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
urhero
Paddle
提交
53580bb4
P
Paddle
项目概览
urhero
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
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
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
0
Issue
0
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
53580bb4
编写于
5月 18, 2021
作者:
L
liuyuhui
提交者:
GitHub
5月 18, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add unit8 for concat (#32850)
上级
bcd40f21
变更
9
隐藏空白更改
内联
并排
Showing
9 changed file
with
26 addition
and
12 deletion
+26
-12
paddle/fluid/operators/concat_op.cc
paddle/fluid/operators/concat_op.cc
+4
-2
paddle/fluid/operators/concat_op.cu.cc
paddle/fluid/operators/concat_op.cu.cc
+4
-2
paddle/fluid/operators/reduce_ops/reduce_mean_op.cc
paddle/fluid/operators/reduce_ops/reduce_mean_op.cc
+4
-1
paddle/fluid/operators/reduce_ops/reduce_mean_op.cu
paddle/fluid/operators/reduce_ops/reduce_mean_op.cu
+2
-1
paddle/fluid/operators/reduce_ops/reduce_mean_op.part.cu
paddle/fluid/operators/reduce_ops/reduce_mean_op.part.cu
+2
-1
paddle/fluid/operators/reduce_ops/reduce_sum_op.cc
paddle/fluid/operators/reduce_ops/reduce_sum_op.cc
+5
-2
paddle/fluid/operators/reduce_ops/reduce_sum_op.cu
paddle/fluid/operators/reduce_ops/reduce_sum_op.cu
+2
-1
paddle/fluid/operators/reduce_ops/reduce_sum_op.part.cu
paddle/fluid/operators/reduce_ops/reduce_sum_op.part.cu
+2
-1
python/paddle/tensor/manipulation.py
python/paddle/tensor/manipulation.py
+1
-1
未找到文件。
paddle/fluid/operators/concat_op.cc
浏览文件 @
53580bb4
...
...
@@ -233,7 +233,8 @@ REGISTER_OP_CPU_KERNEL(
ops
::
ConcatKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int64_t
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CPUDeviceContext
,
paddle
::
platform
::
float16
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
>
);
ops
::
ConcatKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CPUDeviceContext
,
uint8_t
>
);
REGISTER_OP_CPU_KERNEL
(
concat_grad
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
double
>
,
...
...
@@ -242,4 +243,5 @@ REGISTER_OP_CPU_KERNEL(
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int64_t
>
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
paddle
::
platform
::
float16
>
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
>
);
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CPUDeviceContext
,
uint8_t
>
);
paddle/fluid/operators/concat_op.cu.cc
浏览文件 @
53580bb4
...
...
@@ -23,7 +23,8 @@ REGISTER_OP_CUDA_KERNEL(
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
bool
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
plat
::
float16
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int64_t
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int
>
);
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
uint8_t
>
);
REGISTER_OP_CUDA_KERNEL
(
concat_grad
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
double
>
,
...
...
@@ -31,4 +32,5 @@ REGISTER_OP_CUDA_KERNEL(
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
bool
>
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
plat
::
float16
>
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int64_t
>
,
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int
>
);
ops
::
ConcatGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int
>
,
ops
::
ConcatKernel
<
paddle
::
platform
::
CUDADeviceContext
,
uint8_t
>
);
paddle/fluid/operators/reduce_ops/reduce_mean_op.cc
浏览文件 @
53580bb4
...
...
@@ -100,6 +100,8 @@ REGISTER_OPERATOR(reduce_mean_grad, ops::ReduceGradOp,
ops
::
ReduceMeanDoubleGradOpBaseMaker
,
ops
::
ReduceMeanGradNoNeedBufferVarInferer
);
REGISTER_OP_CPU_KERNEL
(
reduce_mean
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
bool
,
ops
::
MeanFunctor
>
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
float
,
ops
::
MeanFunctor
>
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
...
...
@@ -110,5 +112,6 @@ using CPUReduceMeanGradKernel =
ops
::
ReduceGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
T
,
ops
::
MeanGradFunctor
,
true
>
;
REGISTER_OP_CPU_KERNEL
(
reduce_mean_grad
,
CPUReduceMeanGradKernel
<
float
>
,
REGISTER_OP_CPU_KERNEL
(
reduce_mean_grad
,
CPUReduceMeanGradKernel
<
bool
>
,
CPUReduceMeanGradKernel
<
float
>
,
CPUReduceMeanGradKernel
<
double
>
);
paddle/fluid/operators/reduce_ops/reduce_mean_op.cu
浏览文件 @
53580bb4
...
...
