
    type='CocoMetric',
    ann_file='data/coco/annotations/person_keypoints_val2017.json')
test_evaluator = dict(
    type='CocoMetric',
    ann_file='data/coco/annotations/person_keypoints_val2017.json')
launcher = 'none'
work_dir = './work_dirs\\rtmpose-m_8xb256-420e_coco-256x192'

04/01 11:21:18 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used.
04/01 11:21:18 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook
(49          ) EMAHook
(BELOW_NORMAL) LoggerHook
 --------------------
after_load_checkpoint:
(49          ) EMAHook
 --------------------
before_train:
(VERY_HIGH   ) RuntimeInfoHook
(49          ) EMAHook
(NORMAL      ) IterTimerHook
(VERY_LOW    ) CheckpointHook
 --------------------
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook
(NORMAL      ) IterTimerHook
(NORMAL      ) DistSamplerSeedHook
(NORMAL      ) PipelineSwitchHook
 --------------------
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook
(NORMAL      ) IterTimerHook
 --------------------
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook
(49          ) EMAHook
(NORMAL      ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW         ) ParamSchedulerHook
(VERY_LOW    ) CheckpointHook
 --------------------
after_train_epoch:
(NORMAL      ) IterTimerHook
(LOW         ) ParamSchedulerHook
(VERY_LOW    ) CheckpointHook
 --------------------
before_val_epoch:
(49          ) EMAHook
(NORMAL      ) IterTimerHook
 --------------------
before_val_iter:
(NORMAL      ) IterTimerHook
 --------------------
after_val_iter:
(NORMAL      ) IterTimerHook
(NORMAL      ) PoseVisualizationHook
(BELOW_NORMAL) LoggerHook
 --------------------
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook
(49          ) EMAHook
(NORMAL      ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW         ) ParamSchedulerHook
(VERY_LOW    ) CheckpointHook
 --------------------
before_save_checkpoint:
(49          ) EMAHook
 --------------------
before_test_epoch:
(49          ) EMAHook
(NORMAL      ) IterTimerHook
 --------------------
before_test_iter:
(NORMAL      ) IterTimerHook
 --------------------
after_test_iter:
(NORMAL      ) IterTimerHook
(NORMAL      ) PoseVisualizationHook
(BELOW_NORMAL) LoggerHook
 --------------------
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook
(49          ) EMAHook
(NORMAL      ) IterTimerHook
(BELOW_NORMAL) LoggerHook
 --------------------
after_run:
(BELOW_NORMAL) LoggerHook
 --------------------
d:\users\moons\code\mmpose\mmpose\datasets\transforms\common_transforms.py:648: UserWarning: Blur is not pixel-level transformations. Please use with caution.
  warnings.warn(
d:\users\moons\code\mmpose\mmpose\datasets\transforms\common_transforms.py:648: UserWarning: MedianBlur is not pixel-level transformations. Please use with caution.     
  warnings.warn(
d:\users\moons\code\mmpose\mmpose\datasets\transforms\common_transforms.py:648: UserWarning: CoarseDropout is not pixel-level transformations. Please use with caution.  
  warnings.warn(
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stem.0.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stem.0.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stem.1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stem.1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stem.2.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stem.2.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.0.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.0.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.main_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.main_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.short_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.short_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.final_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.final_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.1.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.1.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.1.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.1.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.1.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.1.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage1.1.attention.fc.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.0.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.0.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.main_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.main_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.short_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.short_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.final_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.final_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.3.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.3.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.3.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.3.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.3.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.3.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage2.1.attention.fc.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.0.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.0.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.main_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.main_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.short_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.short_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.final_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.final_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.3.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.3.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.3.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.3.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.3.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.3.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage3.1.attention.fc.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.0.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.0.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv2.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv2.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.main_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.main_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.short_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.short_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.final_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.final_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.1.conv1.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.1.conv1.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.1.conv2.depthwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.1.conv2.depthwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.1.conv2.pointwise_conv.bn.weight:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.1.conv2.pointwise_conv.bn.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- backbone.stage4.2.attention.fc.bias:weight_decay=0.0
04/01 11:21:19 - mmengine - INFO - paramwise_options -- head.final_layer.bias:weight_decay=0.0
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
04/01 11:21:21 - mmengine - INFO - load backbone. in model from: https://download.openmmlab.com/mmpose/v1/projects/rtmpose/cspnext-m_udp-aic-coco_210e-256x192-f2f7d6f6_20230130.pth
Loads checkpoint by http backend from path: https://download.openmmlab.com/mmpose/v1/projects/rtmpose/cspnext-m_udp-aic-coco_210e-256x192-f2f7d6f6_20230130.pth
04/01 11:21:21 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io
04/01 11:21:21 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future.
04/01 11:21:21 - mmengine - INFO - Checkpoints will be saved to D:\users\moons\code\mmpose\work_dirs\rtmpose-m_8xb256-420e_coco-256x192.
