_base_ = [
    '../_base_/models/retinanet_r50_fpn.py',
    '../_base_/datasets/openimages_detection.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]

model = dict(bbox_head=dict(num_classes=601))

# learning rate
param_scheduler = [
    dict(
        type='LinearLR',
        start_factor=1.0 / 64,
        by_epoch=False,
        begin=0,
        end=26000),
    dict(
        type='MultiStepLR',
        begin=0,
        end=12,
        by_epoch=True,
        milestones=[8, 11],
        gamma=0.1)
]

# optimizer
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='SGD', lr=0.08, momentum=0.9, weight_decay=0.0001),
    clip_grad=dict(max_norm=35, norm_type=2))

# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (32 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=64)