code_test/configs/AD_detection/AD_dsxw_test14.py

_base_ = [
    '../_base_/models/cascade_rcnn_r50_fpn.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
    backbone=dict(
        _delete_=True,
        type='PyramidVisionTransformerV2',
        embed_dims=64,
        num_layers=[3, 6, 40, 3],
        mlp_ratios=(4, 4, 4, 4),
        init_cfg=dict(checkpoint='https://github.com/whai362/PVT/'
                      'releases/download/v2/pvt_v2_b5.pth')),
    neck=dict(
        type='FPN',#FPN  PAFPN
        in_channels=[64, 128, 320, 512],
        out_channels=256,
        num_outs=5,
        start_level=1,
        add_extra_convs='on_input'),
    roi_head=dict(
        bbox_head=[
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=3,
                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=3,
                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=3,
                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))
        ]))

dataset_type = 'CocoDataset'
classes = ('False_welding','Missing_parts','Displacement')

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='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='Resize',
        img_scale=[(400, 300), (500, 400)],
        multiscale_mode='value',
        keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=[0.2,0.2,0.2], direction=['horizontal', 'vertical', 'diagonal']),
    dict(type='BrightnessTransform', level=5, prob=0.5),
    dict(type='ContrastTransform', level=5, prob=0.5),
    dict(type='RandomShift', shift_ratio=0.5),
    dict(type='MinIoURandomCrop', min_ious=(0.5, 0.7, 0.9), min_crop_size=0.8),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=[(400, 300), (500, 400)],
        flip=True,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]

data = dict(
    samples_per_gpu=16,
    workers_per_gpu=8,
    train=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_train/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/userdata/datasets/dsxw_train/annotations/train.json',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_test/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/userdata/datasets/dsxw_test/annotations/test.json',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        img_prefix='/home/shanwei-luo/userdata/datasets/dsxw_test/images/',
        classes=classes,
        ann_file='/home/shanwei-luo/userdata/datasets/dsxw_test/annotations/test.json',
        pipeline=test_pipeline))

# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
    policy='CosineAnnealing',
    warmup='linear',
    warmup_iters=2000,
    warmup_ratio=1.0 / 10,
    min_lr_ratio=1e-5)
runner = dict(type='EpochBasedRunner', max_epochs=60)

evaluation = dict(interval=5, metric='bbox')