crosstyan/RapidPoseTriangulation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Create custom dockerfile as well.

Browse Source
This commit is contained in:
Daniel
2025-03-17 16:05:26 +01:00
parent 5de7764e68
commit dff0f71309
4 changed files with 250 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

235
extras/mmpose/configs/rtmpose-l_8xb32-270e_coco-wholebody-384x288.py Normal file
View File

@ -0,0 +1,235 @@
_base_ = ['mmpose::_base_/default_runtime.py']
val_interval=1
max_epochs = 3
# common setting
num_keypoints = 133
input_size = (288, 384)
# runtime
stage2_num_epochs = 30
base_lr = 4e-3
train_batch_size = 32
val_batch_size = 32
train_cfg = dict(max_epochs=max_epochs, val_interval=val_interval)
randomness = dict(seed=21)
# optimizer
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
clip_grad=dict(max_norm=35, norm_type=2),
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(
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=512)
# codec settings
codec = dict(
type='SimCCLabel',
input_size=input_size,
sigma=(6., 6.93),
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=num_keypoints,
input_size=codec['input_size'],
in_featuremap_size=tuple([s // 32 for s in codec['input_size']]),
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 = 'CocoWholeBodyDataset'
data_mode = 'topdown'
data_root = 'data/coco/'
backend_args = dict(backend='local')
# 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=1.0),
]),
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=train_batch_size,
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/coco_wholebody_train_v1.0.json',
data_prefix=dict(img='train2017/'),
pipeline=train_pipeline,
))
val_dataloader = dict(
batch_size=val_batch_size,
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/coco_wholebody_val_v1.0.json',
data_prefix=dict(img='val2017/'),
test_mode=True,
# bbox_file='data/coco/person_detection_results/'
# 'COCO_val2017_detections_AP_H_56_person.json',
pipeline=val_pipeline,
))
test_dataloader = val_dataloader
# hooks
default_hooks = dict(
checkpoint=dict(
save_best='coco-wholebody/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='CocoWholeBodyMetric',
ann_file=data_root + 'annotations/coco_wholebody_val_v1.0.json')
test_evaluator = val_evaluator