Pikaliov/DCN_custom_op
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

birth

Browse Source
This commit is contained in:
Yuwen Xiong
2024-01-16 00:22:22 +08:00
commit 7d59305b5f
288 changed files with 41101 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
segmentation/configs/_base_/models/mask2former_beit.py Normal file
View File

@@ -0,0 +1,138 @@
# model_cfg
num_things_classes = 100
num_stuff_classes = 50
num_classes = num_things_classes + num_stuff_classes
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoderMask2Former',
pretrained=None,
backbone=dict(
type='XCiT',
patch_size=16,
embed_dim=384,
depth=12,
num_heads=8,
mlp_ratio=4,
qkv_bias=True,
use_abs_pos_emb=True,
use_rel_pos_bias=False,
),
decode_head=dict(
type='Mask2FormerHead',
in_channels=[256, 512, 1024, 2048], # pass to pixel_decoder inside
# strides=[4, 8, 16, 32],
feat_channels=256,
out_channels=256,
in_index=[0, 1, 2, 3],
num_things_classes=num_things_classes,
num_stuff_classes=num_stuff_classes,
num_queries=100,
num_transformer_feat_level=3,
pixel_decoder=dict(
type='MSDeformAttnPixelDecoder',
num_outs=3,
norm_cfg=dict(type='GN', num_groups=32),
act_cfg=dict(type='ReLU'),
encoder=dict(
type='DetrTransformerEncoder',
num_layers=6,
transformerlayers=dict(
type='BaseTransformerLayer',
attn_cfgs=dict(
type='MultiScaleDeformableAttention',
embed_dims=256,
num_heads=8,
num_levels=3,
num_points=4,
im2col_step=64,
dropout=0.0,
batch_first=False,
norm_cfg=None,
init_cfg=None),
ffn_cfgs=dict(
type='FFN',
embed_dims=256,
feedforward_channels=1024,
num_fcs=2,
ffn_drop=0.0,
act_cfg=dict(type='ReLU', inplace=True)),
operation_order=('self_attn', 'norm', 'ffn', 'norm')),
init_cfg=None),
positional_encoding=dict(
type='SinePositionalEncoding', num_feats=128, normalize=True),
init_cfg=None),
enforce_decoder_input_project=False,
positional_encoding=dict(
type='SinePositionalEncoding', num_feats=128, normalize=True),
transformer_decoder=dict(
type='DetrTransformerDecoder',
return_intermediate=True,
num_layers=9,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=dict(
type='MultiheadAttention',
embed_dims=256,
num_heads=8,
attn_drop=0.0,
proj_drop=0.0,
dropout_layer=None,
batch_first=False),
ffn_cfgs=dict(
embed_dims=256,
feedforward_channels=2048,
num_fcs=2,
act_cfg=dict(type='ReLU', inplace=True),
ffn_drop=0.0,
dropout_layer=None,
add_identity=True),
feedforward_channels=2048,
operation_order=('cross_attn', 'norm', 'self_attn', 'norm',
'ffn', 'norm')),
init_cfg=None),
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=2.0,
reduction='mean',
class_weight=[1.0] * num_classes + [0.1]),
loss_mask=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
reduction='mean',
loss_weight=5.0),
loss_dice=dict(
type='DiceLoss',
use_sigmoid=True,
activate=True,
reduction='mean',
naive_dice=True,
eps=1.0,
loss_weight=5.0)),
train_cfg=dict(
num_points=12544,
oversample_ratio=3.0,
importance_sample_ratio=0.75,
assigner=dict(
type='MaskHungarianAssigner',
cls_cost=dict(type='ClassificationCost', weight=2.0),
mask_cost=dict(
type='CrossEntropyLossCost', weight=5.0, use_sigmoid=True),
dice_cost=dict(
type='DiceCost', weight=5.0, pred_act=True, eps=1.0)),
sampler=dict(type='MaskPseudoSampler')),
test_cfg=dict(
panoptic_on=True,
# For now, the dataset does not support
# evaluating semantic segmentation metric.
semantic_on=False,
instance_on=True,
# max_per_image is for instance segmentation.
max_per_image=100,
iou_thr=0.8,
# In Mask2Former's panoptic postprocessing,
# it will filter mask area where score is less than 0.5 .
filter_low_score=True),
init_cfg=None)
# find_unused_parameters = True

34
segmentation/configs/_base_/models/segformer_mit-b0.py Normal file
View File

@@ -0,0 +1,34 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained=None,
backbone=dict(
type='MixVisionTransformer',
in_channels=3,
embed_dims=32,
num_stages=4,
num_layers=[2, 2, 2, 2],
num_heads=[1, 2, 5, 8],
patch_sizes=[7, 3, 3, 3],
sr_ratios=[8, 4, 2, 1],
out_indices=(0, 1, 2, 3),
mlp_ratio=4,
qkv_bias=True,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.1),
decode_head=dict(
type='SegformerHead',
in_channels=[32, 64, 160, 256],
in_index=[0, 1, 2, 3],
channels=256,
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)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

46
segmentation/configs/_base_/models/upernet_convnext.py Normal file
View File

@@ -0,0 +1,46 @@
norm_cfg = dict(type='SyncBN', requires_grad=True)
custom_imports = dict(imports='mmcls.models', allow_failed_imports=False)
# checkpoint_file = 'https://download.openmmlab.com/mmclassification/v0/convnext/downstream/convnext-base_3rdparty_32xb128-noema_in1k_20220301-2a0ee547.pth' # noqa
model = dict(
type='EncoderDecoder',
pretrained=None,
backbone=dict(
type='mmcls.ConvNeXt',
arch='base',
norm_cfg=dict(type='LN2dv2', eps=1e-6),
out_indices=[0, 1, 2, 3],
drop_path_rate=0.4,
layer_scale_init_value=1.0,
gap_before_final_norm=False,
# init_cfg=dict(
# type='Pretrained', checkpoint=checkpoint_file,
# prefix='backbone.')
),
decode_head=dict(
type='UPerHead',
in_channels=[128, 256, 512, 1024],
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=384,
in_index=2,
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'))

44
segmentation/configs/_base_/models/upernet_r50.py Normal file
View File

@@ -0,0 +1,44 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained='open-mmlab://resnet50_v1c',
backbone=dict(
type='ResNetV1c',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 1, 1),
strides=(1, 2, 2, 2),
norm_cfg=norm_cfg,
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='UPerHead',
in_channels=[256, 512, 1024, 2048],
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=1024,
in_index=2,
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'))

54
segmentation/configs/_base_/models/upernet_swin.py Normal file
View File

@@ -0,0 +1,54 @@
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
backbone_norm_cfg = dict(type='LN', requires_grad=True)
model = dict(
type='EncoderDecoder',
pretrained=None,
backbone=dict(
type='SwinTransformer',
pretrain_img_size=224,
embed_dims=96,
patch_size=4,
window_size=7,
mlp_ratio=4,
depths=[2, 2, 6, 2],
num_heads=[3, 6, 12, 24],
strides=(4, 2, 2, 2),
out_indices=(0, 1, 2, 3),
qkv_bias=True,
qk_scale=None,
patch_norm=True,
drop_rate=0.,
attn_drop_rate=0.,
drop_path_rate=0.3,
use_abs_pos_embed=False,
act_cfg=dict(type='GELU'),
norm_cfg=backbone_norm_cfg),
decode_head=dict(
type='UPerHead',
in_channels=[96, 192, 384, 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=384,
in_index=2,
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'))