code_test/configs/AD_detection/AD_dsxw_test19.py

_base_ = ['../_base_/schedules/schedule_1x_original.py', '../_base_/default_runtime.py']

# model settings
model = dict(
    type='YOLOX',
    backbone=dict(type='CSPDarknet', deepen_factor=1.0, widen_factor=1.0),
    neck=dict(
        type='YOLOXPAFPN',
        in_channels=[256, 512, 1024],
        out_channels=256,
        num_csp_blocks=3),
    bbox_head=dict(
        type='YOLOXHead', num_classes=11, in_channels=256, feat_channels=256),
    train_cfg=dict(assigner=dict(type='SimOTAAssigner', center_radius=2.5)),
    # In order to align the source code, the threshold of the val phase is
    # 0.01, and the threshold of the test phase is 0.001.
    test_cfg=dict(score_thr=0.01, nms=dict(type='nms', iou_threshold=0.65)))

# dataset settings
dataset_type = 'CocoDataset'
classes = ('yiwei','loujian','celi','libei','fantie','lianxi','duojian','shunjian','shaoxi','jiahan','yiwu')

img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

img_scale = (400, 400)

train_pipeline = [
    dict(type='Mosaic', img_scale=img_scale, pad_val=0),
    dict(
        type='RandomAffine',
        scaling_ratio_range=(0.1, 2),
        border=(-img_scale[0] // 2, -img_scale[1] // 2)),
    dict(
        type='PhotoMetricDistortion',
        brightness_delta=32,
        contrast_range=(0.5, 1.5),
        saturation_range=(0.5, 1.5),
        hue_delta=18),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Resize', keep_ratio=True),
    dict(type='Pad', size_divisor=32),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]

train_dataset = dict(
    type='MultiImageMixDataset',
    dataset=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v4/dsxw_train/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v4/dsxw_train/annotations/train.json',
        pipeline=[
            dict(type='LoadImageFromFile', to_float32=True),
            dict(type='LoadAnnotations', with_bbox=True)
        ],
        filter_empty_gt=False,
    ),
    pipeline=train_pipeline,
    dynamic_scale=img_scale)

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=img_scale,
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Pad', size_divisor=32),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img'])
        ])
]

data = dict(
    samples_per_gpu=8,
    workers_per_gpu=8,
    train=train_dataset,
    val=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v4/dsxw_test/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v4/dsxw_test/annotations/test.json',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v4/dsxw_test/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/userdata/datasets/dsxw_dataset_v4/dsxw_test/annotations/test.json',
        pipeline=test_pipeline))

# optimizer
# default 8 gpu
optimizer = dict(
    type='SGD',
    lr=0.01,
    momentum=0.9,
    weight_decay=5e-4,
    nesterov=True,
    paramwise_cfg=dict(norm_decay_mult=0., bias_decay_mult=0.))
optimizer_config = dict(grad_clip=None)

# learning policy
lr_config = dict(
    _delete_=True,
    policy='YOLOX',
    warmup='exp',
    by_epoch=False,
    warmup_by_epoch=True,
    warmup_ratio=1,
    warmup_iters=5,  # 5 epoch
    num_last_epochs=15,
    min_lr_ratio=0.05)
runner = dict(type='EpochBasedRunner', max_epochs=60)

resume_from = None
interval = 5

custom_hooks = [
    dict(type='YOLOXModeSwitchHook', num_last_epochs=15, priority=48),
    dict(
        type='SyncRandomSizeHook',
        ratio_range=(14, 26),
        img_scale=img_scale,
        priority=48),
    dict(
        type='SyncNormHook',
        num_last_epochs=15,
        interval=interval,
        priority=48),
    dict(type='ExpMomentumEMAHook', resume_from=resume_from, priority=49)
]
checkpoint_config = dict(interval=interval)
evaluation = dict(interval=interval, metric='bbox')
log_config = dict(interval=50)