Mmdetection: how to set the configurations for 2x?

[Hwang64]

Very nice job!!
From the Model Zoo, the lr_schd configuration for some results are 2x, the readme have said that:
"We adopt the same training schedules as Detectron. 1x indicates 12 epochs and 2x indicates 24 epochs,"
So the configurations for 1x for faster_rcnn_r101_fpn_1x are:
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
])
total_epochs = 12

if i want to train 2x(faster_rcnn_r101_fpn_2x), what are configurations? I wonder whether the following configurations are correct (change the total epochs and the lr_steps)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 22])
checkpoint_config = dict(interval=1)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
])
total_epochs = 24

looking forward for your reply~~

[chenxu93]

yes, it is correct