dff7a968a3
* fix patch_embed and pos_embed mismatch error * add docstring * update unittest * use downsampled image shape * use tuple * remove unused parameters and add doc * fix init weights function * revise docstring * Update vit.py If -> Whether * fix lint Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
# model settings
|
|
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
|
model = dict(
|
|
type='EncoderDecoder',
|
|
pretrained='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_224-80ecf9dd.pth', # noqa
|
|
backbone=dict(
|
|
type='VisionTransformer',
|
|
img_size=(512, 512),
|
|
patch_size=16,
|
|
in_channels=3,
|
|
embed_dims=768,
|
|
num_layers=12,
|
|
num_heads=12,
|
|
mlp_ratio=4,
|
|
out_indices=(2, 5, 8, 11),
|
|
qkv_bias=True,
|
|
drop_rate=0.0,
|
|
attn_drop_rate=0.0,
|
|
drop_path_rate=0.0,
|
|
with_cls_token=True,
|
|
norm_cfg=dict(type='LN', eps=1e-6),
|
|
act_cfg=dict(type='GELU'),
|
|
norm_eval=False,
|
|
interpolate_mode='bicubic'),
|
|
neck=dict(
|
|
type='MultiLevelNeck',
|
|
in_channels=[768, 768, 768, 768],
|
|
out_channels=768,
|
|
scales=[4, 2, 1, 0.5]),
|
|
decode_head=dict(
|
|
type='UPerHead',
|
|
in_channels=[768, 768, 768, 768],
|
|
in_index=[0, 1, 2, 3],
|
|
pool_scales=(1, 2, 3, 6),
|
|
channels=512,
|
|
dropout_ratio=0.1,
|
|
num_classes=19,
|
|
norm_cfg=norm_cfg,
|
|
align_corners=False,
|
|
loss_decode=dict(
|
|
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
|
auxiliary_head=dict(
|
|
type='FCNHead',
|
|
in_channels=768,
|
|
in_index=3,
|
|
channels=256,
|
|
num_convs=1,
|
|
concat_input=False,
|
|
dropout_ratio=0.1,
|
|
num_classes=19,
|
|
norm_cfg=norm_cfg,
|
|
align_corners=False,
|
|
loss_decode=dict(
|
|
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
|
# model training and testing settings
|
|
train_cfg=dict(),
|
|
test_cfg=dict(mode='whole')) # yapf: disable
|