Module: DNN::Layers::Conv2DUtils

Included in:
Conv2D, Conv2DTranspose, Pool2D, UnPool2D
Defined in:
lib/dnn/core/layers/cnn_layers.rb

Overview

This module is used for convolution.

Class Method Summary collapse

Class Method Details

.calc_conv2d_out_size(prev_h, prev_w, fil_h, fil_w, pad_h, pad_w, strides) ⇒ Object 



85
86
87
88
89
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 85

def calc_conv2d_out_size(prev_h, prev_w, fil_h, fil_w, pad_h, pad_w, strides)
  out_h = (prev_h + pad_h - fil_h) / strides[0] + 1
  out_w = (prev_w + pad_w - fil_w) / strides[1] + 1
  [out_h, out_w]
end

.calc_conv2d_padding_size(prev_h, prev_w, fil_h, fil_w, strides) ⇒ Object 



97
98
99
100
101
102
103
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 97

def calc_conv2d_padding_size(prev_h, prev_w, fil_h, fil_w, strides)
  out_h = prev_h / strides[0]
  out_w = prev_w / strides[1]
  pad_h = out_h * strides[0] - prev_h + fil_h - strides[0]
  pad_w = out_w * strides[1] - prev_w + fil_w - strides[1]
  [pad_h, pad_w]
end

.calc_conv2d_transpose_out_size(prev_h, prev_w, fil_h, fil_w, pad_h, pad_w, strides) ⇒ Object 



91
92
93
94
95
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 91

def calc_conv2d_transpose_out_size(prev_h, prev_w, fil_h, fil_w, pad_h, pad_w, strides)
  out_h = (prev_h - 1) * strides[0] + fil_h - pad_h
  out_w = (prev_w - 1) * strides[1] + fil_w - pad_w
  [out_h, out_w]
end

.calc_conv2d_transpose_padding_size(prev_h, prev_w, fil_h, fil_w, strides) ⇒ Object 



105
106
107
108
109
110
111
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 105

def calc_conv2d_transpose_padding_size(prev_h, prev_w, fil_h, fil_w, strides)
  out_h = prev_h * strides[0]
  out_w = prev_w * strides[1]
  pad_h = (prev_h - 1) * strides[0] + fil_h - out_h
  pad_w = (prev_w - 1) * strides[1] + fil_w - out_w
  [pad_h, pad_w]
end

.col2im(*args) ⇒ Object

col[bsize * out_h * out_w, fil_h * fil_w * ch] to img[bsize, out_h, out_w, ch]



18
19
20
21
22
23
24
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 18

def col2im(*args)
  if DNN.use_cumo?
    col2im_gpu(*args)
  else
    col2im_cpu(*args)
  end
end

.col2im_cpu(col, img_shape, out_h, out_w, fil_h, fil_w, strides) ⇒ Object 



46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 46

def col2im_cpu(col, img_shape, out_h, out_w, fil_h, fil_w, strides)
  bsize, img_h, img_w, ch = img_shape
  col = col.reshape(bsize, out_h, out_w, fil_h, fil_w, ch)
  img = col.class.zeros(bsize, img_h, img_w, ch)
  (0...fil_h).each do |i|
    i_range = (i...(i + strides[0] * out_h)).step(strides[0]).to_a
    (0...fil_w).each do |j|
      j_range = (j...(j + strides[1] * out_w)).step(strides[1]).to_a
      img[true, i_range, j_range, true] += col[true, true, true, i, j, true]
    end
  end
  img
end

.col2im_gpu(col, img_shape, out_h, out_w, fil_h, fil_w, strides) ⇒ Object 



60
61
62
63
64
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 60

def col2im_gpu(col, img_shape, out_h, out_w, fil_h, fil_w, strides)
  col = Utils.cumo2numo(col)
  img = col2im_cpu(col, img_shape, out_h, out_w, fil_h, fil_w, strides)
  Utils.numo2cumo(img)
end

.im2col(*args) ⇒ Object

img[bsize, out_h, out_w, ch] to col[bsize * out_h * out_w, fil_h * fil_w * ch]



9
10
11
12
13
14
15
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 9

def im2col(*args)
  if DNN.use_cumo?
    im2col_gpu(*args)
  else
    im2col_cpu(*args)
  end
end

.im2col_cpu(img, out_h, out_w, fil_h, fil_w, strides) ⇒ Object 



26
27
28
29
30
31
32
33
34
35
36
37
38
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 26

def im2col_cpu(img, out_h, out_w, fil_h, fil_w, strides)
  bsize = img.shape[0]
  ch = img.shape[3]
  col = img.class.zeros(bsize, out_h, out_w, fil_h, fil_w, ch)
  (0...fil_h).each do |i|
    i_range = (i...(i + strides[0] * out_h)).step(strides[0]).to_a
    (0...fil_w).each do |j|
      j_range = (j...(j + strides[1] * out_w)).step(strides[1]).to_a
      col[true, true, true, i, j, true] = img[true, i_range, j_range, true]
    end
  end
  col.reshape(bsize * out_h * out_w, fil_h * fil_w * ch)
end

.im2col_gpu(img, out_h, out_w, fil_h, fil_w, strides) ⇒ Object 



40
41
42
43
44
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 40

def im2col_gpu(img, out_h, out_w, fil_h, fil_w, strides)
  img = Utils.cumo2numo(img)
  col = im2col_cpu(img, out_h, out_w, fil_h, fil_w, strides)
  Utils.numo2cumo(col)
end

.zero_padding(img, pad) ⇒ Object 



66
67
68
69
70
71
72
73
74
75
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 66

def zero_padding(img, pad)
  bsize, img_h, img_w, ch = img.shape
  img2 = Xumo::SFloat.zeros(bsize, img_h + pad[0], img_w + pad[1], ch)
  i_begin = pad[0] / 2
  i_end = i_begin + img_h
  j_begin = pad[1] / 2
  j_end = j_begin + img_w
  img2[true, i_begin...i_end, j_begin...j_end, true] = img
  img2
end

.zero_padding_bwd(img, pad) ⇒ Object 



77
78
79
80
81
82
83
 
# File 'lib/dnn/core/layers/cnn_layers.rb', line 77

def zero_padding_bwd(img, pad)
  i_begin = pad[0] / 2
  i_end = img.shape[1] - (pad[0] / 2.0).round
  j_begin = pad[1] / 2
  j_end = img.shape[2] - (pad[1] / 2.0).round
  img[true, i_begin...i_end, j_begin...j_end, true]
end