mmdetection/configs/foveabox/fovea_r50_fpn_4xb4-1x_coco.py

_base_ = [
    '../_base_/datasets/coco_detection.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
# model settings
model = dict(
    type='FOVEA',
    data_preprocessor=dict(
        type='DetDataPreprocessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        bgr_to_rgb=True,
        pad_size_divisor=32),
    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',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        num_outs=5,
        add_extra_convs='on_input'),
    bbox_head=dict(
        type='FoveaHead',
        num_classes=80,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        strides=[8, 16, 32, 64, 128],
        base_edge_list=[16, 32, 64, 128, 256],
        scale_ranges=((1, 64), (32, 128), (64, 256), (128, 512), (256, 2048)),
        sigma=0.4,
        with_deform=False,
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=1.50,
            alpha=0.4,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
    # training and testing settings
    train_cfg=dict(),
    test_cfg=dict(
        nms_pre=1000,
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.5),
        max_per_img=100))
train_dataloader = dict(batch_size=4, num_workers=4)
# optimizer
optim_wrapper = dict(
    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001))