我有一个image形状(466,394,1)，我希望将其分成7x7补丁。
image = tf.placeholder(dtype=tf.float32, shape=[1, 466, 394, 1])
使用
image_patches = tf.extract_image_patches(image, [1, 7, 7, 1], [1, 7, 7, 1], [1, 1, 1, 1], 'VALID')
# shape (1, 66, 56, 49)
image_patches_reshaped = tf.reshape(image_patches, [-1, 7, 7, 1])
# shape (3696, 7, 7, 1)
在实践中不起作用，因为image_patches_reshaped混合了像素顺序（如果您查看images_patches_reshaped，则只会看到噪音）。
所以我的新方法是使用tf.split：
image_hsplits = tf.split(1, 4, image_resized)
# [<tf.Tensor 'split_255:0' shape=(462, 7, 1) dtype=float32>,...]
image_patches = []
for split in image_hsplits:
image_patches.extend(tf.split(0, 66, split))
image_patches
# [<tf.Tensor 'split_317:0' shape=(7, 7, 1) dtype=float32>, ...]
这确实保留了图像像素顺序，遗憾的是它创造了很多不太好的OP。
如何使用较少的OP将图像拆分为较小的补丁？
UPDATE1：
我将answer of this question for numpy移植到tensorflow：
def image_to_patches(image, image_height, image_width, patch_height, patch_width):
height = math.ceil(image_height/patch_height)*patch_height
width = math.ceil(image_width/patch_width)*patch_width
image_resized = tf.squeeze(tf.image.resize_image_with_crop_or_pad(image, height, width))
image_reshaped = tf.reshape(image_resized, [height // patch_height, patch_height, -1, patch_width])
image_transposed = tf.transpose(image_reshaped, [0, 2, 1, 3])
return tf.reshape(image_transposed, [-1, patch_height, patch_width, 1])
但我认为还有改进的余地。
UPDATE2：
这会将补丁转换回原始图像。
def patches_to_image(patches, image_height, image_width, patch_height, patch_width):
height = math.ceil(image_height/patch_height)*patch_height
width = math.ceil(image_width/patch_width)*patch_width
image_reshaped = tf.reshape(tf.squeeze(patches), [height // patch_height, width // patch_width, patch_height, patch_width])
image_transposed = tf.transpose(image_reshaped, [0, 2, 1, 3])
image_resized = tf.reshape(image_transposed, [height, width, 1])
return tf.image.resize_image_with_crop_or_pad(image_resized, image_height, image_width)
答案 0 :(得分：8)
我认为您的问题在其他地方。我编写了以下代码片段（使用较小的14x14图像，以便我可以手动检查所有值），并确认您的初始代码执行了正确的操作：
import tensorflow as tf
import numpy as np
IMAGE_SIZE = [1, 14, 14, 1]
PATCH_SIZE = [1, 7, 7, 1]
input_image = np.reshape(np.array(xrange(14*14)), IMAGE_SIZE)
image = tf.placeholder(dtype=tf.int32, shape=IMAGE_SIZE)
image_patches = tf.extract_image_patches(
image, PATCH_SIZE, PATCH_SIZE, [1, 1, 1, 1], 'VALID')
image_patches_reshaped = tf.reshape(image_patches, [-1, 7, 7, 1])
sess = tf.Session()
(output, output_reshaped) = sess.run(
(image_patches, image_patches_reshaped),
feed_dict={image: input_image})
print "Output (shape: %s):" % (output.shape,)
print output
print "Reshaped (shape: %s):" % (output_reshaped.shape,)
print output_reshaped
输出结果为：
python resize.py
Output (shape: (1, 2, 2, 49)):
[[[[ 0 1 2 3 4 5 6 14 15 16 17 18 19 20 28 29 30 31
32 33 34 42 43 44 45 46 47 48 56 57 58 59 60 61 62 70
71 72 73 74 75 76 84 85 86 87 88 89 90]
[ 7 8 9 10 11 12 13 21 22 23 24 25 26 27 35 36 37 38
39 40 41 49 50 51 52 53 54 55 63 64 65 66 67 68 69 77
78 79 80 81 82 83 91 92 93 94 95 96 97]]
[[ 98 99 100 101 102 103 104 112 113 114 115 116 117 118 126 127 128 129
130 131 132 140 141 142 143 144 145 146 154 155 156 157 158 159 160 168
169 170 171 172 173 174 182 183 184 185 186 187 188]
[105 106 107 108 109 110 111 119 120 121 122 123 124 125 133 134 135 136
137 138 139 147 148 149 150 151 152 153 161 162 163 164 165 166 167 175
176 177 178 179 180 181 189 190 191 192 193 194 195]]]]
Reshaped (shape: (4, 7, 7, 1)):
[[[[ 0]
[ 1]
[ 2]
[ 3]
[ 4]
[ 5]
[ 6]]
[[ 14]
[ 15]
[ 16]
[ 17]
[ 18]
[ 19]
[ 20]]
[[ 28]
[ 29]
[ 30]
[ 31]
[ 32]
[ 33]
[ 34]]
[[ 42]
[ 43]
[ 44]
[ 45]
[ 46]
[ 47]
[ 48]]
[[ 56]
[ 57]
[ 58]
[ 59]
[ 60]
[ 61]
[ 62]]
[[ 70]
[ 71]
[ 72]
[ 73]
[ 74]
[ 75]
[ 76]]
[[ 84]
[ 85]
[ 86]
[ 87]
[ 88]
[ 89]
[ 90]]]
[[[ 7]
[ 8]
[ 9]
[ 10]
[ 11]
[ 12]
[ 13]]
[[ 21]
[ 22]
[ 23]
[ 24]
[ 25]
[ 26]
[ 27]]
[[ 35]
[ 36]
[ 37]
[ 38]
[ 39]
[ 40]
[ 41]]
[[ 49]
[ 50]
[ 51]
[ 52]
[ 53]
[ 54]
[ 55]]
[[ 63]
[ 64]
[ 65]
[ 66]
[ 67]
[ 68]
[ 69]]
[[ 77]
[ 78]
[ 79]
[ 80]
[ 81]
[ 82]
[ 83]]
[[ 91]
[ 92]
[ 93]
[ 94]
[ 95]
[ 96]
[ 97]]]
[[[ 98]
[ 99]
[100]
[101]
[102]
[103]
[104]]
[[112]
[113]
[114]
[115]
[116]
[117]
[118]]
[[126]
[127]
[128]
[129]
[130]
[131]
[132]]
[[140]
[141]
[142]
[143]
[144]
[145]
[146]]
[[154]
[155]
[156]
[157]
[158]
[159]
[160]]
[[168]
[169]
[170]
[171]
[172]
[173]
[174]]
[[182]
[183]
[184]
[185]
[186]
[187]
[188]]]
[[[105]
[106]
[107]
[108]
[109]
[110]
[111]]
[[119]
[120]
[121]
[122]
[123]
[124]
[125]]
[[133]
[134]
[135]
[136]
[137]
[138]
[139]]
[[147]
[148]
[149]
[150]
[151]
[152]
[153]]
[[161]
[162]
[163]
[164]
[165]
[166]
[167]]
[[175]
[176]
[177]
[178]
[179]
[180]
[181]]
[[189]
[190]
[191]
[192]
[193]
[194]
[195]]]]
根据重新整形的输出，您可以看到它是一个4x7x7x1，第一个补丁的值为：[0-7]，[14-21]，[28-35]，[42-49]，[56 -63），[70-77）和[84-91），对应于左上角7x7网格。
也许你可以进一步解释当它无法正常工作时会发生什么？