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>
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
_base_ = [
|
|
'../_base_/datasets/imagenet_bs32_simclr.py',
|
|
'../_base_/schedules/imagenet_lars_coslr_200e.py',
|
|
'../_base_/default_runtime.py',
|
|
]
|
|
|
|
# model settings
|
|
model = dict(
|
|
type='SimCLR',
|
|
backbone=dict(
|
|
type='ResNet',
|
|
depth=50,
|
|
norm_cfg=dict(type='SyncBN'),
|
|
zero_init_residual=True),
|
|
neck=dict(
|
|
type='NonLinearNeck', # SimCLR non-linear neck
|
|
in_channels=2048,
|
|
hid_channels=2048,
|
|
out_channels=128,
|
|
num_layers=2,
|
|
with_avg_pool=True),
|
|
head=dict(
|
|
type='ContrastiveHead',
|
|
loss=dict(type='CrossEntropyLoss'),
|
|
temperature=0.1),
|
|
)
|
|
|
|
# optimizer
|
|
optim_wrapper = dict(
|
|
type='OptimWrapper',
|
|
optimizer=dict(type='LARS', lr=0.3, momentum=0.9, weight_decay=1e-6),
|
|
paramwise_cfg=dict(
|
|
custom_keys={
|
|
'bn': dict(decay_mult=0, lars_exclude=True),
|
|
'bias': dict(decay_mult=0, lars_exclude=True),
|
|
# bn layer in ResNet block downsample module
|
|
'downsample.1': dict(decay_mult=0, lars_exclude=True),
|
|
}))
|
|
|
|
# runtime settings
|
|
default_hooks = dict(
|
|
# only keeps the latest 3 checkpoints
|
|
checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))
|
|
|
|
# NOTE: `auto_scale_lr` is for automatically scaling LR
|
|
# based on the actual training batch size.
|
|
auto_scale_lr = dict(base_batch_size=256)
|