retinanet_obb_r50_fpn_3x_hrsc.py

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

# default runtime
checkpoint_config = dict(interval=3)

# lr schedule
optimizer = dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001)
# RetinaNet nms is slow in early stage, disable every epoch evaluation
evaluation = None

model = dict(
    type='RetinaNetOBB',
    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,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5),
    bbox_head=dict(
        type='OBBRetinaHead',
        num_classes=1,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        anchor_generator=dict(
            type='Theta0AnchorGenerator',
            octave_base_scale=4,
            scales_per_octave=3,
            ratios=[0.5, 1.0, 2.0],
            strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type='OBB2OBBDeltaXYWHTCoder',
            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='L1Loss', loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
    assigner=dict(
        type='MaxIoUAssigner',
        pos_iou_thr=0.5,
        neg_iou_thr=0.4,
        min_pos_iou=0,
        gpu_assign_thr=-1,
        ignore_iof_thr=-1,
        iou_calculator=dict(
            type='OBBOverlaps')),
    allowed_border=-1,
    pos_weight=-1,
    debug=False)
test_cfg = dict(
    nms_pre=2000,
    min_bbox_size=0,
    score_thr=0.05,
    nms=dict(type='obb_nms', iou_thr=0.1),
    max_per_img=2000)