@@ -65,5 +65,6 @@ class ReduceMeanKernel : public framework::OpKernel<T> {
}
// namespace operators
}
// namespace paddle
REGISTER_OP_CUDA_KERNEL
(
reduce_mean
,
ops
::
ReduceMeanKernel
<
float
>
,
REGISTER_OP_CUDA_KERNEL
(
reduce_mean
,
ops
::
ReduceMeanKernel
<
bool
>
,
ops
::
ReduceMeanKernel
<
float
>
,
ops
::
ReduceMeanKernel
<
double
>
);
paddle/fluid/operators/reduce_ops/reduce_mean_op.part.cu
浏览文件 @
53580bb4
...
...
@@ -20,5 +20,6 @@ using CUDAReduceMeanGradKernel =
ops
::
ReduceGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
T
,
ops
::
MeanGradFunctor
,
true
>
;
REGISTER_OP_CUDA_KERNEL
(
reduce_mean_grad
,
CUDAReduceMeanGradKernel
<
float
>
,
REGISTER_OP_CUDA_KERNEL
(
reduce_mean_grad
,
CUDAReduceMeanGradKernel
<
bool
>
,
CUDAReduceMeanGradKernel
<
float
>
,
CUDAReduceMeanGradKernel
<
double
>
);
paddle/fluid/operators/reduce_ops/reduce_sum_op.cc
浏览文件 @
53580bb4
...
...
@@ -109,8 +109,10 @@ REGISTER_OPERATOR(reduce_sum_grad, ops::ReduceGradOp,
ops
::
ReduceSumGradNoNeedBufferVarInferer
);
REGISTER_OP_CPU_KERNEL
(
reduce_sum
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
float
,
reduce_sum
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
bool
,
ops
::
SumFunctor
>
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
float
,
ops
::
SumFunctor
>
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
double
,
ops
::
SumFunctor
>
,
ops
::
ReduceKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
,
ops
::
SumFunctor
>
,
...
...
@@ -128,7 +130,8 @@ using CPUReduceSumGradKernel =
ops
::
ReduceSumGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
T
,
ops
::
SumGradFunctor
,
true
>
;
REGISTER_OP_CPU_KERNEL
(
reduce_sum_grad
,
CPUReduceSumGradKernel
<
float
>
,
REGISTER_OP_CPU_KERNEL
(
reduce_sum_grad
,
CPUReduceSumGradKernel
<
bool
>
,
CPUReduceSumGradKernel
<
float
>
,
CPUReduceSumGradKernel
<
double
>
,
CPUReduceSumGradKernel
<
int
>
,
CPUReduceSumGradKernel
<
int64_t
>
,
...
...
paddle/fluid/operators/reduce_ops/reduce_sum_op.cu
浏览文件 @
53580bb4
...
...
@@ -70,7 +70,8 @@ class ReduceSumKernel : public framework::OpKernel<T> {
}
// namespace operators
}
// namespace paddle
REGISTER_OP_CUDA_KERNEL
(
reduce_sum
,
ops
::
ReduceSumKernel
<
float
>
,
REGISTER_OP_CUDA_KERNEL
(
reduce_sum
,
ops
::
ReduceSumKernel
<
bool
>
,
ops
::
ReduceSumKernel
<
float
>
,
ops
::
ReduceSumKernel
<
double
>
,
ops
::
ReduceSumKernel
<
int
>
,
ops
::
ReduceSumKernel
<
int64_t
>
,
ops
::
ReduceSumKernel
<
paddle
::
platform
::
complex64
>
,
...
...
paddle/fluid/operators/reduce_ops/reduce_sum_op.part.cu
浏览文件 @
53580bb4
...
...
@@ -20,7 +20,8 @@ using CUDAReduceSumGradKernel =
ops
::
ReduceGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
T
,
ops
::
SumGradFunctor
,
true
>
;
REGISTER_OP_CUDA_KERNEL
(
reduce_sum_grad
,
CUDAReduceSumGradKernel
<
float
>
,
REGISTER_OP_CUDA_KERNEL
(
reduce_sum_grad
,
CUDAReduceSumGradKernel
<
bool
>
,
CUDAReduceSumGradKernel
<
float
>
,
CUDAReduceSumGradKernel
<
double
>
,
CUDAReduceSumGradKernel
<
int
>
,
CUDAReduceSumGradKernel
<
int64_t
>
,
...
...
python/paddle/tensor/manipulation.py
浏览文件 @
53580bb4
...
...
@@ -80,7 +80,7 @@ def concat(x, axis=0, name=None):
Args:
x(list|tuple): ``x`` is a Tensor list or Tensor tuple which is with data type bool, float16,
float32, float64, int32, int64. All the Tensors in ``x`` must have same data type.
float32, float64, int32, int64
, uint8
. All the Tensors in ``x`` must have same data type.
axis(int|Tensor, optional): Specify the axis to operate on the input Tensors.
It's a scalar with data type int or a Tensor with shape [1] and data type int32
or int64. The effective range is [-R, R), where R is Rank(x). When ``axis < 0``,
...
...
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