1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
/* Copyright 2015 The TensorFlow Authors. All Rights Reserved.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
==============================================================================*/
#if !GOOGLE_CUDA
#error This file must only be included when building with Cuda support
#endif
#ifndef TENSORFLOW_CORE_KERNELS_POOLING_OPS_COMMON_GPU_H_
#define TENSORFLOW_CORE_KERNELS_POOLING_OPS_COMMON_GPU_H_
#include <vector>
#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
#include "tensorflow/core/framework/numeric_op.h"
#include "tensorflow/core/framework/op_kernel.h"
#include "tensorflow/core/framework/tensor_shape.h"
#include "tensorflow/core/kernels/avgpooling_op.h"
#include "tensorflow/core/kernels/maxpooling_op.h"
#include "tensorflow/core/kernels/ops_util.h"
#include "tensorflow/core/platform/stream_executor.h"
#include "tensorflow/core/util/padding.h"
#include "tensorflow/core/util/tensor_format.h"
namespace tensorflow {
// A helper class that launch the cudnn pooling forward operations.
template <typename T>
class DnnPoolingOp {
public:
typedef GPUDevice Device;
static void Compute(OpKernelContext* context,
perftools::gputools::dnn::PoolingMode pooling_mode,
const std::vector<int32>& size,
const std::vector<int32>& stride, Padding padding,
TensorFormat data_format, const Tensor& tensor_in,
const TensorShape& tensor_out_shape);
};
// A helper class that launch the cudnn pooling backward operations.
// The original input and output tensors are optional for AvgPoolGrad, but
// mandatory for MaxPoolGrad.
template <typename T>
class DnnPoolingGradOp {
public:
typedef GPUDevice Device;
static void Compute(OpKernelContext* context,
perftools::gputools::dnn::PoolingMode pooling_mode,
const std::vector<int32>& size,
const std::vector<int32>& stride, Padding padding,
TensorFormat data_format, const Tensor* tensor_in,
const Tensor* tensor_out, const Tensor& out_backprop,
const TensorShape& tensor_in_shape);
};
} // namespace tensorflow
#endif // TENSORFLOW_CORE_KERNELS_POOLING_OPS_COMMON_GPU_H_
|