04/01 11:21:29 - mmengine - INFO - Epoch(train)   [1][1/8]  lr: 4.000000e-08  eta: 7:32:47  time: 8.088079  data_time: 4.277570  memory: 270  loss: 0.024505  loss_kpt: 0.024505  acc_pose: 0.000000
04/01 11:21:29 - mmengine - INFO - Epoch(train)   [1][2/8]  lr: 4.043964e-06  eta: 3:50:19  time: 4.115466  data_time: 2.140288  memory: 398  loss: 0.025944  loss_kpt: 0.025944  acc_pose: 0.000000
04/01 11:21:29 - mmengine - INFO - Epoch(train)   [1][3/8]  lr: 8.047928e-06  eta: 2:36:20  time: 2.794299  data_time: 1.430200  memory: 398  loss: 0.021399  loss_kpt: 0.021399  acc_pose: 0.000000
04/01 11:21:30 - mmengine - INFO - Epoch(train)   [1][4/8]  lr: 1.205189e-05  eta: 2:02:49  time: 2.195940  data_time: 1.138269  memory: 398  loss: 0.024361  loss_kpt: 0.024361  acc_pose: 0.000000
04/01 11:21:30 - mmengine - INFO - Epoch(train)   [1][5/8]  lr: 1.605586e-05  eta: 1:44:01  time: 1.860268  data_time: 0.989604  memory: 398  loss: 0.026822  loss_kpt: 0.026822  acc_pose: 0.000000
04/01 11:21:31 - mmengine - INFO - Epoch(train)   [1][6/8]  lr: 2.005982e-05  eta: 1:30:36  time: 1.620916  data_time: 0.871647  memory: 398  loss: 0.028440  loss_kpt: 0.028440  acc_pose: 0.000000
04/01 11:21:31 - mmengine - INFO - Epoch(train)   [1][7/8]  lr: 2.406378e-05  eta: 1:22:23  time: 1.474214  data_time: 0.808338  memory: 398  loss: 0.026134  loss_kpt: 0.026134  acc_pose: 0.000000
04/01 11:21:32 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:32 - mmengine - INFO - Epoch(train)   [1][8/8]  lr: 2.806775e-05  eta: 1:14:41  time: 1.337105  data_time: 0.741837  memory: 398  loss: 0.027483  loss_kpt: 0.027483  acc_pose: 0.000000
04/01 11:21:32 - mmengine - INFO - Epoch(train)   [2][1/8]  lr: 3.207171e-05  eta: 1:08:48  time: 1.232025  data_time: 0.691350  memory: 398  loss: 0.026463  loss_kpt: 0.026463  acc_pose: 0.000000
04/01 11:21:33 - mmengine - INFO - Epoch(train)   [2][2/8]  lr: 3.607568e-05  eta: 1:03:43  time: 1.141268  data_time: 0.643960  memory: 398  loss: 0.027143  loss_kpt: 0.027143  acc_pose: 0.000000
04/01 11:21:33 - mmengine - INFO - Epoch(train)   [2][3/8]  lr: 4.007964e-05  eta: 0:59:32  time: 1.066848  data_time: 0.605491  memory: 398  loss: 0.026889  loss_kpt: 0.026889  acc_pose: 0.000000
04/01 11:21:34 - mmengine - INFO - Epoch(train)   [2][4/8]  lr: 4.408360e-05  eta: 0:57:16  time: 1.026356  data_time: 0.587635  memory: 398  loss: 0.027696  loss_kpt: 0.027696  acc_pose: 0.000000
04/01 11:21:34 - mmengine - INFO - Epoch(train)   [2][5/8]  lr: 4.808757e-05  eta: 0:54:24  time: 0.975412  data_time: 0.561466  memory: 398  loss: 0.026968  loss_kpt: 0.026968  acc_pose: 0.000000
04/01 11:21:34 - mmengine - INFO - Epoch(train)   [2][6/8]  lr: 5.209153e-05  eta: 0:52:19  time: 0.938139  data_time: 0.546007  memory: 398  loss: 0.027668  loss_kpt: 0.027668  acc_pose: 0.000000
04/01 11:21:35 - mmengine - INFO - Epoch(train)   [2][7/8]  lr: 5.609550e-05  eta: 0:50:27  time: 0.904987  data_time: 0.530379  memory: 398  loss: 0.028256  loss_kpt: 0.028256  acc_pose: 0.000000
04/01 11:21:35 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:35 - mmengine - INFO - Epoch(train)   [2][8/8]  lr: 6.009946e-05  eta: 0:48:40  time: 0.873400  data_time: 0.515847  memory: 398  loss: 0.028772  loss_kpt: 0.028772  acc_pose: 0.000000
04/01 11:21:36 - mmengine - INFO - Epoch(train)   [3][1/8]  lr: 6.410342e-05  eta: 0:47:37  time: 0.854903  data_time: 0.507841  memory: 398  loss: 0.029236  loss_kpt: 0.029236  acc_pose: 0.000000
04/01 11:21:36 - mmengine - INFO - Epoch(train)   [3][2/8]  lr: 6.810739e-05  eta: 0:46:04  time: 0.827127  data_time: 0.493089  memory: 398  loss: 0.028813  loss_kpt: 0.028813  acc_pose: 0.000000
04/01 11:21:36 - mmengine - INFO - Epoch(train)   [3][3/8]  lr: 7.211135e-05  eta: 0:44:30  time: 0.799389  data_time: 0.477512  memory: 398  loss: 0.029249  loss_kpt: 0.029249  acc_pose: 0.000000
04/01 11:21:37 - mmengine - INFO - Epoch(train)   [3][4/8]  lr: 7.611532e-05  eta: 0:43:37  time: 0.783720  data_time: 0.472799  memory: 398  loss: 0.029612  loss_kpt: 0.029612  acc_pose: 0.166667
04/01 11:21:37 - mmengine - INFO - Epoch(train)   [3][5/8]  lr: 8.011928e-05  eta: 0:42:38  time: 0.766137  data_time: 0.464628  memory: 398  loss: 0.029579  loss_kpt: 0.029579  acc_pose: 0.000000
04/01 11:21:38 - mmengine - INFO - Epoch(train)   [3][6/8]  lr: 8.412324e-05  eta: 0:41:30  time: 0.746004  data_time: 0.453164  memory: 398  loss: 0.029906  loss_kpt: 0.029906  acc_pose: 0.000000
