mmpose/demo/mmdetection_cfg/yolox-s_8xb8-300e_coco-face.py

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'