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
OPTHREE
Paddle
提交
09569323
P
Paddle
项目概览
OPTHREE
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
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
1
Issue
1
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
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
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
09569323
编写于
9月 29, 2022
作者:
Z
zhangyikun02
提交者:
GitHub
9月 29, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update docs for ResNetBasicBlock, test=kunlun (#44607)
上级
37bc2d7b
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
101 addition
and
21 deletion
+101
-21
python/paddle/incubate/xpu/resnet_block.py
python/paddle/incubate/xpu/resnet_block.py
+101
-21
未找到文件。
python/paddle/incubate/xpu/resnet_block.py
浏览文件 @
09569323
...
@@ -211,28 +211,108 @@ def resnet_basic_block(x,
...
@@ -211,28 +211,108 @@ def resnet_basic_block(x,
class
ResNetBasicBlock
(
Layer
):
class
ResNetBasicBlock
(
Layer
):
"""
r
"""
ResNetBasicBlock is designed for optimize the performence of the basic unit of ssd resnet block.
ResNetBasicBlock is designed for optimize the performence of the basic unit of ssd resnet block.
The fusion op architecture like this:
If has_shortcut = True, it can calculate 3 Conv2D, 3 BatchNorm and 2 ReLU in one time.
has_shortcut = True: else:
If has_shortcut = False, it can calculate 2 Conv2D, 2 BatchNorm and 2 ReLU in one time. In this
X X
case the shape of output is same with input.
/ /
| | | |
CONV1 | CONV1 |
Args:
| | | |
num_channels (int): The number of input image channel.
BN1 | BN1 |
num_filter (int): The number of filter. It is as same as the output image channel.
| | | |
filter_size (int|list|tuple): The filter size. If filter_size
RELU1 | RELU1 |
is a tuple, it must contain two integers, (filter_size_height,
| | | |
filter_size_width). Otherwise, filter_size_height = filter_size_width =\
CONV2 CONV3 CONV2 |
filter_size.
| | | |
stride (int, optional): The stride size. It means the stride in convolution.
BN2 BN3 BN2 |
If stride is a tuple, it must contain two integers, (stride_height, stride_width).
\ / \ /
Otherwise, stride_height = stride_width = stride. Default: stride = 1.
ADD ADD
act (str, optional): Activation type, if it is set to None, activation is not appended.
| |
Default: None
RELU RELU
momentum (float, optional): The value used for the moving_mean and
| |
moving_var computation. This should be a float number or a Tensor with
Y Y
shape [1] and data type as float32. The updated formula is:
:math:`moving\_mean = moving\_mean * momentum + new\_mean * (1. - momentum)`
:math:`moving\_var = moving\_var * momentum + new\_var * (1. - momentum)`
Default is 0.9.
eps (float, optional): A value added to the denominator for
numerical stability. Default is 1e-5.
data_format (str, optional): Specify the data format of the input, and the data format of the output
will be consistent with that of the input. Now is only support `"NCHW"`, the data is stored in
the order of: `[batch_size, input_channels, input_height, input_width]`.
has_shortcut (bool, optional): Whether to calculate CONV3 and BN3. Default: False.
use_global_stats (bool, optional): Whether to use global mean and
variance. In inference or test mode, set use_global_stats to true
or is_test to true, and the behavior is equivalent.
In train mode, when setting use_global_stats True, the global mean
and variance are also used during train period. Default: False.
is_test (bool, optional): A flag indicating whether it is in
test phrase or not. Default: False.
filter_attr (ParamAttr|None): The parameter attribute for learnable parameters/weights
of conv2d. If it is set to None or one attribute of ParamAttr, conv2d
will create ParamAttr as param_attr. Default: None.
scale_attr (ParamAttr|None): The parameter attribute for Parameter `scale`
of batch_norm. If it is set to None or one attribute of ParamAttr, batch_norm will create ParamAttr
as param_attr, the name of scale can be set in ParamAttr. If the Initializer of the param_attr is not set,
the parameter is initialized with Xavier. Default: None.
bias_attr (ParamAttr|None): The parameter attribute for the bias of batch_norm.
If it is set to None or one attribute of ParamAttr, batch_norm
will create ParamAttr as bias_attr, the name of bias can be set in ParamAttr.
If the Initializer of the bias_attr is not set, the bias is initialized zero.
Default: None.
moving_mean_name (str, optional): The name of moving_mean which store the global Mean. If it
is set to None, batch_norm will save global mean with a random name, otherwise, batch_norm
will save global mean with the string. Default: None.
moving_var_name (str, optional): The name of the moving_variance which store the global Variance.
If it is set to None, batch_norm will save global variance with a random name, otherwise, batch_norm
will save global variance with the string. Default: None.
padding (int, optional): The padding size. It is only spupport padding_height = padding_width = padding.
Default: padding = 0.
dilation (int, optional): The dilation size. It means the spacing between the kernel
points. It is only spupport dilation_height = dilation_width = dilation.
Default: dilation = 1.
trainable_statistics (bool, optional): Whether to calculate mean and var in eval mode. In eval mode, when
setting trainable_statistics True, mean and variance will be calculated by current batch statistics.
Default: False.
find_conv_max (bool, optional): Whether to calculate max value of each conv2d. Default: True.
Returns:
A Tensor representing the ResNetBasicBlock, whose data type is the same with input.
Examples:
.. code-block:: python
# required: xpu
import paddle
from paddle.incubate.xpu.resnet_block import ResNetBasicBlock
ch_in = 4
ch_out = 8
x = paddle.uniform((2, ch_in, 16, 16), dtype='float32', min=-1., max=1.)
resnet_basic_block = ResNetBasicBlock(num_channels1=ch_in,
num_filter1=ch_out,
filter1_size=3,
num_channels2=ch_out,
num_filter2=ch_out,
filter2_size=3,
num_channels3=ch_in,
num_filter3=ch_out,
filter3_size=1,
stride1=1,
stride2=1,
stride3=1,
act='relu',
padding1=1,
padding2=1,
padding3=0,
has_shortcut=True)
out = resnet_basic_block.forward(x)
print(out.shape) # [2, 8, 16, 16]
"""
"""
def
__init__
(
self
,
def
__init__
(
self
,
...
...
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