cyclic_20e.py

# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import CosineAnnealingLR
from mmengine.optim.scheduler.momentum_scheduler import CosineAnnealingMomentum
from torch.optim.adamw import AdamW

# For nuScenes dataset, we usually evaluate the model at the end of training.
# Since the models are trained by 24 epochs by default, we set evaluation
# interval to be 20. Please change the interval accordingly if you do not
# use a default schedule.
# optimizer
lr = 1e-4
# This schedule is mainly used by models on nuScenes dataset
# max_norm=10 is better for SECOND
optim_wrapper = dict(
    type=OptimWrapper,
    optimizer=dict(type=AdamW, lr=lr, weight_decay=0.01),
    clip_grad=dict(max_norm=35, norm_type=2))
# learning rate
param_scheduler = [
    # learning rate scheduler
    # During the first 8 epochs, learning rate increases from 0 to lr * 10
    # during the next 12 epochs, learning rate decreases from lr * 10 to
    # lr * 1e-4
    dict(
        type=CosineAnnealingLR,
        T_max=8,
        eta_min=lr * 10,
        begin=0,
        end=8,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type=CosineAnnealingLR,
        T_max=12,
        eta_min=lr * 1e-4,
        begin=8,
        end=20,
        by_epoch=True,
        convert_to_iter_based=True),
    # momentum scheduler
    # During the first 8 epochs, momentum increases from 0 to 0.85 / 0.95
    # during the next 12 epochs, momentum increases from 0.85 / 0.95 to 1
    dict(
        type=CosineAnnealingMomentum,
        T_max=8,
        eta_min=0.85 / 0.95,
        begin=0,
        end=8,
        by_epoch=True,
        convert_to_iter_based=True),
    dict(
        type=CosineAnnealingMomentum,
        T_max=12,
        eta_min=1,
        begin=8,
        end=20,
        by_epoch=True,
        convert_to_iter_based=True)
]

# runtime settings
train_cfg = dict(by_epoch=True, max_epochs=20, val_interval=20)
val_cfg = dict()
test_cfg = dict()

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (4 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=32)