今天，学习RTMPose关键点检测实战。教大家如何安装安装MMDetection和MMPose。
实战项目以三角板关键点检测场景为例，结合OpenMMLab开源目标检测算法库MMDetection、开源关键点检测算法库MMPose、开源模型部署算法库MMDeploy，全面讲解项目全流程：
数据集：Labelme标注数据集、整理标注格式至MS COCO
目标检测：分别训练Faster R CNN和RTMDet-Tiny目标检测模型、训练日志可视化、测试集评估、对图像、摄像头画面预测
关键点检测：训练RTMPose-S关键点检测模型、训练日志可视化、测试集上评估、分别对“图像、视频、摄像头画面”预测
模型终端部署：转ONNX格式，终端推理
一、引言
耳朵穴位是中医针灸的重要组成部分，准确定位耳朵穴位对于针灸治疗和健康监测具有重要意义。传统的耳朵穴位检测方法依赖于人工标记，效率低下且容易受到人为因素的影响。随着深度学习和计算机视觉技术的发展，基于图像的自动化穴位检测方法逐渐成为研究热点。
RTMPose是一种基于深度学习的姿态估计模型，具有较高的精度和鲁棒性。本文提出了一种结合RTMPose和检测技术的耳朵穴位关键点检测方法，通过引入先进的图像处理算法，实现对耳朵穴位的自动化检测和定位。
项目最终完成展示图
项目源码网盘自取：链接：https://pan.baidu.com/s/1QFFr4UBwaYePyIOFkgh5mw?pwd=4211
提取码：4211
二、首先要配置好所需环境
首先要配置好所需环境
首先要配置好所需环境
重要的事情说三遍！！！！
环境配置参考之前教学，传送门：https://blog.csdn.net/m0_74194018/article/details/140844116
打开项目目录结构如下图所示：（checkpoint权重文件我已经帮大家训练好了训练了7749个小时）
三、config配置文件我也已经准备好了不需要自己手动更改。
mmdetection_cfg
# runtime settings
default_scope = 'mmdet'
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=50),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', interval=1),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='DetVisualizationHook'))
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='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
log_level = 'INFO'
load_from = None
resume = False
# model settings
model = dict(
type='CascadeRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_mask=True,
pad_size_divisor=32),
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
]),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)
]),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
# If you don't have a gt annotation, delete the pipeline
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='AspectRatioBatchSampler'),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/instances_train2017.json',
data_prefix=dict(img='train2017/'),
filter_cfg=dict(filter_empty_gt=True, min_size=32),
pipeline=train_pipeline))
val_dataloader = dict(
batch_size=1,
num_workers=2,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/instances_val2017.json',
data_prefix=dict(img='val2017/'),
test_mode=True,
pipeline=test_pipeline))
test_dataloader = val_dataloader
val_evaluator = dict(
type='CocoMetric',
ann_file=data_root + 'annotations/instances_val2017.json',
metric='bbox',
format_only=False)
test_evaluator = val_evaluator
mmtracking_cfg
model = dict(
detector=dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(
type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[1.0, 1.0, 1.0, 1.0],
clip_border=False),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(
type='SmoothL1Loss', beta=0.1111111111111111,
loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(
type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2],
clip_border=False),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)),
init_cfg=dict(
type='Pretrained',
checkpoint='https://download.openmmlab.com/mmtracking/'
'mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth')),
type='DeepSORT',
motion=dict(type='KalmanFilter', center_only=False),
reid=dict(
type='BaseReID',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(3, ),
style='pytorch'),
neck=dict(type='GlobalAveragePooling', kernel_size=(8, 4), stride=1),
head=dict(
type='LinearReIDHead',
num_fcs=1,
in_channels=2048,
fc_channels=1024,
out_channels=128,
num_classes=380,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
loss_pairwise=dict(
type='TripletLoss', margin=0.3, loss_weight=1.0),
norm_cfg=dict(type='BN1d'),
act_cfg=dict(type='ReLU')),
init_cfg=dict(
type='Pretrained',
checkpoint='https://download.openmmlab.com/mmtracking/'
'mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth')),
tracker=dict(
type='SortTracker',
obj_score_thr=0.5,
reid=dict(
num_samples=10,
img_scale=(256, 128),
img_norm_cfg=None,
match_score_thr=2.0),
match_iou_thr=0.5,
momentums=None,
num_tentatives=2,
