mmclassification/configs/_base_/models/mvit/mvitv2-base.py

20 lines
688 B
Python

model = dict(
type='ImageClassifier',
backbone=dict(type='MViT', arch='base', drop_path_rate=0.3),
neck=dict(type='GlobalAveragePooling'),
head=dict(
type='LinearClsHead',
in_channels=768,
num_classes=1000,
loss=dict(
type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
),
init_cfg=[
dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
],
train_cfg=dict(augments=[
dict(type='BatchMixup', alpha=0.8, num_classes=1000, prob=0.5),
dict(type='BatchCutMix', alpha=1.0, num_classes=1000, prob=0.5)
]))