04/01 11:21:38 - mmengine - INFO - Epoch(train)   [3][7/8]  lr: 8.812721e-05  eta: 0:41:01  time: 0.737653  data_time: 0.450395  memory: 398  loss: 0.029549  loss_kpt: 0.029549  acc_pose: 0.000000
04/01 11:21:39 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:39 - mmengine - INFO - Epoch(train)   [3][8/8]  lr: 9.213117e-05  eta: 0:40:04  time: 0.720851  data_time: 0.441606  memory: 398  loss: 0.028916  loss_kpt: 0.028916  acc_pose: 0.000000
04/01 11:21:39 - mmengine - INFO - Epoch(train)   [4][1/8]  lr: 9.613514e-05  eta: 0:39:29  time: 0.710345  data_time: 0.438231  memory: 398  loss: 0.029163  loss_kpt: 0.029163  acc_pose: 0.000000
04/01 11:21:39 - mmengine - INFO - Epoch(train)   [4][2/8]  lr: 1.001391e-04  eta: 0:38:40  time: 0.695891  data_time: 0.430200  memory: 398  loss: 0.028752  loss_kpt: 0.028752  acc_pose: 0.000000
04/01 11:21:40 - mmengine - INFO - Epoch(train)   [4][3/8]  lr: 1.041431e-04  eta: 0:37:59  time: 0.684035  data_time: 0.424055  memory: 398  loss: 0.028313  loss_kpt: 0.028313  acc_pose: 0.000000
04/01 11:21:40 - mmengine - INFO - Epoch(train)   [4][4/8]  lr: 1.081470e-04  eta: 0:37:28  time: 0.674786  data_time: 0.417787  memory: 398  loss: 0.028611  loss_kpt: 0.028611  acc_pose: 0.000000
04/01 11:21:41 - mmengine - INFO - Epoch(train)   [4][5/8]  lr: 1.121510e-04  eta: 0:36:59  time: 0.666224  data_time: 0.414641  memory: 398  loss: 0.028885  loss_kpt: 0.028885  acc_pose: 0.000000
04/01 11:21:41 - mmengine - INFO - Epoch(train)   [4][6/8]  lr: 1.161550e-04  eta: 0:36:39  time: 0.660500  data_time: 0.413408  memory: 398  loss: 0.029140  loss_kpt: 0.029140  acc_pose: 0.166667
04/01 11:21:41 - mmengine - INFO - Epoch(train)   [4][7/8]  lr: 1.201589e-04  eta: 0:36:03  time: 0.649835  data_time: 0.407256  memory: 398  loss: 0.028725  loss_kpt: 0.028725  acc_pose: 0.000000
04/01 11:21:42 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:42 - mmengine - INFO - Epoch(train)   [4][8/8]  lr: 1.241629e-04  eta: 0:35:38  time: 0.642690  data_time: 0.404222  memory: 398  loss: 0.028581  loss_kpt: 0.028581  acc_pose: 0.000000
04/01 11:21:42 - mmengine - INFO - Epoch(train)   [5][1/8]  lr: 1.281668e-04  eta: 0:35:26  time: 0.639129  data_time: 0.404589  memory: 398  loss: 0.028826  loss_kpt: 0.028826  acc_pose: 0.000000
04/01 11:21:43 - mmengine - INFO - Epoch(train)   [5][2/8]  lr: 1.321708e-04  eta: 0:35:03  time: 0.632387  data_time: 0.401501  memory: 398  loss: 0.029049  loss_kpt: 0.029049  acc_pose: 0.000000
04/01 11:21:43 - mmengine - INFO - Epoch(train)   [5][3/8]  lr: 1.361748e-04  eta: 0:34:34  time: 0.623928  data_time: 0.396608  memory: 398  loss: 0.028842  loss_kpt: 0.028842  acc_pose: 0.000000
04/01 11:21:44 - mmengine - INFO - Epoch(train)   [5][4/8]  lr: 1.401787e-04  eta: 0:34:19  time: 0.619514  data_time: 0.395321  memory: 398  loss: 0.028994  loss_kpt: 0.028994  acc_pose: 0.000000
04/01 11:21:44 - mmengine - INFO - Epoch(train)   [5][5/8]  lr: 1.441827e-04  eta: 0:33:57  time: 0.613070  data_time: 0.391490  memory: 398  loss: 0.028872  loss_kpt: 0.028872  acc_pose: 0.000000
04/01 11:21:44 - mmengine - INFO - Epoch(train)   [5][6/8]  lr: 1.481867e-04  eta: 0:33:31  time: 0.605512  data_time: 0.386910  memory: 398  loss: 0.028679  loss_kpt: 0.028679  acc_pose: 0.000000
04/01 11:21:45 - mmengine - INFO - Epoch(train)   [5][7/8]  lr: 1.521906e-04  eta: 0:33:15  time: 0.600858  data_time: 0.384955  memory: 398  loss: 0.028884  loss_kpt: 0.028884  acc_pose: 0.000000
04/01 11:21:45 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:45 - mmengine - INFO - Epoch(train)   [5][8/8]  lr: 1.561946e-04  eta: 0:32:55  time: 0.595050  data_time: 0.381607  memory: 398  loss: 0.029061  loss_kpt: 0.029061  acc_pose: 0.000000
04/01 11:21:46 - mmengine - INFO - Epoch(train)   [6][1/8]  lr: 1.601986e-04  eta: 0:32:48  time: 0.592987  data_time: 0.380331  memory: 398  loss: 0.029088  loss_kpt: 0.029088  acc_pose: 0.000000
04/01 11:21:46 - mmengine - INFO - Epoch(train)   [6][2/8]  lr: 1.642025e-04  eta: 0:32:22  time: 0.585379  data_time: 0.375157  memory: 398  loss: 0.028816  loss_kpt: 0.028816  acc_pose: 0.000000
04/01 11:21:46 - mmengine - INFO - Epoch(train)   [6][3/8]  lr: 1.682065e-04  eta: 0:32:05  time: 0.580377  data_time: 0.372277  memory: 398  loss: 0.028998  loss_kpt: 0.028998  acc_pose: 0.000000