num_frames_retain=100))
dataset_type = 'MOTChallengeDataset'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadMultiImagesFromFile', to_float32=True),
dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
dict(
type='SeqResize',
img_scale=(1088, 1088),
share_params=True,
ratio_range=(0.8, 1.2),
keep_ratio=True,
bbox_clip_border=False),
dict(type='SeqPhotoMetricDistortion', share_params=True),
dict(
type='SeqRandomCrop',
share_params=False,
crop_size=(1088, 1088),
bbox_clip_border=False),
dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
dict(
type='SeqNormalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='SeqPad', size_divisor=32),
dict(type='MatchInstances', skip_nomatch=True),
dict(
type='VideoCollect',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
'gt_instance_ids'
]),
dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1088, 1088),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='VideoCollect', keys=['img'])
])
]
data_root = 'data/MOT17/'
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='MOTChallengeDataset',
visibility_thr=-1,
ann_file='data/MOT17/annotations/half-train_cocoformat.json',
img_prefix='data/MOT17/train',
ref_img_sampler=dict(
num_ref_imgs=1,
frame_range=10,
filter_key_img=True,
method='uniform'),
pipeline=[
dict(type='LoadMultiImagesFromFile', to_float32=True),
dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
dict(
type='SeqResize',
img_scale=(1088, 1088),
share_params=True,
ratio_range=(0.8, 1.2),
keep_ratio=True,
bbox_clip_border=False),
dict(type='SeqPhotoMetricDistortion', share_params=True),
dict(
type='SeqRandomCrop',
share_params=False,
crop_size=(1088, 1088),
bbox_clip_border=False),
dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
dict(
type='SeqNormalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='SeqPad', size_divisor=32),
dict(type='MatchInstances', skip_nomatch=True),
dict(
type='VideoCollect',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
'gt_instance_ids'
]),
dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
]),
val=dict(
type='MOTChallengeDataset',
ann_file='data/MOT17/annotations/half-val_cocoformat.json',
img_prefix='data/MOT17/train',
ref_img_sampler=None,
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1088, 1088),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='VideoCollect', keys=['img'])
])
]),
test=dict(
type='MOTChallengeDataset',
ann_file='data/MOT17/annotations/half-val_cocoformat.json',
img_prefix='data/MOT17/train',
ref_img_sampler=None,
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1088, 1088),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='VideoCollect', keys=['img'])
])
]))
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=100,
warmup_ratio=0.01,
step=[3])
total_epochs = 4
evaluation = dict(metric=['bbox', 'track'], interval=1)
search_metrics = ['MOTA', 'IDF1', 'FN', 'FP', 'IDs', 'MT', 'ML']
当然这里也可以用yolo来进行detection目标检测Yolo_cfg
Yolo的具体详细介绍可以参考我之前写的博客介绍，传送门：https://blog.csdn.net/m0_74194018/article/details/140747393
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=300, val_interval=10)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [
dict(
type='mmdet.QuadraticWarmupLR',
by_epoch=True,
begin=0,
end=5,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
eta_min=0.0005,
begin=5,
T_max=285,
end=285,
by_epoch=True,
convert_to_iter_based=True),
dict(type='ConstantLR', by_epoch=True, factor=1, begin=285, end=300)
]
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(
type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005, nesterov=True),
paramwise_cfg=dict(norm_decay_mult=0.0, bias_decay_mult=0.0))
auto_scale_lr = dict(enable=False, base_batch_size=64)
default_scope = 'mmdet'
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=50),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='DetVisualizationHook'))
