关于双线性插值中重叠像素与空白像素掩膜函数的一种迭代batch的写法

  1 from __future__ import division
  2 import matplotlib.pyplot as plt
  3 import numpy as np
  4 import tensorflow as tf
  5 
  6 
  7 imgs = [[[[255, 0, 0], [0, 255, 0], [0, 0, 255]],
  8          [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
  9          [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
 10          [[255, 0, 0], [0, 255, 0], [0, 0, 255]]],
 11         [[[255, 0, 0], [0, 255, 0], [0, 0, 255]],
 12          [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
 13          [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
 14          [[255, 0, 0], [0, 255, 0], [0, 0, 255]]]]
 15 imgs = tf.reshape(imgs, [2, 4, 3, 3])
 16 coords = [[[[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
 17            [[0.5, 2], [1.3, 2], [0.2, 1.6]],
 18            [[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
 19            [[0.5, 2], [1.3, 2], [0.2, 1.6]]],
 20           [[[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
 21            [[0.5, 2], [1.3, 2], [0.2, 1.6]],
 22            [[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
 23            [[0.5, 2], [1.3, 2], [0.2, 1.6]]]]
 24 coords = tf.reshape(coords, [2, 4, 3, 2])
 25 
 26 
 27 cam_coords = [[[[1, 2, 3, 1], [2, 3, 4, 1], [3, 4, 5, 1]],
 28                [[4, 5, 6, 1], [7, 8, 9, 1], [10, 11, 12, 1]],
 29                [[1, 0, 3, 1], [3, 3, 4, 1], [3, 5, 5, 1]],
 30                [[4, 4, 6, 1], [7, 7, 9, 1], [10, 12, 12, 1]]],
 31               [[[1, 2, 3, 1], [2, 3, 4, 1], [3, 4, 5, 1]],
 32                [[4, 5, 6, 1], [7, 8, 9, 1], [10, 11, 12, 1]],
 33                [[1, 0, 3, 1], [3, 3, 4, 1], [3, 5, 5, 1]],
 34                [[4, 4, 6, 1], [7, 7, 9, 1], [10, 12, 12, 1]]]]
 35 cam_coords = tf.reshape(cam_coords, [2, 4, 3, 4])
 36 
 37 
 38 def bilinear_sampler(imgs, coords, cam_coords):
 39     def _repeat(x, n_repeats):  # x = tf.cast(tf.range(4), ‘float32‘) * 53248 n_repeats = 53248。
 40         rep = tf.transpose(
 41             tf.expand_dims(tf.ones(shape=tf.stack([
 42                 n_repeats,
 43             ])), 1), [1,
 44                       0])  # 最后得到[1,53248]大小的全一矩阵。tf.stack其作用类似于tf.concat，都是拼接两个张量，而不同之处在于，tf.concat拼接的是两个shape完全相同的张量，并且产生的张量的阶数不会发生变化，而tf.stack则会在新的张量阶上拼接，产生的张量的阶数将会增加
 45         rep = tf.cast(rep, ‘float32‘)
 46         x = tf.matmul(tf.reshape(x, (-1, 1)),
 47                       rep)  # reshape为一列，得到[[     0.][ 53248.][106496.][159744.]]*rep，最后得到shape=(4, 53248)的矩阵。
 48         return tf.reshape(x, [-1])  # 最后又化为一列Tensor("Reshape_1:0", shape=(212992,), dtype=float32)
 49 
 50     with tf.name_scope(‘image_sampling‘):
 51         coords_x, coords_y = tf.split(coords, [1, 1], axis=3)
 52         inp_size = imgs.get_shape()
 53         coord_size = coords.get_shape()
 54         out_size = coords.get_shape().as_list()
 55         out_size[3] = imgs.get_shape().as_list()[3]
 56 
 57         coords_x = tf.cast(coords_x, ‘float32‘)
 58         coords_y = tf.cast(coords_y, ‘float32‘)
 59 
 60         x0 = tf.floor(coords_x)
 61         x1 = x0 + 1
 62         y0 = tf.floor(coords_y)
 63         y1 = y0 + 1
 64 
 65         y_max = tf.cast(tf.shape(imgs)[1] - 1, ‘float32‘)
 66         x_max = tf.cast(tf.shape(imgs)[2] - 1, ‘float32‘)
 67         zero = tf.zeros([1], dtype=‘float32‘)
 68 
 69         x0_safe = tf.clip_by_value(x0, zero, x_max)
 70         y0_safe = tf.clip_by_value(y0, zero, y_max)
 71         x1_safe = tf.clip_by_value(x1, zero, x_max)
 72         y1_safe = tf.clip_by_value(y1, zero, y_max)
 73 
 74         ## bilinear interp weights, with points outside the grid having weight 0#判断是否相等，相等为1，不相等为0.
