[Bug] KeyError: 'YOLODetector is not in the mmpose::model registry.

[yuyingliu-1]

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• The bug has not been fixed in the latest version(https://github.com/open-mmlab/mmpose).

Environment

OrderedDict([('sys.platform', 'linux'), ('Python', '3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0]'), ('CUDA available', True), ('MUSA available', False), ('numpy_random_seed', 2147483648), ('GPU 0', 'NVIDIA GeForce RTX 3080'), ('CUDA_HOME', ':/usr/local/cuda'), ('GCC', 'gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0'), ('PyTorch', '1.10.1+cu111'), ('PyTorch compiling details', 'PyTorch built with:\n - GCC 7.3\n - C++ Version: 201402\n - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications\n - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)\n - OpenMP 201511 (a.k.a. OpenMP 4.5)\n - LAPACK is enabled (usually provided by MKL)\n - NNPACK is enabled\n - CPU capability usage: AVX512\n - CUDA Runtime 11.1\n - 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_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\n - CuDNN 8.0.5\n - Magma 2.5.2\n - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, \n'), ('TorchVision', '0.11.2+cu111'), ('OpenCV', '4.9.0'), ('MMEngine', '0.10.3'), ('MMPose', '1.0.0+HEAD')])

Reproduces the problem - code sample

base = ['mmpose::base/default_runtime.py']

model settings

model = dict(
type='YOLODetector',
use_syncbn=False,
init_cfg=dict(
type='Pretrained',
checkpoint='https://download.openmmlab.com/mmyolo/v0/yolox/'
'yolox_s_fast_8xb32-300e-rtmdet-hyp_coco/yolox_s_fast_'
'8xb32-300e-rtmdet-hyp_coco_20230210_134645-3a8dfbd7.pth'),
data_preprocessor=dict(
type='mmdet.DetDataPreprocessor',
pad_size_divisor=32,
batch_augments=[
dict(
type='PoseBatchSyncRandomResize',
random_size_range=(480, 800),
size_divisor=32,
interval=1)
]),
backbone=dict(
type='YOLOXCSPDarknet',
deepen_factor=0.33,
widen_factor=0.5,
out_indices=(2, 3, 4),
spp_kernal_sizes=(5, 9, 13),
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='SiLU', inplace=True),
),
neck=dict(
type='YOLOXPAFPN',
deepen_factor=0.33,
widen_factor=0.5,
in_channels=[256, 512, 1024],
out_channels=256,
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='SiLU', inplace=True)),
bbox_head=dict(
type='YOLOXPoseHead',
head_module=dict(
type='YOLOXPoseHeadModule',
num_classes=1,
in_channels=256,
feat_channels=256,
widen_factor=0.5,
stacked_convs=2,
num_keypoints=1,
featmap_strides=(8, 16, 32),
use_depthwise=False,
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='SiLU', inplace=True),
),
loss_cls=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=True,
reduction='sum',
loss_weight=1.0),
loss_bbox=dict(
type='mmdet.IoULoss',
mode='square',
eps=1e-16,
reduction='sum',
loss_weight=5.0),
loss_obj=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=True,
reduction='sum',
loss_weight=1.0),
loss_pose=dict(
type='OksLoss',
metainfo='configs/base/datasets/coco.py',
loss_weight=30.0),
loss_bbox_aux=dict(
type='mmdet.L1Loss', reduction='sum', loss_weight=1.0)),
train_cfg=dict(
assigner=dict(
type='PoseSimOTAAssigner',
center_radius=2.5,
iou_calculator=dict(type='mmdet.BboxOverlaps2D'),
oks_calculator=dict(
type='OksLoss', metainfo='configs/base/datasets/coco.py'))),
test_cfg=dict(
yolox_style=True,
multi_label=False,
score_thr=0.001,
max_per_img=300,
nms=dict(type='nms', iou_threshold=0.65)))

data related

img_scale = (640, 640)

pipelines

pre_transform = [
dict(type='mmpose.LoadImage', backend_args=base.backend_args),
dict(type='PoseToDetConverter')
]

train_pipeline_stage1 = [
*pre_transform,
dict(
type='Mosaic',
img_scale=img_scale,
pad_val=114.0,
pre_transform=pre_transform),
dict(
type='mmdet.RandomAffine',
scaling_ratio_range=(0.75, 1.0),
border=(-img_scale[0] // 2, -img_scale[1] // 2)),
dict(
type='YOLOXMixUp',
img_scale=img_scale,
ratio_range=(0.8, 1.6),
pad_val=114.0,
pre_transform=pre_transform),
dict(type='mmdet.YOLOXHSVRandomAug'),
dict(type='mmdet.RandomFlip', prob=0.5),
dict(type='FilterDetPoseAnnotations', keep_empty=False),
dict(
type='PackDetPoseInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape'))
]