04/01 11:21:47 - mmengine - INFO - Epoch(train)   [6][4/8]  lr: 1.722105e-04  eta: 0:31:56  time: 0.577833  data_time: 0.371999  memory: 398  loss: 0.029180  loss_kpt: 0.029180  acc_pose: 0.000000
04/01 11:21:47 - mmengine - INFO - Epoch(train)   [6][5/8]  lr: 1.762144e-04  eta: 0:31:52  time: 0.576891  data_time: 0.373013  memory: 398  loss: 0.029228  loss_kpt: 0.029228  acc_pose: 0.000000
04/01 11:21:48 - mmengine - INFO - Epoch(train)   [6][6/8]  lr: 1.802184e-04  eta: 0:31:41  time: 0.573878  data_time: 0.371927  memory: 398  loss: 0.029386  loss_kpt: 0.029386  acc_pose: 0.166667
04/01 11:21:48 - mmengine - INFO - Epoch(train)   [6][7/8]  lr: 1.842223e-04  eta: 0:31:29  time: 0.570354  data_time: 0.369545  memory: 398  loss: 0.029284  loss_kpt: 0.029284  acc_pose: 0.000000
04/01 11:21:49 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:49 - mmengine - INFO - Epoch(train)   [6][8/8]  lr: 1.882263e-04  eta: 0:31:23  time: 0.568750  data_time: 0.368452  memory: 398  loss: 0.029167  loss_kpt: 0.029167  acc_pose: 0.000000
04/01 11:21:49 - mmengine - INFO - Epoch(train)   [7][1/8]  lr: 1.922303e-04  eta: 0:31:15  time: 0.566492  data_time: 0.368127  memory: 398  loss: 0.028925  loss_kpt: 0.028925  acc_pose: 0.000000
04/01 11:21:49 - mmengine - INFO - Epoch(train)   [7][2/8]  lr: 1.962342e-04  eta: 0:30:59  time: 0.561814  data_time: 0.365066  memory: 398  loss: 0.028866  loss_kpt: 0.028866  acc_pose: 0.000000
04/01 11:21:50 - mmengine - INFO - Epoch(train)   [7][3/8]  lr: 2.002382e-04  eta: 0:30:57  time: 0.410769  data_time: 0.287585  memory: 398  loss: 0.028865  loss_kpt: 0.028865  acc_pose: 0.000000
04/01 11:21:50 - mmengine - INFO - Epoch(train)   [7][4/8]  lr: 2.042422e-04  eta: 0:30:44  time: 0.415288  data_time: 0.292818  memory: 398  loss: 0.028894  loss_kpt: 0.028894  acc_pose: 0.000000
04/01 11:21:51 - mmengine - INFO - Epoch(train)   [7][5/8]  lr: 2.082461e-04  eta: 0:30:39  time: 0.421907  data_time: 0.298709  memory: 398  loss: 0.029380  loss_kpt: 0.029380  acc_pose: 0.000000
04/01 11:21:51 - mmengine - INFO - Epoch(train)   [7][6/8]  lr: 2.122501e-04  eta: 0:30:28  time: 0.421749  data_time: 0.298743  memory: 398  loss: 0.029185  loss_kpt: 0.029185  acc_pose: 0.000000
04/01 11:21:52 - mmengine - INFO - Epoch(train)   [7][7/8]  lr: 2.162541e-04  eta: 0:30:15  time: 0.418390  data_time: 0.295502  memory: 398  loss: 0.028789  loss_kpt: 0.028789  acc_pose: 0.000000
04/01 11:21:52 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:52 - mmengine - INFO - Epoch(train)   [7][8/8]  lr: 2.202580e-04  eta: 0:30:11  time: 0.419457  data_time: 0.297270  memory: 398  loss: 0.028552  loss_kpt: 0.028552  acc_pose: 0.000000
04/01 11:21:53 - mmengine - INFO - Epoch(train)   [8][1/8]  lr: 2.242620e-04  eta: 0:30:07  time: 0.417338  data_time: 0.296340  memory: 398  loss: 0.028775  loss_kpt: 0.028775  acc_pose: 0.000000
04/01 11:21:53 - mmengine - INFO - Epoch(train)   [8][2/8]  lr: 2.282659e-04  eta: 0:30:02  time: 0.419137  data_time: 0.296592  memory: 398  loss: 0.028671  loss_kpt: 0.028671  acc_pose: 0.000000
04/01 11:21:53 - mmengine - INFO - Epoch(train)   [8][3/8]  lr: 2.322699e-04  eta: 0:29:54  time: 0.419788  data_time: 0.297194  memory: 398  loss: 0.028718  loss_kpt: 0.028718  acc_pose: 0.000000
04/01 11:21:54 - mmengine - INFO - Epoch(train)   [8][4/8]  lr: 2.362739e-04  eta: 0:29:43  time: 0.420395  data_time: 0.297513  memory: 398  loss: 0.028173  loss_kpt: 0.028173  acc_pose: 0.000000
04/01 11:21:54 - mmengine - INFO - Epoch(train)   [8][5/8]  lr: 2.402778e-04  eta: 0:29:32  time: 0.420713  data_time: 0.297257  memory: 398  loss: 0.028403  loss_kpt: 0.028403  acc_pose: 0.000000
04/01 11:21:55 - mmengine - INFO - Epoch(train)   [8][6/8]  lr: 2.442818e-04  eta: 0:29:30  time: 0.419490  data_time: 0.297064  memory: 398  loss: 0.028414  loss_kpt: 0.028414  acc_pose: 0.000000
04/01 11:21:55 - mmengine - INFO - Epoch(train)   [8][7/8]  lr: 2.482858e-04  eta: 0:29:28  time: 0.422422  data_time: 0.299549  memory: 398  loss: 0.028509  loss_kpt: 0.028509  acc_pose: 0.000000
04/01 11:21:56 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:56 - mmengine - INFO - Epoch(train)   [8][8/8]  lr: 2.522897e-04  eta: 0:29:29  time: 0.424639  data_time: 0.300102  memory: 398  loss: 0.028503  loss_kpt: 0.028503  acc_pose: 0.000000
04/01 11:21:56 - mmengine - INFO - Epoch(train)   [9][1/8]  lr: 2.562937e-04  eta: 0:29:24  time: 0.424677  data_time: 0.300180  memory: 398  loss: 0.028487  loss_kpt: 0.028487  acc_pose: 0.000000
