File: max_pool_with_index_gpu.h

package info (click to toggle)
pytorch 1.13.1%2Bdfsg-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 139,252 kB
  • sloc: cpp: 1,100,274; python: 706,454; ansic: 83,052; asm: 7,618; java: 3,273; sh: 2,841; javascript: 612; makefile: 323; xml: 269; ruby: 185; yacc: 144; objc: 68; lex: 44
file content (46 lines) | stat: -rw-r--r-- 1,155 bytes parent folder | download | duplicates (2)
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
#pragma once

#include <cfloat>
#include "caffe2/core/context.h"
#include "caffe2/core/context_gpu.h"
#include "caffe2/core/logging.h"
#include "caffe2/core/operator.h"
#include "caffe2/operators/conv_pool_op_base.h"
#include "caffe2/operators/pool_op.h"
#include "caffe2/utils/math.h"

namespace caffe2 {

class MaxPoolWithIndexOp final : public ConvPoolOpBase<CUDAContext> {
 public:
  USE_CONV_POOL_BASE_FUNCTIONS(CUDAContext);
  MaxPoolWithIndexOp(const OperatorDef& operator_def, Workspace* ws)
      : ConvPoolOpBase<CUDAContext>(operator_def, ws) {}
  ~MaxPoolWithIndexOp() {}

  template <typename T>
  bool DoRunWithType();

  bool RunOnDevice() override;

  // Input: X
  // Output: Y, mask
};

class MaxPoolWithIndexGradientOp final : public ConvPoolOpBase<CUDAContext> {
 public:
  USE_CONV_POOL_BASE_FUNCTIONS(CUDAContext);
  MaxPoolWithIndexGradientOp(const OperatorDef& operator_def, Workspace* ws)
      : ConvPoolOpBase<CUDAContext>(operator_def, ws) {}
  ~MaxPoolWithIndexGradientOp() {}

  template <typename T>
  bool DoRunWithType();

  bool RunOnDevice() override;

  // Input: X, dY, mask
  // Output: dX
};

}; // namespace caffe2