| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104 |
- _base_ = [
- '../_base_/datasets/coco_detection.py',
- '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
- ]
- # model settings
- model = dict(
- type='VFNet',
- data_preprocessor=dict(
- type='DetDataPreprocessor',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- bgr_to_rgb=True,
- pad_size_divisor=32),
- 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
- train_pipeline = [
- dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(type='Resize', scale=(1333, 800), keep_ratio=True),
- dict(type='RandomFlip', prob=0.5),
- dict(type='PackDetInputs')
- ]
- test_pipeline = [
- dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
- dict(type='Resize', scale=(1333, 800), keep_ratio=True),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='PackDetInputs',
- meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
- 'scale_factor'))
- ]
- train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
- val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
- test_dataloader = val_dataloader
- # optimizer
- optim_wrapper = dict(
- optimizer=dict(lr=0.01),
- paramwise_cfg=dict(bias_lr_mult=2., bias_decay_mult=0.),
- clip_grad=None)
- # learning rate
- max_epochs = 12
- param_scheduler = [
- dict(type='LinearLR', start_factor=0.1, by_epoch=False, begin=0, end=500),
- dict(
- type='MultiStepLR',
- begin=0,
- end=max_epochs,
- by_epoch=True,
- milestones=[8, 11],
- gamma=0.1)
- ]
- train_cfg = dict(max_epochs=max_epochs)
|