04/01 11:21:57 - mmengine - INFO - Epoch(train)   [9][2/8]  lr: 2.602977e-04  eta: 0:29:21  time: 0.426413  data_time: 0.301676  memory: 398  loss: 0.028433  loss_kpt: 0.028433  acc_pose: 0.000000
04/01 11:21:57 - mmengine - INFO - Epoch(train)   [9][3/8]  lr: 2.643016e-04  eta: 0:29:13  time: 0.422853  data_time: 0.299660  memory: 398  loss: 0.027892  loss_kpt: 0.027892  acc_pose: 0.000000
04/01 11:21:57 - mmengine - INFO - Epoch(train)   [9][4/8]  lr: 2.683056e-04  eta: 0:29:08  time: 0.424459  data_time: 0.301336  memory: 398  loss: 0.028084  loss_kpt: 0.028084  acc_pose: 0.000000
04/01 11:21:58 - mmengine - INFO - Epoch(train)   [9][5/8]  lr: 2.723095e-04  eta: 0:29:04  time: 0.427833  data_time: 0.304381  memory: 398  loss: 0.028072  loss_kpt: 0.028072  acc_pose: 0.000000
04/01 11:21:58 - mmengine - INFO - Epoch(train)   [9][6/8]  lr: 2.763135e-04  eta: 0:28:56  time: 0.425547  data_time: 0.301326  memory: 398  loss: 0.027946  loss_kpt: 0.027946  acc_pose: 0.000000
04/01 11:21:59 - mmengine - INFO - Epoch(train)   [9][7/8]  lr: 2.803175e-04  eta: 0:28:50  time: 0.425308  data_time: 0.301233  memory: 398  loss: 0.028099  loss_kpt: 0.028099  acc_pose: 0.000000
04/01 11:21:59 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:21:59 - mmengine - INFO - Epoch(train)   [9][8/8]  lr: 2.843214e-04  eta: 0:28:41  time: 0.425595  data_time: 0.301666  memory: 398  loss: 0.028076  loss_kpt: 0.028076  acc_pose: 0.000000
04/01 11:22:00 - mmengine - INFO - Epoch(train)  [10][1/8]  lr: 2.883254e-04  eta: 0:28:37  time: 0.423404  data_time: 0.300434  memory: 398  loss: 0.028256  loss_kpt: 0.028256  acc_pose: 0.000000
04/01 11:22:00 - mmengine - INFO - Epoch(train)  [10][2/8]  lr: 2.923294e-04  eta: 0:28:32  time: 0.425518  data_time: 0.301761  memory: 398  loss: 0.028681  loss_kpt: 0.028681  acc_pose: 0.000000
04/01 11:22:00 - mmengine - INFO - Epoch(train)  [10][3/8]  lr: 2.963333e-04  eta: 0:28:31  time: 0.426297  data_time: 0.300867  memory: 398  loss: 0.028329  loss_kpt: 0.028329  acc_pose: 0.333333
04/01 11:22:01 - mmengine - INFO - Epoch(train)  [10][4/8]  lr: 3.003373e-04  eta: 0:28:24  time: 0.427169  data_time: 0.301572  memory: 398  loss: 0.028693  loss_kpt: 0.028693  acc_pose: 0.000000
04/01 11:22:01 - mmengine - INFO - Epoch(train)  [10][5/8]  lr: 3.043413e-04  eta: 0:28:15  time: 0.426023  data_time: 0.300416  memory: 398  loss: 0.029088  loss_kpt: 0.029088  acc_pose: 0.000000
04/01 11:22:02 - mmengine - INFO - Epoch(train)  [10][6/8]  lr: 3.083452e-04  eta: 0:28:12  time: 0.426831  data_time: 0.302222  memory: 398  loss: 0.028838  loss_kpt: 0.028838  acc_pose: 0.000000
04/01 11:22:02 - mmengine - INFO - Epoch(train)  [10][7/8]  lr: 3.123492e-04  eta: 0:28:07  time: 0.426414  data_time: 0.301687  memory: 398  loss: 0.028840  loss_kpt: 0.028840  acc_pose: 0.000000
04/01 11:22:02 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:02 - mmengine - INFO - Epoch(train)  [10][8/8]  lr: 3.163532e-04  eta: 0:27:59  time: 0.422809  data_time: 0.298465  memory: 398  loss: 0.028468  loss_kpt: 0.028468  acc_pose: 0.000000
04/01 11:22:02 - mmengine - INFO - Saving checkpoint at 10 epochs
04/01 11:22:08 - mmengine - INFO - Epoch(val)  [10][1/1]    eta: 0:00:00  time: 3.785827  data_time: 3.624997  memory: 280  
04/01 11:22:08 - mmengine - INFO - Evaluating CocoMetric...
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *keypoints*
DONE (t=0.00s).
Accumulating evaluation results...
DONE (t=0.00s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets= 20 ] =  0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets= 20 ] =  0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets= 20 ] =  0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] =  0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 20 ] =  0.000
 Average Recall     (AR) @[ IoU=0.50      | area=   all | maxDets= 20 ] =  0.000
 Average Recall     (AR) @[ IoU=0.75      | area=   all | maxDets= 20 ] =  0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] =  0.000
04/01 11:22:08 - mmengine - INFO - Epoch(val) [10][1/1]  coco/AP: 0.000000  coco/AP .5: 0.000000  coco/AP .75: 0.000000  coco/AP (M): -1.000000  coco/AP (L): 0.000000  coco/AR: 0.000000  coco/AR .5: 0.000000  coco/AR .75: 0.000000  coco/AR (M): -1.000000  coco/AR (L): 0.000000data_time: 3.624997  time: 3.785827    
04/01 11:22:10 - mmengine - INFO - The best checkpoint with 0.0000 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth.
