最终完全用tensorflow函数的解决方案

tf对新手还是很不友好的，不知道相关函数根本不能高效实现相关功能，了解到相关函数后也需要花时间上手。

from __future__ import division
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf

imgs = [[[[255, 0, 0], [0, 255, 0], [0, 0, 255]],
         [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
         [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
         [[255, 0, 0], [0, 255, 0], [0, 0, 255]]],
        [[[255, 0, 0], [0, 255, 0], [0, 0, 255]],
         [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
         [[255, 0, 0], [0, 255, 0], [0, 0, 255]],
         [[255, 0, 0], [0, 255, 0], [0, 0, 255]]]]
imgs = tf.reshape(imgs, [2, 4, 3, 3])

coords = [[[[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
           [[0.5, 2], [1.3, 2], [0.2, 1.6]],
           [[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
           [[0.5, 2], [1.3, 2], [0.2, 1.6]]],
          [[[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
           [[0.5, 2], [1.3, 2], [0.2, 1.6]],
           [[0.2, 0.2], [1.3, 0.2], [1.8, 2.2]],
           [[0.5, 2], [1.3, 2], [0.2, 1.6]]]]
coords = tf.reshape(coords, [2, 4, 3, 2])

cam_coords = [[[[1, 2, 3, 1], [2, 3, 4, 1], [3, 4, 5, 1]],
               [[4, 5, 6, 1], [7, 8, 9, 1], [10, 11, 12, 1]],
               [[1, 2, 3, 1], [2, 3, 4, 1], [3, 4, 5, 1]],
               [[4, 5, 6, 1], [7, 8, 9, 1], [10, 11, 12, 1]]],
              [[[1, 2, 3, 1], [2, 3, 4, 1], [3, 4, 5, 1]],
               [[4, 5, 6, 1], [7, 8, 9, 1], [10, 11, 12, 1]],
               [[2, 2, 3, 1], [3, 3, 4, 1], [4, 4, 5, 1]],
               [[5, 5, 6, 1], [8, 8, 9, 1], [11, 11, 12, 1]]]]
cam_coords = tf.reshape(cam_coords, [2, 4, 3, 4])
cam_coords = tf.transpose(cam_coords, perm=[0, 3, 1, 2])


# def bilinear_sampler(imgs, coords, cam_coords_T):
    # imgs = tf.tile(imgs, multiples=[1, 100, 50, 1])
    # coords = tf.tile(coords, multiples=[1, 100, 50, 1])
    # cam_coords_T = tf.tile(cam_coords_T, multiples=[1, 1, 100, 50])
def _repeat(x, n_repeats):  # x = tf.cast(tf.range(4), 'float32') * 53248 n_repeats = 53248。
    rep = tf.transpose(
        tf.expand_dims(tf.ones(shape=tf.stack([
            n_repeats,
        ])), 1), [1,
                  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
    rep = tf.cast(rep, 'float32')
    x = tf.matmul(tf.reshape(x, (-1, 1)),
                  rep)  # reshape为一列，得到[[     0.][ 53248.][106496.][159744.]]*rep，最后得到shape=(4, 53248)的矩阵。
    return tf.reshape(x, [-1])  # 最后又化为一列Tensor("Reshape_1:0", shape=(212992,), dtype=float32)

with tf.name_scope('image_sampling'):
    coords_x, coords_y = tf.split(coords, [1, 1], axis=3)
    inp_size = imgs.get_shape()
    coord_size = coords.get_shape()
    out_size = coords.get_shape().as_list()
    out_size[3] = imgs.get_shape().as_list()[3]

    coords_x = tf.cast(coords_x, 'float32')
    coords_y = tf.cast(coords_y, 'float32')

    x0 = tf.floor(coords_x)
    x1 = x0 + 1
    y0 = tf.floor(coords_y)
    y1 = y0 + 1

    y_max = tf.cast(tf.shape(imgs)[1] - 1, 'float32')
    x_max = tf.cast(tf.shape(imgs)[2] - 1, 'float32')
    zero = tf.zeros([1], dtype='float32')

    x0_safe = tf.clip_by_value(x0, zero, x_max)
    y0_safe = tf.clip_by_value(y0, zero, y_max)
    x1_safe = tf.clip_by_value(x1, zero, x_max)
    y1_safe = tf.clip_by_value(y1, zero, y_max)

