在 tensorflow 中调整 3D 数据的大小，如 tf.image.resize_images [英] Resize 3D data in tensorflow like tf.image.resize_images

问题描述

我需要调整一些 3D 数据的大小，就像在用于 2d 数据的 tf.image.resize_images 方法中一样.

I need to resize some 3D data, like in the tf.image.resize_images method for 2d data.

我想我可以尝试在其上循环运行 tf.image.resize_images 并交换轴，但我认为必须有更简单的方法.简单的最近邻应该没问题.

I was thinking I could try and run tf.image.resize_images on it in a loop and swap axes, but I thought there must be an easier way. Simple nearest neighbour should be fine.

有什么想法吗?这并不理想，但我可以解决数据仅为 0 或 1 的情况并使用以下内容:

Any ideas? It's not ideal, but I could settle for the case where the data is just 0 or 1 and use something like:

tf.where(boolMap, tf.fill(data_im*2, 0), tf.fill(data_im*2), 1)

但我不确定如何获得 boolMap.使用 tf.while_loop 遍历所有值会显着降低性能吗?我觉得它会在 GPU 上，除非有某种自动循环并行化.

But I'm not sure how to get boolMap. Would use of tf.while_loop to go over all the values dramatically decrease performance? i feel like it would on GPU unless the have some kind of automatic loop parallelisation.

数据是一个大小为[batch_size, width, height, depth, 1]

提前致谢.

N.B 输出维度应该是:

N.B The output dimensions should be:

[batch_size, width*scale, height*scale, depth*scale, 1]

我想出了这个:

def resize3D(self, input_layer, width_factor, height_factor, depth_factor):
    shape = input_layer.shape
    print(shape)
    rsz1 = tf.image.resize_images(tf.reshape(input_layer, [shape[0], shape[1], shape[2], shape[3]*shape[4]]), [shape[1]*width_factor, shape[2]*height_factor])
    rsz2 = tf.image.resize_images(tf.reshape(tf.transpose(tf.reshape(rsz1, [shape[0], shape[1]*width_factor, shape[2]*height_factor, shape[3], shape[4]]), [0, 3, 2, 1, 4]), [shape[0], shape[3], shape[2]*height_factor, shape[1]*width_factor*shape[4]]), [shape[3]*depth_factor, shape[2]*height_factor])

    return tf.transpose(tf.reshape(rsz2, [shape[0], shape[3]*depth_factor, shape[2]*height_factor, shape[1]*width_factor, shape[4]]), [0, 3, 2, 1, 4])

哪个转弯:

进入:

我认为最近的邻居不应该有楼梯套管效果(我故意去掉了颜色).

I believe nearest neighbour shouldn't have the stair-casing effect (I intentionally removed the colour).

Hars 的回答是正确的，但是如果有人能破解它，我想知道我的有什么问题.

Hars answer works correctly, however I would like to know whats wrong with mine if anyone can crack it.

推荐答案

我的方法是沿两个轴调整图像大小，在下面粘贴的代码中，我沿深度和宽度重新采样

My approach to this would be to resize the image along two axis, in the code I paste below, I resample along depth and then width

def resize_by_axis(image, dim_1, dim_2, ax, is_grayscale):

    resized_list = []


    if is_grayscale:
        unstack_img_depth_list = [tf.expand_dims(x,2) for x in tf.unstack(image, axis = ax)]
        for i in unstack_img_depth_list:
            resized_list.append(tf.image.resize_images(i, [dim_1, dim_2],method=0))
        stack_img = tf.squeeze(tf.stack(resized_list, axis=ax))
        print(stack_img.get_shape())

    else:
        unstack_img_depth_list = tf.unstack(image, axis = ax)
        for i in unstack_img_depth_list:
            resized_list.append(tf.image.resize_images(i, [dim_1, dim_2],method=0))
        stack_img = tf.stack(resized_list, axis=ax)

    return stack_img

resized_along_depth = resize_by_axis(x,50,60,2, True)
resized_along_width = resize_by_axis(resized_along_depth,50,70,1,True)

其中 x 将是灰度或 RGB 的 3-d 张量；resized_along_width 是最终调整大小的张量.这里我们要将 3-d 图像的尺寸调整为 (50,60,70)

Where x will be the 3-d tensor either grayscale or RGB; resized_along_width is the final resized tensor. Here we want to resize the 3-d image to dimensions of (50,60,70)

这篇关于在 tensorflow 中调整 3D 数据的大小，如 tf.image.resize_images的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！