mirror of
https://github.com/open-mmlab/mmpretrain.git
synced 2025-06-03 14:59:18 +08:00
18f6bb0b10
* implement the conformer * format code style * format code style * reuse the TransformerEncoderLayer in the vision_transformer.py * Modify variable name * delete unused params * Remove warning info in Conformer head since it already exists in Conformer. * Rename some variables * Add unit tests * Use `getattr` instead of `get_submodule`. * Remove some useless layers * Refactor conformer and add configs * Update configs and add metafile. * Fix unit tests * Update README Co-authored-by: mzr1996 <mzr1996@163.com>
23 lines
752 B
Python
23 lines
752 B
Python
# model settings
|
|
model = dict(
|
|
type='ImageClassifier',
|
|
backbone=dict(
|
|
type='Conformer', arch='tiny', drop_path_rate=0.1, init_cfg=None),
|
|
neck=None,
|
|
head=dict(
|
|
type='ConformerHead',
|
|
num_classes=1000,
|
|
in_channels=[256, 384],
|
|
init_cfg=None,
|
|
loss=dict(
|
|
type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
|
|
cal_acc=False),
|
|
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)
|
|
]))
|