|
- _base_ = [
- '../_base_/datasets/coco_detection.py',
- '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
- ]
- # model settings
- model = dict(
- type='VFNet',
- backbone=dict(
- type='ResNet',
- depth=50,
- num_stages=4,
- out_indices=(0, 1, 2, 3),
- frozen_stages=1,
- norm_cfg=dict(type='BN', requires_grad=True),
- norm_eval=True,
- style='pytorch',
- init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
- neck=dict(
- type='FPN',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- start_level=1,
- add_extra_convs='on_output', # use P5
- num_outs=5,
- relu_before_extra_convs=True),
- bbox_head=dict(
- type='VFNetHead',
- num_classes=80,
- in_channels=256,
- stacked_convs=3,
- feat_channels=256,
- strides=[8, 16, 32, 64, 128],
- center_sampling=False,
- dcn_on_last_conv=False,
- use_atss=True,
- use_vfl=True,
- loss_cls=dict(
- type='VarifocalLoss',
- use_sigmoid=True,
- alpha=0.75,
- gamma=2.0,
- iou_weighted=True,
- loss_weight=1.0),
- loss_bbox=dict(type='GIoULoss', loss_weight=1.5),
- loss_bbox_refine=dict(type='GIoULoss', loss_weight=2.0)),
- # 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))
-
- # data setting
- dataset_type = 'CocoDataset'
- data_root = 'data/coco/'
- 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=(1333, 800), keep_ratio=True),
- dict(type='RandomFlip', flip_ratio=0.5),
- 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=(1333, 800),
- 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='DefaultFormatBundle'),
- dict(type='Collect', keys=['img']),
- ])
- ]
- data = dict(
- samples_per_gpu=2,
- workers_per_gpu=2,
- train=dict(pipeline=train_pipeline),
- val=dict(pipeline=test_pipeline),
- test=dict(pipeline=test_pipeline))
-
- # optimizer
- optimizer = dict(
- lr=0.01, paramwise_cfg=dict(bias_lr_mult=2., bias_decay_mult=0.))
- optimizer_config = dict(grad_clip=None)
- # learning policy
- lr_config = dict(
- policy='step',
- warmup='linear',
- warmup_iters=500,
- warmup_ratio=0.1,
- step=[8, 11])
- runner = dict(type='EpochBasedRunner', max_epochs=12)
|