123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105 |
- _base_ = [
- '../_base_/datasets/coco_detection.py',
- '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
- ]
- model = dict(
- type='CenterNet',
- # use caffe img_norm
- data_preprocessor=dict(
- type='DetDataPreprocessor',
- mean=[103.530, 116.280, 123.675],
- std=[1.0, 1.0, 1.0],
- bgr_to_rgb=False,
- 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=False),
- norm_eval=True,
- style='caffe',
- init_cfg=dict(
- type='Pretrained',
- checkpoint='open-mmlab://detectron2/resnet50_caffe')),
- neck=dict(
- type='FPN',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- start_level=1,
- add_extra_convs='on_output',
- num_outs=5,
- # There is a chance to get 40.3 after switching init_cfg,
- # otherwise it is about 39.9~40.1
- init_cfg=dict(type='Caffe2Xavier', layer='Conv2d'),
- relu_before_extra_convs=True),
- bbox_head=dict(
- type='CenterNetUpdateHead',
- num_classes=80,
- in_channels=256,
- stacked_convs=4,
- feat_channels=256,
- strides=[8, 16, 32, 64, 128],
- hm_min_radius=4,
- hm_min_overlap=0.8,
- more_pos_thresh=0.2,
- more_pos_topk=9,
- soft_weight_on_reg=False,
- loss_cls=dict(
- type='GaussianFocalLoss',
- pos_weight=0.25,
- neg_weight=0.75,
- loss_weight=1.0),
- loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
- ),
- train_cfg=None,
- 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))
- # single-scale training is about 39.3
- train_pipeline = [
- dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='RandomChoiceResize',
- scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
- (1333, 768), (1333, 800)],
- keep_ratio=True),
- dict(type='RandomFlip', prob=0.5),
- dict(type='PackDetInputs')
- ]
- train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
- # learning rate
- param_scheduler = [
- dict(
- type='LinearLR',
- start_factor=0.00025,
- by_epoch=False,
- begin=0,
- end=4000),
- dict(
- type='MultiStepLR',
- begin=0,
- end=12,
- by_epoch=True,
- milestones=[8, 11],
- gamma=0.1)
- ]
- optim_wrapper = dict(
- optimizer=dict(lr=0.01),
- # Experiments show that there is no need to turn on clip_grad.
- paramwise_cfg=dict(norm_decay_mult=0.))
- # NOTE: `auto_scale_lr` is for automatically scaling LR,
- # USER SHOULD NOT CHANGE ITS VALUES.
- # base_batch_size = (8 GPUs) x (2 samples per GPU)
- auto_scale_lr = dict(base_batch_size=16)
|