|
- _base_ = [
- '../_base_/datasets/coco_detection.py', '../_base_/default_runtime.py'
- ]
- model = dict(
- type='DeformableDETR',
- backbone=dict(
- type='ResNet',
- depth=50,
- num_stages=4,
- out_indices=(1, 2, 3),
- frozen_stages=1,
- norm_cfg=dict(type='BN', requires_grad=False),
- norm_eval=True,
- style='pytorch',
- init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
- neck=dict(
- type='ChannelMapper',
- in_channels=[512, 1024, 2048],
- kernel_size=1,
- out_channels=256,
- act_cfg=None,
- norm_cfg=dict(type='GN', num_groups=32),
- num_outs=4),
- bbox_head=dict(
- type='DeformableDETRHead',
- with_box_refine=True,
- as_two_stage=True,
- num_query=300,
- num_classes=11,
- in_channels=2048,
- sync_cls_avg_factor=True,
- transformer=dict(
- type='DeformableDetrTransformer',
- encoder=dict(
- type='DetrTransformerEncoder',
- num_layers=6,
- transformerlayers=dict(
- type='BaseTransformerLayer',
- attn_cfgs=dict(
- type='MultiScaleDeformableAttention', embed_dims=256),
- feedforward_channels=1024,
- ffn_dropout=0.1,
- operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
- decoder=dict(
- type='DeformableDetrTransformerDecoder',
- num_layers=6,
- return_intermediate=True,
- transformerlayers=dict(
- type='DetrTransformerDecoderLayer',
- attn_cfgs=[
- dict(
- type='MultiheadAttention',
- embed_dims=256,
- num_heads=8,
- dropout=0.1),
- dict(
- type='MultiScaleDeformableAttention',
- embed_dims=256)
- ],
- feedforward_channels=1024,
- ffn_dropout=0.1,
- operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
- 'ffn', 'norm')))),
- positional_encoding=dict(
- type='SinePositionalEncoding',
- num_feats=128,
- normalize=True,
- offset=-0.5),
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=2.0),
- loss_bbox=dict(type='L1Loss', loss_weight=5.0),
- loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
- # training and testing settings
- train_cfg=dict(
- assigner=dict(
- type='HungarianAssigner',
- cls_cost=dict(type='FocalLossCost', weight=2.0),
- reg_cost=dict(type='BBoxL1Cost', weight=5.0, box_format='xywh'),
- iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
- test_cfg=dict(max_per_img=100))
- img_norm_cfg = dict(
- mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
- # train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
- # from the default setting in mmdet.
- 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),
- 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']),
- ])
- ]
-
- dataset_type = 'CocoDataset'
- classes = ('yiwei','loujian','celi','libei','fantie','lianxi','duojian','shunjian','shaoxi','jiahan','yiwu')
-
- data = dict(
- samples_per_gpu=16,
- workers_per_gpu=8,
- train=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=train_pipeline),
- 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
- optimizer = dict(
- type='AdamW',
- lr=2e-4,
- weight_decay=0.0001,
- paramwise_cfg=dict(
- custom_keys={
- 'backbone': dict(lr_mult=0.1),
- 'sampling_offsets': dict(lr_mult=0.1),
- 'reference_points': dict(lr_mult=0.1)
- }))
- optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
- # learning policy
- lr_config = dict(policy='step', step=[40])
- runner = dict(type='EpochBasedRunner', max_epochs=60)
-
- evaluation = dict(interval=5, metric='bbox')
|