|
- _base_ = [
- '../_base_/datasets/dotav1.py', '../_base_/schedules/schedule_1x.py',
- '../_base_/default_runtime.py'
- ]
-
- angle_version = 'oc'
- model = dict(
- type='R3Det',
- backbone=dict(
- type='ResNet',
- depth=50,
- num_stages=4,
- out_indices=(0, 1, 2, 3),
- frozen_stages=1,
- zero_init_residual=False,
- 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_input',
- num_outs=5),
- bbox_head=dict(
- type='RotatedRetinaHead',
- num_classes=15,
- in_channels=256,
- stacked_convs=2,
- feat_channels=256,
- anchor_generator=dict(
- type='RotatedAnchorGenerator',
- octave_base_scale=4,
- scales_per_octave=3,
- ratios=[1.0, 0.5, 2.0],
- strides=[8, 16, 32, 64, 128]),
- bbox_coder=dict(
- type='DeltaXYWHAOBBoxCoder',
- angle_range=angle_version,
- norm_factor=None,
- edge_swap=False,
- proj_xy=False,
- target_means=(.0, .0, .0, .0, .0),
- target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
- frm_cfgs=[dict(in_channels=256, featmap_strides=[8, 16, 32, 64, 128])],
- num_refine_stages=1,
- refine_heads=[
- dict(
- type='RotatedRetinaRefineHead',
- num_classes=15,
- in_channels=256,
- stacked_convs=2,
- feat_channels=256,
- assign_by_circumhbbox=None,
- anchor_generator=dict(
- type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
- bbox_coder=dict(
- type='DeltaXYWHAOBBoxCoder',
- angle_range=angle_version,
- norm_factor=None,
- edge_swap=False,
- proj_xy=False,
- target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
- target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0))
- ],
- train_cfg=dict(
- s0=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.5,
- neg_iou_thr=0.4,
- min_pos_iou=0,
- ignore_iof_thr=-1,
- iou_calculator=dict(type='RBboxOverlaps2D')),
- allowed_border=-1,
- pos_weight=-1,
- debug=False),
- sr=[
- dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.6,
- neg_iou_thr=0.5,
- min_pos_iou=0,
- ignore_iof_thr=-1,
- iou_calculator=dict(type='RBboxOverlaps2D')),
- allowed_border=-1,
- pos_weight=-1,
- debug=False)
- ],
- stage_loss_weights=[1.0]),
- test_cfg=dict(
- nms_pre=2000,
- min_bbox_size=0,
- score_thr=0.05,
- nms=dict(iou_thr=0.1),
- max_per_img=2000))
-
- 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='RResize', img_scale=(1024, 1024)),
- dict(
- type='RRandomFlip',
- flip_ratio=[0.25, 0.25, 0.25],
- direction=['horizontal', 'vertical', 'diagonal'],
- version=angle_version),
- dict(type='Normalize', **img_norm_cfg),
- dict(type='Pad', size_divisor=32),
- dict(type='DefaultFormatBundle'),
- dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
- ]
- data = dict(
- train=dict(pipeline=train_pipeline, version=angle_version),
- val=dict(version=angle_version),
- test=dict(version=angle_version))
|