mmdetection/configs/dyhead/atss_r50-caffe_fpn_dyhead_1x_coco.py

_base_ = [
    '../_base_/datasets/coco_detection.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
    type='ATSS',
    data_preprocessor=dict(
        type='DetDataPreprocessor',
        mean=[103.530, 116.280, 123.675],
        std=[1.0, 1.0, 1.0],
        bgr_to_rgb=False,
        pad_size_divisor=128),
    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=False),
        norm_eval=True,
        style='caffe',
        init_cfg=dict(
            type='Pretrained',
            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
    neck=[
        dict(
            type='FPN',
            in_channels=[256, 512, 1024, 2048],
            out_channels=256,
            start_level=1,
            add_extra_convs='on_output',
            num_outs=5),
        dict(
            type='DyHead',
            in_channels=256,
            out_channels=256,
            num_blocks=6,
            # disable zero_init_offset to follow official implementation
            zero_init_offset=False)
    ],
    bbox_head=dict(
        type='ATSSHead',
        num_classes=80,
        in_channels=256,
        pred_kernel_size=1,  # follow DyHead official implementation
        stacked_convs=0,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            ratios=[1.0],
            octave_base_scale=8,
            scales_per_octave=1,
            strides=[8, 16, 32, 64, 128],
            center_offset=0.5),  # follow DyHead official implementation
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[.0, .0, .0, .0],
            target_stds=[0.1, 0.1, 0.2, 0.2]),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
        loss_centerness=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
    # training and testing settings
    train_cfg=dict(
        assigner=dict(type='ATSSAssigner', topk=9),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.6),
        max_per_img=100))

# optimizer
optim_wrapper = dict(optimizer=dict(lr=0.01))

train_pipeline = [
    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', scale=(1333, 800), keep_ratio=True, backend='pillow'),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
    dict(type='Resize', scale=(1333, 800), keep_ratio=True, backend='pillow'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                   'scale_factor'))
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = val_dataloader