|
- _base_ = [
- '../_base_/datasets/hrsc.py', '../_base_/schedules/schedule_3x.py',
- '../_base_/default_runtime.py'
- ]
-
- angle_version = 'le90'
- model = dict(
- type='ReDet',
- backbone=dict(
- type='ReResNet',
- depth=50,
- num_stages=4,
- out_indices=(0, 1, 2, 3),
- frozen_stages=1,
- style='pytorch',
- pretrained='./work_dirs/re_resnet50_c8_batch256-25b16846.pth'),
- neck=dict(
- type='ReFPN',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- num_outs=5),
- rpn_head=dict(
- type='RotatedRPNHead',
- in_channels=256,
- feat_channels=256,
- version=angle_version,
- anchor_generator=dict(
- type='AnchorGenerator',
- scales=[8],
- ratios=[0.5, 1.0, 2.0],
- strides=[4, 8, 16, 32, 64]),
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[.0, .0, .0, .0],
- target_stds=[1.0, 1.0, 1.0, 1.0]),
- loss_cls=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
- roi_head=dict(
- type='RoITransRoIHead',
- version=angle_version,
- num_stages=2,
- stage_loss_weights=[1, 1],
- bbox_roi_extractor=[
- dict(
- type='SingleRoIExtractor',
- roi_layer=dict(
- type='RoIAlign', output_size=7, sampling_ratio=0),
- out_channels=256,
- featmap_strides=[4, 8, 16, 32]),
- dict(
- type='RotatedSingleRoIExtractor',
- roi_layer=dict(
- type='RiRoIAlignRotated',
- out_size=7,
- num_samples=2,
- num_orientations=8,
- clockwise=True),
- out_channels=256,
- featmap_strides=[4, 8, 16, 32]),
- ],
- bbox_head=[
- dict(
- type='RotatedShared2FCBBoxHead',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=1,
- bbox_coder=dict(
- type='DeltaXYWHAHBBoxCoder',
- angle_range=angle_version,
- norm_factor=2,
- edge_swap=True,
- target_means=[0., 0., 0., 0., 0.],
- target_stds=[0.1, 0.1, 0.2, 0.2, 0.1]),
- reg_class_agnostic=True,
- loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
- loss_weight=1.0)),
- dict(
- type='RotatedShared2FCBBoxHead',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=1,
- bbox_coder=dict(
- type='DeltaXYWHAOBBoxCoder',
- angle_range=angle_version,
- norm_factor=None,
- edge_swap=True,
- proj_xy=True,
- target_means=[0., 0., 0., 0., 0.],
- target_stds=[0.05, 0.05, 0.1, 0.1, 0.05]),
- reg_class_agnostic=False,
- loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
- ]),
- train_cfg=dict(
- rpn=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.7,
- neg_iou_thr=0.3,
- min_pos_iou=0.3,
- match_low_quality=True,
- ignore_iof_thr=-1),
- sampler=dict(
- type='RandomSampler',
- num=256,
- pos_fraction=0.5,
- neg_pos_ub=-1,
- add_gt_as_proposals=False),
- allowed_border=0,
- pos_weight=-1,
- debug=False),
- rpn_proposal=dict(
- nms_pre=2000,
- max_per_img=2000,
- nms=dict(type='nms', iou_threshold=0.7),
- min_bbox_size=0),
- rcnn=[
- dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.5,
- neg_iou_thr=0.5,
- min_pos_iou=0.5,
- match_low_quality=False,
- ignore_iof_thr=-1,
- iou_calculator=dict(type='BboxOverlaps2D')),
- sampler=dict(
- type='RandomSampler',
- num=512,
- pos_fraction=0.25,
- neg_pos_ub=-1,
- add_gt_as_proposals=True),
- pos_weight=-1,
- debug=False),
- dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.5,
- neg_iou_thr=0.5,
- min_pos_iou=0.5,
- match_low_quality=False,
- ignore_iof_thr=-1,
- iou_calculator=dict(type='RBboxOverlaps2D')),
- sampler=dict(
- type='RRandomSampler',
- num=512,
- pos_fraction=0.25,
- neg_pos_ub=-1,
- add_gt_as_proposals=True),
- pos_weight=-1,
- debug=False)
- ]),
- test_cfg=dict(
- rpn=dict(
- nms_pre=2000,
- max_per_img=2000,
- nms=dict(type='nms', iou_threshold=0.7),
- min_bbox_size=0),
- rcnn=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=(800, 512)),
- dict(type='RRandomFlip', 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=(800, 512),
- flip=False,
- transforms=[
- dict(type='RResize'),
- dict(type='Normalize', **img_norm_cfg),
- dict(type='Pad', size_divisor=32),
- dict(type='DefaultFormatBundle'),
- dict(type='Collect', keys=['img'])
- ])
- ]
-
- data = dict(
- train=dict(pipeline=train_pipeline),
- val=dict(pipeline=test_pipeline),
- test=dict(pipeline=test_pipeline))
-
- evaluation = dict(interval=12, metric='mAP')
- optimizer = dict(lr=0.01)
|