 75         # wt_x0 = (x1 - coords_x) * tf.cast(tf.equal(x0, x0_safe), ‘float32‘)
 76         # wt_x1 = (coords_x - x0) * tf.cast(tf.equal(x1, x1_safe), ‘float32‘)
 77         # wt_y0 = (y1 - coords_y) * tf.cast(tf.equal(y0, y0_safe), ‘float32‘)
 78         # wt_y1 = (coords_y - y0) * tf.cast(tf.equal(y1, y1_safe), ‘float32‘)
 79 
 80         wt_x0 = x1_safe - coords_x
 81         wt_x1 = coords_x - x0_safe
 82         wt_y0 = y1_safe - coords_y
 83         wt_y1 = coords_y - y0_safe
 84 
 85         ## indices in the flat image to sample from
 86         dim2 = tf.cast(inp_size[2], ‘float32‘)
 87         dim1 = tf.cast(inp_size[2] * inp_size[1], ‘float32‘)
 88         base = tf.reshape(
 89             _repeat(
 90                 tf.cast(tf.range(coord_size[0]), ‘float32‘) * dim1,
 91                 coord_size[1] * coord_size[2]),
 92             [out_size[0], out_size[1], out_size[2],
 93              1])  # tf.reshape(_repeat(tf.cast(tf.range(4), ‘float32‘) * 128 * 416, 128 * 416), [4, 128, 416, 1])
 94         # 上面最后得base=Tensor("Reshape_2:0", shape=(4, 128, 416, 1), dtype=float32)。中间有[     0.][ 53248.][106496.][159744.]四种数。
 95         base_y0 = base + y0_safe * dim2
 96         base_y1 = base + y1_safe * dim2  # 考虑进有4个batch，所以不同batch要加上不同的基数。
 97         idx00 = tf.reshape(x0_safe + base_y0, [-1])  # 加上基数之后构成了四个像素值的索引。
 98         idx01 = x0_safe + base_y1
 99         idx10 = x1_safe + base_y0
100         idx11 = x1_safe + base_y1
101 
102         ## sample from imgs
103         imgs_flat = tf.reshape(imgs, tf.stack([-1, inp_size[3]]))
104         imgs_flat = tf.cast(imgs_flat, ‘float32‘)
105         im00 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx00, ‘int32‘)), out_size)  # 每一个输出都有对应的四个像素点的值参与运算。
106         im01 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx01, ‘int32‘)), out_size)
107         im10 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx10, ‘int32‘)), out_size)
108         im11 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx11, ‘int32‘)), out_size)
109 
110         w00 = wt_x0 * wt_y0  ######这里横轴和纵轴的距离乘机就算距离了。
111         w01 = wt_x0 * wt_y1
112         w10 = wt_x1 * wt_y0
113         w11 = wt_x1 * wt_y1
114 
115         output = tf.add_n([
116             w00 * im00, w01 * im01,
117             w10 * im10, w11 * im11
118         ])
119 
120         # 以下为自定义代码
121         batch, height, width, channels = imgs.get_shape().as_list()
122         cam_coords = cam_coords[:, :, :, 0:-1]
123         cam_coords = tf.cast(cam_coords, ‘float32‘)
124         euclidean = tf.sqrt(tf.reduce_sum(tf.square(cam_coords), 3))
125         euclidean = tf.reshape(euclidean, [2, -1])
126 
127         xy00 = tf.concat([x0, y0], axis=3)
128         for i in range(batch):
129             cam_coordsi = cam_coords[i, :, :, :]
130             euclideani = euclidean[i, :]
131             euclideani = tf.reshape(euclideani, [-1, 1])
132             xy00_batchi = xy00[i, :, :, :]  # 将横纵坐标合在一起，取batch1.
