gliding_vertex_r50_fpn_3x_hrsc.py

_base_ = [
    '../_base_/schedules/schedule_3x.py',
    '../../_base_/default_runtime.py'
]

# default runtime
checkpoint_config = dict(interval=3)

model = dict(
    type='GlidingVertex',
    pretrained='torchvision://resnet50',
    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'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        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='GVRatioRoIHead',
        bbox_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        bbox_head=dict(
            type='GVBBoxHead',
            num_shared_fcs=2,
            roi_feat_size=7,
            in_channels=256,
            fc_out_channels=1024,
            num_classes=1,
            ratio_thr=0.8,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0., 0., 0., 0.],
                target_stds=[0.1, 0.1, 0.2, 0.2]),
            fix_coder=dict(type='GVFixCoder'),
            ratio_coder=dict(type='GVRatioCoder'),
            loss_cls=dict(
                type='CrossEntropyLoss',
                use_sigmoid=False,
                loss_weight=1.0),
            loss_bbox=dict(
                type='SmoothL1Loss', beta=1., loss_weight=1.0),
            loss_fix=dict(
                type='SmoothL1Loss', beta=1./3., loss_weight=1.0),
            loss_ratio=dict(
                type='SmoothL1Loss', beta=1./3., loss_weight=16.0))))
# model training and testing settings
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,
            gpu_assign_thr=200,
            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_across_levels=False,
        nms_pre=2000,
        nms_post=2000,
        max_num=2000,
        nms_thr=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))
test_cfg = dict(
    rpn=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=2000,
        max_num=2000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.05, nms=dict(type='poly_nms', iou_thr=0.1), max_per_img=2000))

# Dataset
dataset_type = 'HRSCDataset'
data_root = 'data/hrsc/'
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='LoadOBBAnnotations', with_bbox=True,
         with_label=True, obb_as_mask=True),
    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
    dict(type='OBBRandomFlip', h_flip_ratio=0.5, v_flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='RandomOBBRotate', rotate_after_flip=True,
         angles=(0, 0), vert_rate=0.5),
    dict(type='Pad', size_divisor=32),
    dict(type='Mask2OBB', obb_type='poly'),
    dict(type='OBBDefaultFormatBundle'),
    dict(type='OBBCollect', keys=['img', 'gt_bboxes', 'gt_obboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipRotateAug',
        img_scale=[(1333, 800)],
        h_flip=False,
        v_flip=False,
        rotate=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='OBBRandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='RandomOBBRotate', rotate_after_flip=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='OBBCollect', keys=['img']),
        ])
]

# does evaluation while training
# uncomments it  when you need evaluate every epoch
# data = dict(
    # samples_per_gpu=2,
    # workers_per_gpu=4,
    # train=dict(
        # type=dataset_type,
        # imgset=data_root + 'ImageSets/train.txt',
        # ann_file=data_root + 'FullDataSet/Annotations/',
        # img_prefix=data_root + 'FullDataSet/AllImages/',
        # pipeline=train_pipeline),
    # val=dict(
        # type=dataset_type,
        # imgset=data_root + 'ImageSets/val.txt',
        # ann_file=data_root + 'FullDataSet/Annotations/',
        # img_prefix=data_root + 'FullDataSet/AllImages/',
        # pipeline=test_pipeline),
    # test=dict(
        # type=dataset_type,
        # imgset=data_root + 'ImageSets/val.txt',
        # ann_file=data_root + 'FullDataSet/Annotations/',
        # img_prefix=data_root + 'FullDataSet/AllImages/',
        # pipeline=test_pipeline))
# evaluation = dict(metric='mAP')

# disable evluation, only need train and test
# uncomments it when use trainval as train
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=4,
    train=dict(
        type=dataset_type,
        imgset=data_root + 'ImageSets/trainval.txt',
        ann_file=data_root + 'FullDataSet/Annotations/',
        img_prefix=data_root + 'FullDataSet/AllImages/',
        pipeline=train_pipeline),
    test=dict(
        type=dataset_type,
        imgset=data_root + 'ImageSets/test.txt',
        ann_file=data_root + 'FullDataSet/Annotations/',
        img_prefix=data_root + 'FullDataSet/AllImages/',
        pipeline=test_pipeline))
evaluation = None