train_pipeline_stage2 = [
*pre_transform,
dict(type='mmdet.Resize', scale=img_scale, keep_ratio=True),
dict(
type='mmdet.Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='mmdet.YOLOXHSVRandomAug'),
dict(type='mmdet.RandomFlip', prob=0.5),
dict(type='FilterDetPoseAnnotations', keep_empty=False),
dict(type='PackDetPoseInputs')
]

test_pipeline = [
*pre_transform,
dict(type='mmdet.Resize', scale=img_scale, keep_ratio=True),
dict(
type='mmdet.Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(
type='PackDetPoseInputs',
meta_keys=('id', 'img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip_indices'))
]

dataset settings

dataset_type = 'CocoDataset'
data_mode = 'bottomup'
data_root = 'data/my/'

train_dataloader = dict(
batch_size=8,
num_workers=1,
persistent_workers=True,
pin_memory=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type=dataset_type,
data_mode=data_mode,
data_root=data_root,
ann_file='train_coco.json',
data_prefix=dict(img='images/'),
filter_cfg=dict(filter_empty_gt=False, min_size=32),
pipeline=train_pipeline_stage1))

val_dataloader = dict(
batch_size=8,
num_workers=1,
persistent_workers=True,
pin_memory=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_mode=data_mode,
data_root=data_root,
ann_file='val_coco.json',
data_prefix=dict(img='images/'),
test_mode=True,
pipeline=test_pipeline))

test_dataloader = val_dataloader

evaluators

val_evaluator = dict(
type='mmpose.CocoMetric',
ann_file=data_root + 'val_coco.json',
score_mode='bbox')
test_evaluator = val_evaluator

default_hooks = dict(checkpoint=dict(save_best='coco/AP', rule='greater'))

optimizer

base_lr = 0.004
max_epochs = 300
num_last_epochs = 20
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))

param_scheduler = [
dict(
# use quadratic formula to warm up 5 epochs
# and lr is updated by iteration
type='mmdet.QuadraticWarmupLR',
by_epoch=True,
begin=0,
end=5,
convert_to_iter_based=True),
dict(
# use cosine lr from 5 to 285 epoch
type='CosineAnnealingLR',
eta_min=base_lr * 0.05,
begin=5,
T_max=max_epochs - num_last_epochs,
end=max_epochs - num_last_epochs,
by_epoch=True,
convert_to_iter_based=True),
dict(
# use fixed lr during last num_last_epochs epochs
type='ConstantLR',
by_epoch=True,
factor=1,
begin=max_epochs - num_last_epochs,
end=max_epochs,
)
]

runtime

custom_hooks = [
dict(
type='YOLOXModeSwitchHook',
num_last_epochs=num_last_epochs,
new_train_pipeline=train_pipeline_stage2,
priority=48),
dict(type='mmdet.SyncNormHook', priority=48),
dict(
type='EMAHook',
ema_type='ExpMomentumEMA',
momentum=0.0002,
update_buffers=True,
strict_load=False,
priority=49)
]

train_cfg = dict(
type='EpochBasedTrainLoop',
max_epochs=max_epochs,
val_interval=10,
dynamic_intervals=[(max_epochs - num_last_epochs, 1)])

auto_scale_lr = dict(base_batch_size=256)

Reproduces the problem - command or script

python tools/train.py data/yolox.py

Reproduces the problem - error message

Traceback (most recent call last):
File "tools/train.py", line 160, in
main()
File "tools/train.py", line 153, in main
runner = Runner.from_cfg(cfg)
File "/home/dell/anaconda3/envs/mmpose/lib/python3.8/site-packages/mmengine/runner/runner.py", line 462, in from_cfg
runner = cls(
File "/home/dell/anaconda3/envs/mmpose/lib/python3.8/site-packages/mmengine/runner/runner.py", line 429, in init
self.model = self.build_model(model)
File "/home/dell/anaconda3/envs/mmpose/lib/python3.8/site-packages/mmengine/runner/runner.py", line 836, in build_model
model = MODELS.build(model)
File "/home/dell/anaconda3/envs/mmpose/lib/python3.8/site-packages/mmengine/registry/registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/home/dell/anaconda3/envs/mmpose/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 232, in build_model_from_cfg
return build_from_cfg(cfg, registry, default_args)
File "/home/dell/anaconda3/envs/mmpose/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 100, in build_from_cfg
raise KeyError(
KeyError: 'YOLODetector is not in the mmpose::model registry. Please check whether the value of YOLODetector is correct or it was registered as expected. More details can be found at https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module'

Additional information

No response