mirror of
https://github.com/open-mmlab/mmpretrain.git
synced 2025-06-03 14:59:18 +08:00
08dc8c75d3
* remove basehead * add moco series * add byol simclr simsiam * add ut * update configs * add simsiam hook * add and refactor beit * update ut * add cae * update extract_feat * refactor cae * add mae * refactor data preprocessor * update heads * add maskfeat * add milan * add simmim * add mixmim * fix lint * fix ut * fix lint * add eva * add densecl * add barlowtwins * add swav * fix lint * update readtherdocs rst * update docs * update * Decrease UT memory usage * Fix docstring * update DALLEEncoder * Update model docs * refactor dalle encoder * update docstring * fix ut * fix config error * add val_cfg and test_cfg * refactor clip generator * fix lint * pass check * fix ut * add lars * update type of BEiT in configs * Use MMEngine style momentum in EMA. * apply mmpretrain solarize --------- Co-authored-by: mzr1996 <mzr1996@163.com>
59 lines
1.6 KiB
Python
59 lines
1.6 KiB
Python
_base_ = [
|
|
'../_base_/datasets/imagenet_bs32_mocov2.py',
|
|
'../_base_/schedules/imagenet_sgd_coslr_200e.py',
|
|
'../_base_/default_runtime.py',
|
|
]
|
|
|
|
# model settings
|
|
model = dict(
|
|
type='SimSiam',
|
|
backbone=dict(
|
|
type='ResNet',
|
|
depth=50,
|
|
norm_cfg=dict(type='SyncBN'),
|
|
zero_init_residual=True),
|
|
neck=dict(
|
|
type='NonLinearNeck',
|
|
in_channels=2048,
|
|
hid_channels=2048,
|
|
out_channels=2048,
|
|
num_layers=3,
|
|
with_last_bn_affine=False,
|
|
with_avg_pool=True),
|
|
head=dict(
|
|
type='LatentPredictHead',
|
|
loss=dict(type='CosineSimilarityLoss'),
|
|
predictor=dict(
|
|
type='NonLinearNeck',
|
|
in_channels=2048,
|
|
hid_channels=512,
|
|
out_channels=2048,
|
|
with_avg_pool=False,
|
|
with_last_bn=False,
|
|
with_last_bias=True)),
|
|
)
|
|
|
|
# optimizer
|
|
# set base learning rate
|
|
lr = 0.05
|
|
optim_wrapper = dict(
|
|
type='OptimWrapper',
|
|
optimizer=dict(type='SGD', lr=lr, weight_decay=1e-4, momentum=0.9),
|
|
paramwise_cfg=dict(custom_keys={'predictor': dict(fix_lr=True)}))
|
|
|
|
# learning rate scheduler
|
|
param_scheduler = [
|
|
dict(type='CosineAnnealingLR', T_max=100, by_epoch=True, begin=0, end=100)
|
|
]
|
|
|
|
# runtime settings
|
|
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=100)
|
|
default_hooks = dict(
|
|
# only keeps the latest 3 checkpoints
|
|
checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))
|
|
|
|
# additional hooks
|
|
custom_hooks = [
|
|
dict(type='SimSiamHook', priority='HIGH', fix_pred_lr=True, lr=lr)
|
|
]
|