|
- _base_ = [
- '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
- ]
- pretrained = 'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth'
- model = dict(
- type='ATSS',
- backbone=dict(
- depths=[2, 2, 18, 2],
- type='SwinTransformer',
- embed_dims=96,
- num_heads=[3, 6, 12, 24],
- window_size=7,
- mlp_ratio=4,
- qkv_bias=True,
- qk_scale=None,
- drop_rate=0.,
- attn_drop_rate=0.,
- drop_path_rate=0.2,
- patch_norm=True,
- out_indices=(0, 1, 2, 3),
- with_cp=False,
- convert_weights=True,
- init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
- neck=dict(
- type='FPN',
- in_channels=[96, 192, 384, 768],
- out_channels=256,
- num_outs=5),
- bbox_head=dict(
- type='ATSSHead',
- num_classes=11,
- in_channels=256,
- stacked_convs=4,
- feat_channels=256,
- anchor_generator=dict(
- type='AnchorGenerator',
- ratios=[1.0],
- octave_base_scale=8,
- scales_per_octave=1,
- strides=[8, 16, 32, 64, 128]),
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[.0, .0, .0, .0],
- target_stds=[0.1, 0.1, 0.2, 0.2]),
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
- loss_centerness=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
- # training and testing settings
- train_cfg=dict(
- assigner=dict(type='ATSSAssigner', topk=9),
- allowed_border=-1,
- pos_weight=-1,
- debug=False),
- test_cfg=dict(
- nms_pre=1000,
- min_bbox_size=0,
- score_thr=0.05,
- nms=dict(type='nms', iou_threshold=0.6),
- max_per_img=100))
-
- 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)
-
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='Resize',
- img_scale=[(400, 400), (500, 500)],
- 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, 400)],
- flip=False,
- 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=6,
- workers_per_gpu=6,
- train=dict(
- type='AD_ClassBalancedDataset',
- dataset=dict(
- type=dataset_type,
- img_prefix='/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_2106_10_coco/train/images/',
- classes=classes,
- ann_file='/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_2106_10_coco/train/annotations/train.json',
- pipeline=train_pipeline,
- ),
- oversample_thr = 1.0),
- val=dict(
- type=dataset_type,
- img_prefix='/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_2112_coco/test/images/',
- classes=classes,
- ann_file='/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_2112_coco/test/annotations/test.json',
- pipeline=test_pipeline),
- test=dict(
- type=dataset_type,
- img_prefix='/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_2112_coco/test/images/',
- classes=classes,
- ann_file='/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_2112_coco/test/annotations/test.json',
- pipeline=test_pipeline))
-
- # optimizer
- optimizer = dict(
- _delete_=True,
- type='AdamW',
- lr=0.0001,
- betas=(0.9, 0.999),
- weight_decay=0.05,
- paramwise_cfg=dict(
- custom_keys={
- 'absolute_pos_embed': dict(decay_mult=0.),
- 'relative_position_bias_table': dict(decay_mult=0.),
- 'norm': dict(decay_mult=0.)
- }))
- optimizer_config = dict(grad_clip=None)
- # learning policy
- lr_config = dict(
- _delete_=True,
- policy='step',
- warmup='linear',
- warmup_iters=1000,
- warmup_ratio=0.001,
- step=[8, 11])
-
- runner = dict(type='EpochBasedRunner', max_epochs=20)
-
- evaluation = dict(interval=1, metric='bbox')
- checkpoint_config = dict(interval=1)
|