    ## 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.
    ## 以下方式没有提高效果的原因是令重建的对应像素值为0了，但是原图像对应位置还有值，计算误差单纯为原图像的像素值。
    # wt_x0 = (x1 - coords_x) * tf.cast(tf.equal(x0, x0_safe), 'float32')
    # wt_x1 = (coords_x - x0) * tf.cast(tf.equal(x1, x1_safe), 'float32')
    # wt_y0 = (y1 - coords_y) * tf.cast(tf.equal(y0, y0_safe), 'float32')
    # wt_y1 = (coords_y - y0) * tf.cast(tf.equal(y1, y1_safe), 'float32')
    mask_p = tf.logical_and(  # 如果四个值都在图像中说明投影点没有落到图像外。这个mask和相邻帧即投影来点的图像大小相等。
        tf.logical_and(x0 >= zero, x1 <= x_max),
        tf.logical_and(y0 >= zero, y1 <= y_max))
    mask_p = tf.to_float(mask_p)
    mask_p = tf.tile(mask_p, multiples=[1, 1, 1, 3])

    wt_x0 = x1_safe - coords_x
    wt_x1 = coords_x - x0_safe
    wt_y0 = y1_safe - coords_y
    wt_y1 = coords_y - y0_safe

    ## indices in the flat image to sample from
    dim2 = tf.cast(inp_size[2], 'float32')
    dim1 = tf.cast(inp_size[2] * inp_size[1], 'float32')
    base = tf.reshape(
        _repeat(
            tf.cast(tf.range(coord_size[0]), 'float32') * dim1,
            coord_size[1] * coord_size[2]),
        [out_size[0], out_size[1], out_size[2],
         1])  # tf.reshape(_repeat(tf.cast(tf.range(4), 'float32') * 128 * 416, 128 * 416), [4, 128, 416, 1])
    # 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。
    base_y0 = base + y0_safe * dim2
    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。
    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。
    idx01 = x0_safe + base_y1
    idx10 = x1_safe + base_y0
    idx11 = x1_safe + base_y1

    ## sample from imgs
    imgs_flat = tf.reshape(imgs, tf.stack([-1, inp_size[3]]))
    imgs_flat = tf.cast(imgs_flat, 'float32')
    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。
    im01 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx01, 'int32')), out_size)
    im10 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx10, 'int32')), out_size)
    im11 = tf.reshape(tf.gather(imgs_flat, tf.cast(idx11, 'int32')), out_size)

    w00 = wt_x0 * wt_y0  ######这里横轴和纵轴的距离乘机就算距离了。
    w01 = wt_x0 * wt_y1
    w10 = wt_x1 * wt_y0
    w11 = wt_x1 * wt_y1

    output = tf.add_n([
        w00 * im00, w01 * im01,
        w10 * im10, w11 * im11
    ])
    # 以下为自定义代码
    cam_coords = tf.transpose(cam_coords, perm=[0, 2, 3, 1])
    batch, height, width, channels = imgs.get_shape().as_list()
    cam_coords = cam_coords[:, :, :, 0:-1]
    cam_coords = tf.cast(cam_coords, 'float32')
    euclidean = tf.sqrt(tf.reduce_sum(tf.square(cam_coords), 3))
    euclidean = tf.reshape(euclidean, [batch, -1])
    xy00 = tf.concat([x0, y0], axis=3)

    for i in range(2):
        euclideani = euclidean[i, :]
        euclideani = tf.reshape(euclideani, [-1, 1])
        xy00_batchi = xy00[i, :, :, :]  # 将横纵坐标合在一起，取batch1.
        xy00_batchi = tf.reshape(xy00_batchi, [-1, 2])
        xy00_batchi = tf.cast(xy00_batchi, tf.int32)

        unique_xy00_batchi, ids = tf.unique(xy00_batchi[:, 0]*width+xy00_batchi[:, 1])
        num_segments = tf.shape(unique_xy00_batchi)
        outputs = tf.unsorted_segment_min(euclideani, ids, num_segments[0])
        zuixiaojuli = tf.gather(outputs, ids)
        mask0 = tf.where(tf.less_equal(euclideani, zuixiaojuli), tf.ones_like(euclideani), tf.zeros_like(euclideani))

        mask0 = tf.reshape(mask0, [height, width])
        mask0 = tf.expand_dims(mask0, 0)
        if i == 0:
            mask0_stack = mask0
        else:
            mask0_stack = tf.concat([mask0_stack, mask0], axis=0)
    # mask0_stack = tf.tile(tf.expand_dims(mask0_stack, 3), multiples=[1, 1, 1, 3])
    # return output, mask_p, mask0_stack


# output, mask_p, mask0_stack = bilinear_sampler(imgs, coords, cam_coords)
# imgs = tf.cast(imgs, 'float32')
# imgs_mask = imgs*mask1_stack
with tf.Session() as sess:

    print(sess.run(xy00_batchi[:, 0]))
    print(xy00_batchi[:, 0])
    print(sess.run(euclideani))
    print(euclideani)
    print(mask0_stack)
    print(sess.run(mask0_stack))