Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
stoneliu1981
pytorch-image-models
提交
bda8ab01
P
pytorch-image-models
项目概览
stoneliu1981
/
pytorch-image-models
与 Fork 源项目一致
从无法访问的项目Fork
通知
7
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
DevOps
流水线
流水线任务
计划
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
pytorch-image-models
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
DevOps
DevOps
流水线
流水线任务
计划
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
流水线任务
提交
Issue看板
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
bda8ab01
编写于
5月 31, 2021
作者:
R
Ross Wightman
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
上级
a27f4aec
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
5 addition
and
7 deletion
+5
-7
timm/models/layers/selective_kernel.py
timm/models/layers/selective_kernel.py
+2
-4
timm/models/sknet.py
timm/models/sknet.py
+3
-3
未找到文件。
timm/models/layers/selective_kernel.py
浏览文件 @
bda8ab01
...
@@ -49,7 +49,7 @@ class SelectiveKernelAttn(nn.Module):
...
@@ -49,7 +49,7 @@ class SelectiveKernelAttn(nn.Module):
class
SelectiveKernel
(
nn
.
Module
):
class
SelectiveKernel
(
nn
.
Module
):
def
__init__
(
self
,
in_channels
,
out_channels
=
None
,
kernel_size
=
None
,
stride
=
1
,
dilation
=
1
,
groups
=
1
,
def
__init__
(
self
,
in_channels
,
out_channels
=
None
,
kernel_size
=
None
,
stride
=
1
,
dilation
=
1
,
groups
=
1
,
rd_ratio
=
1.
/
16
,
rd_channels
=
None
,
min_rd_channels
=
32
,
rd_divisor
=
8
,
keep_3x3
=
True
,
split_input
=
True
,
rd_ratio
=
1.
/
16
,
rd_channels
=
None
,
rd_divisor
=
8
,
keep_3x3
=
True
,
split_input
=
True
,
drop_block
=
None
,
act_layer
=
nn
.
ReLU
,
norm_layer
=
nn
.
BatchNorm2d
,
aa_layer
=
None
):
drop_block
=
None
,
act_layer
=
nn
.
ReLU
,
norm_layer
=
nn
.
BatchNorm2d
,
aa_layer
=
None
):
""" Selective Kernel Convolution Module
""" Selective Kernel Convolution Module
...
@@ -68,7 +68,6 @@ class SelectiveKernel(nn.Module):
...
@@ -68,7 +68,6 @@ class SelectiveKernel(nn.Module):
dilation (int): dilation for module as a whole, impacts dilation of each branch
dilation (int): dilation for module as a whole, impacts dilation of each branch
groups (int): number of groups for each branch
groups (int): number of groups for each branch
rd_ratio (int, float): reduction factor for attention features
rd_ratio (int, float): reduction factor for attention features
min_rd_channels (int): minimum attention feature channels
keep_3x3 (bool): keep all branch convolution kernels as 3x3, changing larger kernels for dilations
keep_3x3 (bool): keep all branch convolution kernels as 3x3, changing larger kernels for dilations
split_input (bool): split input channels evenly across each convolution branch, keeps param count lower,
split_input (bool): split input channels evenly across each convolution branch, keeps param count lower,
can be viewed as grouping by path, output expands to module out_channels count
can be viewed as grouping by path, output expands to module out_channels count
...
@@ -103,8 +102,7 @@ class SelectiveKernel(nn.Module):
...
@@ -103,8 +102,7 @@ class SelectiveKernel(nn.Module):
ConvBnAct
(
in_channels
,
out_channels
,
kernel_size
=
k
,
dilation
=
d
,
**
conv_kwargs
)
ConvBnAct
(
in_channels
,
out_channels
,
kernel_size
=
k
,
dilation
=
d
,
**
conv_kwargs
)
for
k
,
d
in
zip
(
kernel_size
,
dilation
)])
for
k
,
d
in
zip
(
kernel_size
,
dilation
)])
attn_channels
=
rd_channels
or
make_divisible
(
attn_channels
=
rd_channels
or
make_divisible
(
out_channels
*
rd_ratio
,
divisor
=
rd_divisor
)
out_channels
*
rd_ratio
,
min_value
=
min_rd_channels
,
divisor
=
rd_divisor
)
self
.
attn
=
SelectiveKernelAttn
(
out_channels
,
self
.
num_paths
,
attn_channels
)
self
.
attn
=
SelectiveKernelAttn
(
out_channels
,
self
.
num_paths
,
attn_channels
)
self
.
drop_block
=
drop_block
self
.
drop_block
=
drop_block
...