04/01 11:22:11 - mmengine - INFO - Epoch(train)  [11][1/8]  lr: 3.203571e-04  eta: 0:27:58  time: 0.426340  data_time: 0.299827  memory: 398  loss: 0.028834  loss_kpt: 0.028834  acc_pose: 0.000000
04/01 11:22:11 - mmengine - INFO - Epoch(train)  [11][2/8]  lr: 3.243611e-04  eta: 0:27:49  time: 0.423939  data_time: 0.297466  memory: 398  loss: 0.029084  loss_kpt: 0.029084  acc_pose: 0.166667
04/01 11:22:11 - mmengine - INFO - Epoch(train)  [11][3/8]  lr: 3.283650e-04  eta: 0:27:42  time: 0.420114  data_time: 0.293626  memory: 398  loss: 0.028687  loss_kpt: 0.028687  acc_pose: 0.000000
04/01 11:22:12 - mmengine - INFO - Epoch(train)  [11][4/8]  lr: 3.323690e-04  eta: 0:27:38  time: 0.420303  data_time: 0.293816  memory: 398  loss: 0.028548  loss_kpt: 0.028548  acc_pose: 0.166667
04/01 11:22:12 - mmengine - INFO - Epoch(train)  [11][5/8]  lr: 3.363730e-04  eta: 0:27:37  time: 0.423662  data_time: 0.297162  memory: 398  loss: 0.028793  loss_kpt: 0.028793  acc_pose: 0.000000
04/01 11:22:13 - mmengine - INFO - Epoch(train)  [11][6/8]  lr: 3.403769e-04  eta: 0:27:29  time: 0.420693  data_time: 0.294438  memory: 398  loss: 0.028880  loss_kpt: 0.028880  acc_pose: 0.000000
04/01 11:22:13 - mmengine - INFO - Epoch(train)  [11][7/8]  lr: 3.443809e-04  eta: 0:27:26  time: 0.421895  data_time: 0.295447  memory: 398  loss: 0.029084  loss_kpt: 0.029084  acc_pose: 0.000000
04/01 11:22:14 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:14 - mmengine - INFO - Epoch(train)  [11][8/8]  lr: 3.483849e-04  eta: 0:27:24  time: 0.424600  data_time: 0.298210  memory: 398  loss: 0.029381  loss_kpt: 0.029381  acc_pose: 0.000000
04/01 11:22:14 - mmengine - INFO - Epoch(train)  [12][1/8]  lr: 3.523888e-04  eta: 0:27:21  time: 0.424687  data_time: 0.298253  memory: 398  loss: 0.029398  loss_kpt: 0.029398  acc_pose: 0.000000
04/01 11:22:14 - mmengine - INFO - Epoch(train)  [12][2/8]  lr: 3.563928e-04  eta: 0:27:20  time: 0.427210  data_time: 0.300939  memory: 398  loss: 0.029404  loss_kpt: 0.029404  acc_pose: 0.000000
04/01 11:22:15 - mmengine - INFO - Epoch(train)  [12][3/8]  lr: 3.603968e-04  eta: 0:27:15  time: 0.424302  data_time: 0.299513  memory: 398  loss: 0.029534  loss_kpt: 0.029534  acc_pose: 0.000000
04/01 11:22:15 - mmengine - INFO - Epoch(train)  [12][4/8]  lr: 3.644007e-04  eta: 0:27:16  time: 0.429669  data_time: 0.303356  memory: 398  loss: 0.029860  loss_kpt: 0.029860  acc_pose: 0.166667
04/01 11:22:16 - mmengine - INFO - Epoch(train)  [12][5/8]  lr: 3.684047e-04  eta: 0:27:09  time: 0.428431  data_time: 0.302176  memory: 398  loss: 0.029855  loss_kpt: 0.029855  acc_pose: 0.000000
04/01 11:22:16 - mmengine - INFO - Epoch(train)  [12][6/8]  lr: 3.724086e-04  eta: 0:27:08  time: 0.429137  data_time: 0.302741  memory: 398  loss: 0.029829  loss_kpt: 0.029829  acc_pose: 0.000000
04/01 11:22:17 - mmengine - INFO - Epoch(train)  [12][7/8]  lr: 3.764126e-04  eta: 0:27:05  time: 0.426477  data_time: 0.300385  memory: 398  loss: 0.029958  loss_kpt: 0.029958  acc_pose: 0.000000
04/01 11:22:17 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:17 - mmengine - INFO - Epoch(train)  [12][8/8]  lr: 3.804166e-04  eta: 0:27:01  time: 0.425758  data_time: 0.300041  memory: 398  loss: 0.029834  loss_kpt: 0.029834  acc_pose: 0.000000
04/01 11:22:18 - mmengine - INFO - Epoch(train)  [13][1/8]  lr: 3.844205e-04  eta: 0:27:02  time: 0.428491  data_time: 0.302089  memory: 398  loss: 0.029718  loss_kpt: 0.029718  acc_pose: 0.000000
04/01 11:22:18 - mmengine - INFO - Epoch(train)  [13][2/8]  lr: 3.884245e-04  eta: 0:26:57  time: 0.425814  data_time: 0.300633  memory: 398  loss: 0.029965  loss_kpt: 0.029965  acc_pose: 0.000000
04/01 11:22:18 - mmengine - INFO - Epoch(train)  [13][3/8]  lr: 3.924285e-04  eta: 0:26:54  time: 0.424995  data_time: 0.299733  memory: 398  loss: 0.029975  loss_kpt: 0.029975  acc_pose: 0.000000
04/01 11:22:19 - mmengine - INFO - Epoch(train)  [13][4/8]  lr: 3.964324e-04  eta: 0:26:47  time: 0.424450  data_time: 0.299363  memory: 398  loss: 0.030188  loss_kpt: 0.030188  acc_pose: 0.000000
04/01 11:22:19 - mmengine - INFO - Epoch(train)  [13][5/8]  lr: 4.004364e-04  eta: 0:26:43  time: 0.421449  data_time: 0.296817  memory: 398  loss: 0.030414  loss_kpt: 0.030414  acc_pose: 0.000000
04/01 11:22:19 - mmengine - INFO - Epoch(train)  [13][6/8]  lr: 4.044404e-04  eta: 0:26:38  time: 0.420891  data_time: 0.295996  memory: 398  loss: 0.030554  loss_kpt: 0.030554  acc_pose: 0.000000
