_base_ = ['./ld_r18-gflv1-r101_fpn_1x_coco.py']
teacher_ckpt = 'https://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(
    teacher_config='configs/gfl/gfl_r101-dconv-c3-c5_fpn_ms-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',
        init_cfg=dict(type='Pretrained',
                      checkpoint='torchvision://resnet101')),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_output',
        num_outs=5))

max_epochs = 24
param_scheduler = [
    dict(
        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
    dict(
        type='MultiStepLR',
        begin=0,
        end=max_epochs,
        by_epoch=True,
        milestones=[16, 22],
        gamma=0.1)
]
train_cfg = dict(max_epochs=max_epochs)

# multi-scale training
train_pipeline = [
    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='RandomResize', scale=[(1333, 480), (1333, 800)],
        keep_ratio=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs')
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))