...
timm/models/sknet.py
浏览文件 @
bda8ab01
...
@@ -153,7 +153,7 @@ def skresnet18(pretrained=False, **kwargs):
...
@@ -153,7 +153,7 @@ def skresnet18(pretrained=False, **kwargs):
Different from configs in Select Kernel paper or "Compounding the Performance Improvements..." this
Different from configs in Select Kernel paper or "Compounding the Performance Improvements..." this
variation splits the input channels to the selective convolutions to keep param count down.
variation splits the input channels to the selective convolutions to keep param count down.
"""
"""
sk_kwargs
=
dict
(
min_rd_channels
=
16
,
rd_ratio
=
1
/
8
,
split_input
=
True
)
sk_kwargs
=
dict
(
rd_ratio
=
1
/
8
,
rd_divisor
=
16
,
split_input
=
True
)
model_args
=
dict
(
model_args
=
dict
(
block
=
SelectiveKernelBasic
,
layers
=
[
2
,
2
,
2
,
2
],
block_args
=
dict
(
sk_kwargs
=
sk_kwargs
),
block
=
SelectiveKernelBasic
,
layers
=
[
2
,
2
,
2
,
2
],
block_args
=
dict
(
sk_kwargs
=
sk_kwargs
),
zero_init_last_bn
=
False
,
**
kwargs
)
zero_init_last_bn
=
False
,
**
kwargs
)
...
@@ -167,7 +167,7 @@ def skresnet34(pretrained=False, **kwargs):
...
@@ -167,7 +167,7 @@ def skresnet34(pretrained=False, **kwargs):
Different from configs in Select Kernel paper or "Compounding the Performance Improvements..." this
Different from configs in Select Kernel paper or "Compounding the Performance Improvements..." this
variation splits the input channels to the selective convolutions to keep param count down.
variation splits the input channels to the selective convolutions to keep param count down.
"""
"""
sk_kwargs
=
dict
(
min_rd_channels
=
16
,
rd_ratio
=
1
/
8
,
split_input
=
True
)
sk_kwargs
=
dict
(
rd_ratio
=
1
/
8
,
rd_divisor
=
16
,
split_input
=
True
)
model_args
=
dict
(
model_args
=
dict
(
block
=
SelectiveKernelBasic
,
layers
=
[
3
,
4
,
6
,
3
],
block_args
=
dict
(
sk_kwargs
=
sk_kwargs
),
block
=
SelectiveKernelBasic
,
layers
=
[
3
,
4
,
6
,
3
],
block_args
=
dict
(
sk_kwargs
=
sk_kwargs
),
zero_init_last_bn
=
False
,
**
kwargs
)
zero_init_last_bn
=
False
,
**
kwargs
)
...
@@ -207,7 +207,7 @@ def skresnext50_32x4d(pretrained=False, **kwargs):
...
@@ -207,7 +207,7 @@ def skresnext50_32x4d(pretrained=False, **kwargs):
"""Constructs a Select Kernel ResNeXt50-32x4d model. This should be equivalent to
"""Constructs a Select Kernel ResNeXt50-32x4d model. This should be equivalent to
the SKNet-50 model in the Select Kernel Paper
the SKNet-50 model in the Select Kernel Paper
"""
"""
sk_kwargs
=
dict
(
min_rd_channels
=
32
,
rd_ratio
=
1
/
16
,
split_input
=
False
)
sk_kwargs
=
dict
(
rd_ratio
=
1
/
16
,
rd_divisor
=
32
,
split_input
=
False
)
model_args
=
dict
(
model_args
=
dict
(
block
=
SelectiveKernelBottleneck
,
layers
=
[
3
,
4
,
6
,
3
],
cardinality
=
32
,
base_width
=
4
,
block
=
SelectiveKernelBottleneck
,
layers
=
[
3
,
4
,
6
,
3
],
cardinality
=
32
,
base_width
=
4
,
block_args
=
dict
(
sk_kwargs
=
sk_kwargs
),
zero_init_last_bn
=
False
,
**
kwargs
)
block_args
=
dict
(
sk_kwargs
=
sk_kwargs
),
zero_init_last_bn
=
False
,
**
kwargs
)
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录