Divide the image tensor into small spots

Question

I have an image form (466,394,1) that I want to split into 7x7 patches.

 image = tf.placeholder(dtype=tf.float32, shape=[1, 466, 394, 1]) 

Using

 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) 

unfortunately, this does not work in practice, since image_patches_reshaped mixes the order of pixels (if you see images_patches_reshaped , you will only see noise).

So my new approach was to use 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>, ...] 

it really preserves the pixel order of the image, unfortunately, it creates a lot of OP, which is not very good.

How to split the image into smaller patches with less OP?

Update1:

I put the answer of this question to numpy in 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]) 

but I think there is still room for improvement.

Update2:

This will convert the corrections back to the original image.

 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) 

Answer 1

I think your problem is elsewhere. I wrote the following code snippet (using a smaller 14x14 image so that I can manually check all the values) and confirmed that your source code performed the correct operations:

 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 

The output was:

 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]]]] 

Based on the modified output, you can see that it is 4x7x7x1 with values ​​for the first patch: [0-7), [14-21], [28-35], [42-49], [56-63), [70- 77] and [84-91], which corresponds to the upper left grid 7x7.

Perhaps you can explain a little more what happens when it malfunctions?