133             xy00_batchi = tf.reshape(xy00_batchi, [-1, 2])
134             xy00_batchi = tf.cast(xy00_batchi, tf.int32)
135             xy10_batchi = xy00_batchi + [1, 0]
136             xy01_batchi = xy00_batchi + [0, 1]
137             xy11_batchi = xy00_batchi + [1, 1]
138 
139             mask0 = tf.ones(shape=[height * width], dtype=‘float32‘)
140 
141             def true_1():
142                 h = tf.cond(pred=tf.less(euclideani[h2, 0], euclideani[h1, 0]), true_fn=lambda: h1, false_fn=lambda: h2)
143                 one_hot_true = tf.one_hot(indices=h, depth=12, axis=0)
144                 return one_hot_true
145 
146             def false_1():
147                 one_hot_false = tf.zeros([tf.shape(mask0)[0]])
148                 return one_hot_false
149 
150             for h1 in range(xy00_batchi.get_shape().as_list()[0] - 1):
151                 for h2 in range(h1 + 1, xy00_batchi.get_shape().as_list()[0]):
152                     one_hot = tf.cond(pred=tf.reduce_all(tf.equal(xy00_batchi[h1, :], xy00_batchi[h2, :])), true_fn=true_1,
153                                       false_fn=false_1)
154                     mask0 = mask0 - one_hot
155             mask0 = tf.clip_by_value(mask0, 0, 1)
156             mask0 = tf.reshape(mask0, [height, width])
157             mask1 = np.zeros(shape=[height, width], dtype=‘float32‘)
158             for l1 in range(xy00_batchi.get_shape().as_list()[0]):
159                 q001 = xy00_batchi[l1, 0]
160                 q002 = xy00_batchi[l1, 1]
161                 q101 = xy10_batchi[l1, 0]
162                 q102 = xy10_batchi[l1, 1]
163                 q011 = xy01_batchi[l1, 0]
164                 q012 = xy01_batchi[l1, 1]
165                 q111 = xy11_batchi[l1, 0]
166                 q112 = xy11_batchi[l1, 1]
167                 var001 = tf.one_hot(indices=q002, depth=width, on_value=q001, off_value=height, axis=-1)
168                 var002 = tf.one_hot(indices=var001, depth=height, axis=0)
169                 var101 = tf.one_hot(indices=q102, depth=width, on_value=q101, off_value=height, axis=-1)
170                 var102 = tf.one_hot(indices=var101, depth=height, axis=0)
171                 var011 = tf.one_hot(indices=q012, depth=width, on_value=q011, off_value=height, axis=-1)
172                 var012 = tf.one_hot(indices=var011, depth=height, axis=0)
173                 var111 = tf.one_hot(indices=q112, depth=width, on_value=q111, off_value=height, axis=-1)
174                 var112 = tf.one_hot(indices=var111, depth=height, axis=0)
175                 mask1 = mask1 + var002 + var102 + var012 + var112
176             mask1 = tf.clip_by_value(mask1, 0, 1)
177             if i == 0:
178                 mask0_stack = mask0
179                 mask1_stack = mask1
180             else:
181                 mask0_stack = tf.stack([mask0_stack, mask0], axis=0)
182                 mask1_stack = tf.stack([mask1_stack, mask1], axis=0)
183     return output, mask0_stack, mask1_stack
184 
185 
186 output_img, mask0_stack, mask1_stack = bilinear_sampler(imgs, coords, cam_coords)
187 with tf.Session() as sess:
188     # print(output_img)
189     # print(sess.run(output))
190     print(sess.run(output_img))
191     print(sess.run(mask0_stack))
192     print(sess.run(mask1_stack))
193     print(mask0_stack)
194     print(mask1_stack)