04/01 11:22:20 - mmengine - INFO - Epoch(train)  [13][7/8]  lr: 4.084443e-04  eta: 0:26:32  time: 0.417639  data_time: 0.293989  memory: 398  loss: 0.030436  loss_kpt: 0.030436  acc_pose: 0.000000
04/01 11:22:20 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:20 - mmengine - INFO - Epoch(train)  [13][8/8]  lr: 4.124483e-04  eta: 0:26:31  time: 0.418959  data_time: 0.295623  memory: 398  loss: 0.030656  loss_kpt: 0.030656  acc_pose: 0.333333
04/01 11:22:21 - mmengine - INFO - Epoch(train)  [14][1/8]  lr: 4.164523e-04  eta: 0:26:28  time: 0.420520  data_time: 0.296239  memory: 398  loss: 0.031010  loss_kpt: 0.031010  acc_pose: 0.000000
04/01 11:22:21 - mmengine - INFO - Epoch(train)  [14][2/8]  lr: 4.204562e-04  eta: 0:26:23  time: 0.417791  data_time: 0.293517  memory: 398  loss: 0.030873  loss_kpt: 0.030873  acc_pose: 0.000000
04/01 11:22:21 - mmengine - INFO - Epoch(train)  [14][3/8]  lr: 4.244602e-04  eta: 0:26:18  time: 0.414965  data_time: 0.290382  memory: 398  loss: 0.031144  loss_kpt: 0.031144  acc_pose: 0.000000
04/01 11:22:22 - mmengine - INFO - Epoch(train)  [14][4/8]  lr: 4.284641e-04  eta: 0:26:14  time: 0.412842  data_time: 0.289691  memory: 398  loss: 0.031221  loss_kpt: 0.031221  acc_pose: 0.000000
04/01 11:22:22 - mmengine - INFO - Epoch(train)  [14][5/8]  lr: 4.324681e-04  eta: 0:26:09  time: 0.411050  data_time: 0.287815  memory: 398  loss: 0.031307  loss_kpt: 0.031307  acc_pose: 0.000000
04/01 11:22:22 - mmengine - INFO - Epoch(train)  [14][6/8]  lr: 4.364721e-04  eta: 0:26:07  time: 0.412121  data_time: 0.289243  memory: 398  loss: 0.031904  loss_kpt: 0.031904  acc_pose: 0.000000
04/01 11:22:23 - mmengine - INFO - Epoch(train)  [14][7/8]  lr: 4.404760e-04  eta: 0:26:04  time: 0.413764  data_time: 0.291423  memory: 398  loss: 0.031844  loss_kpt: 0.031844  acc_pose: 0.000000
04/01 11:22:23 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:23 - mmengine - INFO - Epoch(train)  [14][8/8]  lr: 4.444800e-04  eta: 0:26:00  time: 0.410160  data_time: 0.288341  memory: 398  loss: 0.031877  loss_kpt: 0.031877  acc_pose: 0.000000
04/01 11:22:24 - mmengine - INFO - Epoch(train)  [15][1/8]  lr: 4.484840e-04  eta: 0:26:02  time: 0.411477  data_time: 0.289414  memory: 398  loss: 0.031844  loss_kpt: 0.031844  acc_pose: 0.000000
04/01 11:22:24 - mmengine - INFO - Epoch(train)  [15][2/8]  lr: 4.524879e-04  eta: 0:26:01  time: 0.409793  data_time: 0.289113  memory: 398  loss: 0.031866  loss_kpt: 0.031866  acc_pose: 0.000000
04/01 11:22:24 - mmengine - INFO - Epoch(train)  [15][3/8]  lr: 4.564919e-04  eta: 0:25:56  time: 0.406888  data_time: 0.286667  memory: 398  loss: 0.031880  loss_kpt: 0.031880  acc_pose: 0.000000
04/01 11:22:25 - mmengine - INFO - Epoch(train)  [15][4/8]  lr: 4.604959e-04  eta: 0:25:54  time: 0.405699  data_time: 0.285383  memory: 398  loss: 0.031938  loss_kpt: 0.031938  acc_pose: 0.000000
04/01 11:22:25 - mmengine - INFO - Epoch(train)  [15][5/8]  lr: 4.644998e-04  eta: 0:25:52  time: 0.406668  data_time: 0.286106  memory: 398  loss: 0.032468  loss_kpt: 0.032468  acc_pose: 0.333333
04/01 11:22:26 - mmengine - INFO - Epoch(train)  [15][6/8]  lr: 4.685038e-04  eta: 0:25:50  time: 0.406681  data_time: 0.285953  memory: 398  loss: 0.032201  loss_kpt: 0.032201  acc_pose: 0.000000
04/01 11:22:26 - mmengine - INFO - Epoch(train)  [15][7/8]  lr: 4.725077e-04  eta: 0:25:46  time: 0.403823  data_time: 0.283235  memory: 398  loss: 0.031966  loss_kpt: 0.031966  acc_pose: 0.000000
04/01 11:22:26 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:26 - mmengine - INFO - Epoch(train)  [15][8/8]  lr: 4.765117e-04  eta: 0:25:41  time: 0.403121  data_time: 0.283317  memory: 398  loss: 0.032069  loss_kpt: 0.032069  acc_pose: 0.000000
04/01 11:22:27 - mmengine - INFO - Epoch(train)  [16][1/8]  lr: 4.805157e-04  eta: 0:25:42  time: 0.405375  data_time: 0.285554  memory: 398  loss: 0.031816  loss_kpt: 0.031816  acc_pose: 0.000000
04/01 11:22:27 - mmengine - INFO - Epoch(train)  [16][2/8]  lr: 4.845196e-04  eta: 0:25:42  time: 0.408280  data_time: 0.286778  memory: 398  loss: 0.031470  loss_kpt: 0.031470  acc_pose: 0.000000
04/01 11:22:28 - mmengine - INFO - Epoch(train)  [16][3/8]  lr: 4.885236e-04  eta: 0:25:39  time: 0.407393  data_time: 0.285771  memory: 398  loss: 0.031554  loss_kpt: 0.031554  acc_pose: 0.166667
04/01 11:22:28 - mmengine - INFO - Epoch(train)  [16][4/8]  lr: 4.925276e-04  eta: 0:25:36  time: 0.405765  data_time: 0.284488  memory: 398  loss: 0.031237  loss_kpt: 0.031237  acc_pose: 0.000000
