|
| 1 | +_base_ = [ |
| 2 | + '../_base_/datasets/dotav15.py', '../_base_/schedules/schedule_1x.py', |
| 3 | + '../_base_/default_runtime.py' |
| 4 | +] |
| 5 | +angle_version = 'le90' |
| 6 | + |
| 7 | +# model settings |
| 8 | +model = dict( |
| 9 | + type='H2RBoxV2Detector', |
| 10 | + crop_size=(1024, 1024), |
| 11 | + view_range=(0.25, 0.75), |
| 12 | + data_preprocessor=dict( |
| 13 | + type='mmdet.DetDataPreprocessor', |
| 14 | + mean=[123.675, 116.28, 103.53], |
| 15 | + std=[58.395, 57.12, 57.375], |
| 16 | + bgr_to_rgb=True, |
| 17 | + pad_size_divisor=32, |
| 18 | + boxtype2tensor=False), |
| 19 | + backbone=dict( |
| 20 | + type='mmdet.ResNet', |
| 21 | + depth=50, |
| 22 | + num_stages=4, |
| 23 | + out_indices=(0, 1, 2, 3), |
| 24 | + frozen_stages=1, |
| 25 | + norm_cfg=dict(type='BN', requires_grad=True), |
| 26 | + norm_eval=True, |
| 27 | + style='pytorch', |
| 28 | + init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), |
| 29 | + neck=dict( |
| 30 | + type='mmdet.FPN', |
| 31 | + in_channels=[256, 512, 1024, 2048], |
| 32 | + out_channels=256, |
| 33 | + start_level=1, |
| 34 | + add_extra_convs='on_output', |
| 35 | + num_outs=5, |
| 36 | + relu_before_extra_convs=True), |
| 37 | + bbox_head=dict( |
| 38 | + type='H2RBoxV2Head', |
| 39 | + num_classes=16, |
| 40 | + in_channels=256, |
| 41 | + angle_version='le90', |
| 42 | + stacked_convs=4, |
| 43 | + feat_channels=256, |
| 44 | + strides=[8, 16, 32, 64, 128], |
| 45 | + center_sampling=True, |
| 46 | + center_sample_radius=1.5, |
| 47 | + norm_on_bbox=True, |
| 48 | + centerness_on_reg=True, |
| 49 | + use_hbbox_loss=False, |
| 50 | + scale_angle=False, |
| 51 | + rotation_agnostic_classes=[1, 9, 11], |
| 52 | + agnostic_resize_classes=[1], |
| 53 | + use_circumiou_loss=True, |
| 54 | + use_standalone_angle=True, |
| 55 | + use_reweighted_loss_bbox=False, |
| 56 | + angle_coder=dict( |
| 57 | + type='PSCCoder', |
| 58 | + angle_version=angle_version, |
| 59 | + dual_freq=False, |
| 60 | + num_step=3, |
| 61 | + thr_mod=0), |
| 62 | + bbox_coder=dict( |
| 63 | + type='DistanceAnglePointCoder', angle_version=angle_version), |
| 64 | + loss_cls=dict( |
| 65 | + type='mmdet.FocalLoss', |
| 66 | + use_sigmoid=True, |
| 67 | + gamma=2.0, |
| 68 | + alpha=0.25, |
| 69 | + loss_weight=1.0), |
| 70 | + loss_bbox=dict(type='mmdet.IoULoss', loss_weight=1.0), |
| 71 | + loss_centerness=dict( |
| 72 | + type='mmdet.CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), |
| 73 | + loss_symmetry_ss=dict( |
| 74 | + type='H2RBoxV2ConsistencyLoss', |
| 75 | + use_snap_loss=True, |
| 76 | + loss_rot=dict( |
| 77 | + type='mmdet.SmoothL1Loss', loss_weight=1.0, beta=0.1), |
| 78 | + loss_flp=dict( |
| 79 | + type='mmdet.SmoothL1Loss', loss_weight=0.05, beta=0.1))), |
| 80 | + # training and testing settings |
| 81 | + train_cfg=None, |
| 82 | + test_cfg=dict( |
| 83 | + nms_pre=2000, |
| 84 | + min_bbox_size=0, |
| 85 | + score_thr=0.05, |
| 86 | + nms=dict(type='nms_rotated', iou_threshold=0.1), |
| 87 | + max_per_img=2000)) |
| 88 | + |
| 89 | +# load hbox annotations |
| 90 | +train_pipeline = [ |
| 91 | + dict(type='mmdet.LoadImageFromFile', backend_args={{_base_.backend_args}}), |
| 92 | + dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'), |
| 93 | + # Horizontal GTBox, (x1,y1,x2,y2) |
| 94 | + dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='hbox')), |
| 95 | + # Horizontal GTBox, (x,y,w,h,theta) |
| 96 | + dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')), |
| 97 | + dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True), |
| 98 | + dict( |
| 99 | + type='mmdet.RandomFlip', |
| 100 | + prob=0.75, |
| 101 | + direction=['horizontal', 'vertical', 'diagonal']), |
| 102 | + dict(type='mmdet.PackDetInputs') |
| 103 | +] |
| 104 | + |
| 105 | +train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) |
| 106 | + |
| 107 | +# optimizer |
| 108 | +optim_wrapper = dict( |
| 109 | + optimizer=dict( |
| 110 | + _delete_=True, |
| 111 | + type='AdamW', |
| 112 | + lr=0.00005, |
| 113 | + betas=(0.9, 0.999), |
| 114 | + weight_decay=0.05)) |
| 115 | + |
| 116 | +train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=6) |
0 commit comments