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='DetLocalVisualizer',
vis_backends=[dict(type='LocalVisBackend')],
name='visualizer')
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
log_level = 'INFO'
load_from = 'https://download.openmmlab.com/mmdetection/' \
'v2.0/yolox/yolox_s_8x8_300e_coco/' \
'yolox_s_8x8_300e_coco_20211121_095711-4592a793.pth'
resume = False
img_scale = (640, 640)
model = dict(
type='YOLOX',
data_preprocessor=dict(
type='DetDataPreprocessor',
pad_size_divisor=32,
batch_augments=[
dict(
type='BatchSyncRandomResize',
random_size_range=(480, 800),
size_divisor=32,
interval=10)
]),
backbone=dict(
type='CSPDarknet',
deepen_factor=0.33,
widen_factor=0.5,
out_indices=(2, 3, 4),
use_depthwise=False,
spp_kernal_sizes=(5, 9, 13),
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='Swish')),
neck=dict(
type='YOLOXPAFPN',
in_channels=[128, 256, 512],
out_channels=128,
num_csp_blocks=1,
use_depthwise=False,
upsample_cfg=dict(scale_factor=2, mode='nearest'),
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='Swish')),
bbox_head=dict(
type='YOLOXHead',
num_classes=1,
in_channels=128,
feat_channels=128,
stacked_convs=2,
strides=(8, 16, 32),
use_depthwise=False,
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='Swish'),
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
reduction='sum',
loss_weight=1.0),
loss_bbox=dict(
type='IoULoss',
mode='square',
eps=1e-16,
reduction='sum',
loss_weight=5.0),
loss_obj=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
reduction='sum',
loss_weight=1.0),
loss_l1=dict(type='L1Loss', reduction='sum', loss_weight=1.0)),
train_cfg=dict(assigner=dict(type='SimOTAAssigner', center_radius=2.5)),
test_cfg=dict(score_thr=0.01, nms=dict(type='nms', iou_threshold=0.65)))
data_root = 'data/coco/'
dataset_type = 'CocoDataset'
backend_args = dict(backend='local')
train_pipeline = [
dict(type='Mosaic', img_scale=(640, 640), pad_val=114.0),
dict(
type='RandomAffine', scaling_ratio_range=(0.1, 2),
border=(-320, -320)),
dict(
type='MixUp',
img_scale=(640, 640),
ratio_range=(0.8, 1.6),
pad_val=114.0),
dict(type='YOLOXHSVRandomAug'),
dict(type='RandomFlip', prob=0.5),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False),
dict(type='PackDetInputs')
]
train_dataset = dict(
type='MultiImageMixDataset',
dataset=dict(
type='CocoDataset',
data_root='data/coco/',
ann_file='annotations/instances_train2017.json',
data_prefix=dict(img='train2017/'),
pipeline=[
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
dict(type='LoadAnnotations', with_bbox=True)
],
filter_cfg=dict(filter_empty_gt=False, min_size=32)),
pipeline=[
dict(type='Mosaic', img_scale=(640, 640), pad_val=114.0),
dict(
type='RandomAffine',
scaling_ratio_range=(0.1, 2),
border=(-320, -320)),
dict(
type='MixUp',
img_scale=(640, 640),
ratio_range=(0.8, 1.6),
pad_val=114.0),
dict(type='YOLOXHSVRandomAug'),
dict(type='RandomFlip', prob=0.5),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(
type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False),
dict(type='PackDetInputs')
])
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=8,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type='MultiImageMixDataset',
dataset=dict(
type='CocoDataset',
data_root='data/coco/',
ann_file='annotations/coco_face_train.json',
data_prefix=dict(img='train2017/'),
pipeline=[
dict(
type='LoadImageFromFile',
backend_args=dict(backend='local')),
dict(type='LoadAnnotations', with_bbox=True)
],
filter_cfg=dict(filter_empty_gt=False, min_size=32),
metainfo=dict(CLASSES=('person', ), PALETTE=(220, 20, 60))),
pipeline=[
dict(type='Mosaic', img_scale=(640, 640), pad_val=114.0),
dict(
type='RandomAffine',
scaling_ratio_range=(0.1, 2),
border=(-320, -320)),
dict(
type='MixUp',
img_scale=(640, 640),
ratio_range=(0.8, 1.6),
pad_val=114.0),
dict(type='YOLOXHSVRandomAug'),