04/01 11:22:29 - mmengine - INFO - Epoch(train)  [16][5/8]  lr: 4.965315e-04  eta: 0:25:34  time: 0.404014  data_time: 0.284042  memory: 398  loss: 0.031253  loss_kpt: 0.031253  acc_pose: 0.000000
04/01 11:22:29 - mmengine - INFO - Epoch(train)  [16][6/8]  lr: 5.005355e-04  eta: 0:25:31  time: 0.404306  data_time: 0.284421  memory: 398  loss: 0.030909  loss_kpt: 0.030909  acc_pose: 0.000000
04/01 11:22:29 - mmengine - INFO - Epoch(train)  [16][7/8]  lr: 5.045395e-04  eta: 0:25:29  time: 0.405969  data_time: 0.286127  memory: 398  loss: 0.030898  loss_kpt: 0.030898  acc_pose: 0.000000
04/01 11:22:30 - mmengine - INFO - Exp name: rtmpose-m_8xb256-420e_coco-256x192_20230401_112112
04/01 11:22:30 - mmengine - INFO - Epoch(train)  [16][8/8]  lr: 5.085434e-04  eta: 0:25:26  time: 0.404716  data_time: 0.285364  memory: 398  loss: 0.030783  loss_kpt: 0.030783  acc_pose: 0.000000
04/01 11:22:30 - mmengine - INFO - Epoch(train)  [17][1/8]  lr: 5.125474e-04  eta: 0:25:29  time: 0.408489  data_time: 0.287623  memory: 398  loss: 0.030766  loss_kpt: 0.030766  acc_pose: 0.000000
04/01 11:22:31 - mmengine - INFO - Epoch(train)  [17][2/8]  lr: 5.165514e-04  eta: 0:25:25  time: 0.409007  data_time: 0.288007  memory: 398  loss: 0.030995  loss_kpt: 0.030995  acc_pose: 0.000000
04/01 11:22:31 - mmengine - INFO - Epoch(train)  [17][3/8]  lr: 5.205553e-04  eta: 0:25:21  time: 0.405462  data_time: 0.286734  memory: 398  loss: 0.030944  loss_kpt: 0.030944  acc_pose: 0.000000
04/01 11:22:31 - mmengine - INFO - Epoch(train)  [17][4/8]  lr: 5.245593e-04  eta: 0:25:19  time: 0.407223  data_time: 0.288462  memory: 398  loss: 0.030560  loss_kpt: 0.030560  acc_pose: 0.000000
04/01 11:22:32 - mmengine - INFO - Epoch(train)  [17][5/8]  lr: 5.285632e-04  eta: 0:25:17  time: 0.409267  data_time: 0.290376  memory: 398  loss: 0.030953  loss_kpt: 0.030792  acc_pose: 0.000000
04/01 11:22:34 - mmengine - INFO - Epoch(train)  [18][3/8]  lr: 5.525870e-04  eta: 0:25:04  time: 0.405283  data_time: 0.285804  memory: 398  loss: 0.030736  loss_kpt: 0.030736  acc_pose: 0.000000
04/01 11:22:35 - mmengine - INFO - Epoch(train)  [18][4/8]  lr: 5.565910e-04  eta: 0:25:03  time: 0.404247  data_time: 0.283191  memory: 398  loss: 0.030743  loss_kpt: 0.030743  acc_pose: 0.000000
Traceback (most recent call last):
  File "D:\users\moons\code\mmpose\tools\train.py", line 160, in <module>    main()
  File "D:\users\moons\code\mmpose\tools\train.py", line 156, in main    runner.train()
  File "C:\Users\moons\.conda\envs\rtmpose\lib\site-packages\mmengine\runner\runner.py", line 1701, in train    model = self.train_loop.run()  # type: ignore
  File "C:\Users\moons\.conda\envs\rtmpose\lib\site-packages\mmengine\runner\loops.py", line 96, in run    self.run_epoch()
  File "C:\Users\moons\.conda\envs\rtmpose\lib\site-packages\mmengine\runner\loops.py", line 112, in run_epoch    self.run_iter(idx, data_batch)
  File "C:\Users\moons\.conda\envs\rtmpose\lib\site-packages\mmengine\runner\loops.py", line 128, in run_iter
    outputs = self.runner.model.train_step(
  File "C:\Users\moons\.conda\envs\rtmpose\lib\site-packages\mmengine\model\base_model\base_model.py", line 115, in train_step
    parsed_losses, log_vars = self.parse_losses(losses)  # type: ignore
  File "C:\Users\moons\.conda\envs\rtmpose\lib\site-packages\mmengine\model\base_model\base_model.py", line 165, in parse_losses
    log_vars.append([loss_name, loss_value.mean()])
RuntimeError: mean(): input dtype should be either floating point or complex dtypes. Got Long instead.

Environment

(rtmpose) PS D:\users\moons\code\mmpose> python .\mmpose\utils\collect_env.py
  - C++ Version: 199711
  - MSVC 192829337
  - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  - OpenMP 2019
  - LAPACK is enabled (usually provided by MKL)
  - CPU capability usage: AVX512
  - CUDA Runtime 11.3
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.2
  - Magma 2.5.4
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=C:/w/b/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -IC:/w/b/windows/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON,

TorchVision: 0.11.2+cu113OpenCV: 4.7.0MMEngine: 0.7.0
MMPose: 1.0.0rc1+896e9d5
vansinhu commented 1 year ago

https://github.com/vansinhu/mmpose/tree/triangle/projects/triangle

reproduct

Tau-J commented 1 year ago

Solved with more training data.