Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
byol_resnet50_16xb256-coslr-200e_in1k.py 1.63 KB
Newer Older
renzhc's avatar
upload mmpretrain  
renzhc committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60 
_base_ = [
    '../_base_/datasets/imagenet_bs32_byol.py',
    '../_base_/schedules/imagenet_lars_coslr_200e.py',
    '../_base_/default_runtime.py',
]

train_dataloader = dict(batch_size=256)

# model settings
model = dict(
    type='BYOL',
    base_momentum=0.01,
    backbone=dict(
        type='ResNet',
        depth=50,
        norm_cfg=dict(type='SyncBN'),
        zero_init_residual=False),
    neck=dict(
        type='NonLinearNeck',
        in_channels=2048,
        hid_channels=4096,
        out_channels=256,
        num_layers=2,
        with_bias=True,
        with_last_bn=False,
        with_avg_pool=True),
    head=dict(
        type='LatentPredictHead',
        predictor=dict(
            type='NonLinearNeck',
            in_channels=256,
            hid_channels=4096,
            out_channels=256,
            num_layers=2,
            with_bias=True,
            with_last_bn=False,
            with_avg_pool=False),
        loss=dict(type='CosineSimilarityLoss')),
)

# optimizer
optimizer = dict(type='LARS', lr=4.8, momentum=0.9, weight_decay=1e-6)
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=optimizer,
    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(checkpoint=dict(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=4096)