dict(type='RandomFlip', prob=0.5),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(
type='FilterAnnotations',
min_gt_bbox_wh=(1, 1),
keep_empty=False),
dict(type='PackDetInputs')
]))
val_dataloader = dict(
batch_size=8,
num_workers=4,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='CocoDataset',
data_root='data/coco/',
ann_file='annotations/coco_face_val.json',
data_prefix=dict(img='val2017/'),
test_mode=True,
pipeline=[
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
],
metainfo=dict(CLASSES=('person', ), PALETTE=(220, 20, 60))))
test_dataloader = dict(
batch_size=8,
num_workers=4,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='CocoDataset',
data_root='data/coco/',
ann_file='annotations/coco_face_val.json',
data_prefix=dict(img='val2017/'),
test_mode=True,
pipeline=[
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
],
metainfo=dict(CLASSES=('person', ), PALETTE=(220, 20, 60))))
val_evaluator = dict(
type='CocoMetric',
ann_file='data/coco/annotations/coco_face_val.json',
metric='bbox')
test_evaluator = dict(
type='CocoMetric',
ann_file='data/coco/annotations/instances_val2017.json',
metric='bbox')
max_epochs = 300
num_last_epochs = 15
interval = 10
base_lr = 0.01
custom_hooks = [
dict(type='YOLOXModeSwitchHook', num_last_epochs=15, priority=48),
dict(type='SyncNormHook', priority=48),
dict(
type='EMAHook',
ema_type='ExpMomentumEMA',
momentum=0.0001,
strict_load=False,
update_buffers=True,
priority=49)
]
metainfo = dict(CLASSES=('person', ), PALETTE=(220, 20, 60))
launcher = 'pytorch'
四、output文件夹
这里主要存放模型推理处理过后的图像
work_dirs文件夹：主要存放我的训练日志
Ear.py
（这个文件主要用python的pyqt框架写一个特比简单的qt界面）
# -*- coding: utf-8 -*-
# Form implementation generated from reading ui file 'Ear.ui'
#
# Created by: PyQt5 UI code generator 5.15.9
#
# WARNING: Any manual changes made to this file will be lost when pyuic5 is
# run again. Do not edit this file unless you know what you are doing.
from PyQt5 import QtCore, QtGui, QtWidgets
class Ui_Form(object):
def setupUi(self, Form):
Form.setObjectName("Form")
Form.resize(795, 593)
self.listWidget = QtWidgets.QListWidget(Form)
self.listWidget.setGeometry(QtCore.QRect(90, 120, 221, 261))
self.listWidget.setObjectName("listWidget")
self.listWidget_2 = QtWidgets.QListWidget(Form)
self.listWidget_2.setGeometry(QtCore.QRect(480, 120, 221, 261))
self.listWidget_2.setObjectName("listWidget_2")
self.pushButton = QtWidgets.QPushButton(Form)
self.pushButton.setGeometry(QtCore.QRect(340, 310, 111, 31))
self.pushButton.setObjectName("pushButton")
self.label = QtWidgets.QLabel(Form)
self.label.setGeometry(QtCore.QRect(-30, -70, 1256, 707))
self.label.setText("")
self.label.setPixmap(QtGui.QPixmap("C:/Users/lenovo/Pictures/0d9289b1001061e53ca12b2063016c0.png"))
self.label.setScaledContents(True)
self.label.setWordWrap(False)
self.label.setOpenExternalLinks(True)
self.label.setObjectName("label")
self.pushButton_2 = QtWidgets.QPushButton(Form)
self.pushButton_2.setGeometry(QtCore.QRect(140, 200, 121, 101))
self.pushButton_2.setBaseSize(QtCore.QSize(0, 0))
self.pushButton_2.setIconSize(QtCore.QSize(16, 16))
self.pushButton_2.setShortcut("")
self.pushButton_2.setCheckable(False)
self.pushButton_2.setAutoRepeatInterval(100)
self.pushButton_2.setObjectName("pushButton_2")
self.label.raise_()
self.listWidget.raise_()
self.listWidget_2.raise_()
self.pushButton.raise_()
self.pushButton_2.raise_()
self.retranslateUi(Form)
QtCore.QMetaObject.connectSlotsByName(Form)
def retranslateUi(self, Form):
_translate = QtCore.QCoreApplication.translate
Form.setWindowTitle(_translate("Form", "Form"))
self.pushButton.setText(_translate("Form", "开始转换"))
self.pushButton_2.setText(_translate("Form", "上传"))
接着可以打开Ear_main.py文件运行一下查看效果:
五、上传我提前为大家准备好的侧视图test1.png，点击开始转换
处理好的图片保存到outputs文件夹里了
有两个warning可能是因为版本冲突的问题不是error可以忽略结果图
致辞这个项目完成啦，别忘了点赞收藏哦！！！继续关注我，教大家更多cv项目！！！
