File: roi_align_common.h

package info (click to toggle)
pytorch-vision 0.21.0-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 20,228 kB
  • sloc: python: 65,904; cpp: 11,406; ansic: 2,459; java: 550; sh: 265; xml: 79; objc: 56; makefile: 33
file content (128 lines) | stat: -rw-r--r-- 3,461 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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
#pragma once

#include <ATen/ATen.h>

namespace vision {
namespace ops {
namespace detail {

template <typename T>
struct PreCalc {
  int pos1;
  int pos2;
  int pos3;
  int pos4;
  T w1;
  T w2;
  T w3;
  T w4;
};

// This helper computes the interpolation weights (w1, w2...) for every sampling
// point of a given box. There are pool_height * pool_width * roi_bin_grid_h *
// roi_bin_grid_w such sampling points.
//
// The weights (w1, w2...) are computed as the areas in this figure:
// https://en.wikipedia.org/wiki/Bilinear_interpolation#/media/File:Bilinear_interpolation_visualisation.svg
// and pos1, pos2 etc correspond to the indices of their respective pixels.
//
// Note: the weights and indices are shared across all channels, which is why
// they are pre-calculated prior to the main loop in the RoIAlign kernel.
// implementation taken from Caffe2
template <typename T>
void pre_calc_for_bilinear_interpolate(
    int height,
    int width,
    int pooled_height,
    int pooled_width,
    T roi_start_h,
    T roi_start_w,
    T bin_size_h,
    T bin_size_w,
    int roi_bin_grid_h,
    int roi_bin_grid_w,
    std::vector<PreCalc<T>>& pre_calc) {
  int pre_calc_index = 0;
  for (int ph = 0; ph < pooled_height; ph++) {
    for (int pw = 0; pw < pooled_width; pw++) {
      for (int iy = 0; iy < roi_bin_grid_h; iy++) {
        const T yy = roi_start_h + ph * bin_size_h +
            static_cast<T>(iy + .5f) * bin_size_h /
                static_cast<T>(roi_bin_grid_h); // e.g., 0.5, 1.5
        for (int ix = 0; ix < roi_bin_grid_w; ix++) {
          const T xx = roi_start_w + pw * bin_size_w +
              static_cast<T>(ix + .5f) * bin_size_w /
                  static_cast<T>(roi_bin_grid_w);

          T x = xx;
          T y = yy;
          // deal with: inverse elements are out of feature map boundary
          if (y < -1.0 || y > height || x < -1.0 || x > width) {
            // empty
            PreCalc<T> pc;
            pc.pos1 = 0;
            pc.pos2 = 0;
            pc.pos3 = 0;
            pc.pos4 = 0;
            pc.w1 = 0;
            pc.w2 = 0;
            pc.w3 = 0;
            pc.w4 = 0;
            pre_calc[pre_calc_index] = pc;
            pre_calc_index += 1;
            continue;
          }

          if (y <= 0) {
            y = 0;
          }
          if (x <= 0) {
            x = 0;
          }

          int y_low = (int)y;
          int x_low = (int)x;
          int y_high;
          int x_high;

          if (y_low >= height - 1) {
            y_high = y_low = height - 1;
            y = (T)y_low;
          } else {
            y_high = y_low + 1;
          }

          if (x_low >= width - 1) {
            x_high = x_low = width - 1;
            x = (T)x_low;
          } else {
            x_high = x_low + 1;
          }

          T ly = y - y_low;
          T lx = x - x_low;
          T hy = 1. - ly, hx = 1. - lx;
          T w1 = hy * hx, w2 = hy * lx, w3 = ly * hx, w4 = ly * lx;

          // save weights and indices
          PreCalc<T> pc;
          pc.pos1 = y_low * width + x_low;
          pc.pos2 = y_low * width + x_high;
          pc.pos3 = y_high * width + x_low;
          pc.pos4 = y_high * width + x_high;
          pc.w1 = w1;
          pc.w2 = w2;
          pc.w3 = w3;
          pc.w4 = w4;
          pre_calc[pre_calc_index] = pc;

          pre_calc_index += 1;
        }
      }
    }
  }
}

} // namespace detail
} // namespace ops
} // namespace vision