configs/ld/ld_r101_gflv1_r101dcn_fpn_coco_2x.py

_base_ = ['./ld_r18_gflv1_r101_fpn_coco_1x.py']
teacher_ckpt = 'http://download.openmmlab.com/mmdetection/v2.0/gfl/gfl_r101_fpn_dconv_c3-c5_mstrain_2x_coco/gfl_r101_fpn_dconv_c3-c5_mstrain_2x_coco_20200630_102002-134b07df.pth'  # noqa
model = dict(
    pretrained='torchvision://resnet101',
    teacher_config='configs/gfl/gfl_r101_fpn_dconv_c3-c5_mstrain_2x_coco.py',
    teacher_ckpt=teacher_ckpt,
    backbone=dict(
        type='ResNet',
        depth=101,
        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_output',
        num_outs=5))

lr_config = dict(step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=24)
# multi-scale training
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='LoadAnnotations', with_bbox=True),
    dict(
        type='Resize',
        img_scale=[(1333, 480), (1333, 800)],
        multiscale_mode='range',
        keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
data = dict(train=dict(pipeline=train_pipeline))