Spaces:
Running
Running
File size: 1,843 Bytes
28c256d |
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 61 62 63 64 65 66 67 68 69 70 71 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
_base_ = [
'mmpretrain::_base_/datasets/imagenet_bs256_rsb_a12.py',
'mmpretrain::_base_/schedules/imagenet_bs2048_rsb.py',
'mmpretrain::_base_/default_runtime.py'
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='mmdet.CSPNeXt',
arch='P5',
out_indices=(4, ),
expand_ratio=0.5,
deepen_factor=0.33,
widen_factor=0.5,
channel_attention=True,
norm_cfg=dict(type='BN'),
act_cfg=dict(type='mmdet.SiLU')),
neck=dict(type='GlobalAveragePooling'),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=512,
loss=dict(
type='LabelSmoothLoss',
label_smooth_val=0.1,
mode='original',
loss_weight=1.0),
topk=(1, 5)),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.2),
dict(type='CutMix', alpha=1.0)
]))
# dataset settings
train_dataloader = dict(sampler=dict(type='RepeatAugSampler', shuffle=True))
# schedule settings
optim_wrapper = dict(
optimizer=dict(weight_decay=0.01),
paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.),
)
param_scheduler = [
# warm up learning rate scheduler
dict(
type='LinearLR',
start_factor=0.0001,
by_epoch=True,
begin=0,
end=5,
# update by iter
convert_to_iter_based=True),
# main learning rate scheduler
dict(
type='CosineAnnealingLR',
T_max=595,
eta_min=1.0e-6,
by_epoch=True,
begin=5,
end=600)
]
train_cfg = dict(by_epoch=True, max_epochs=600)
|