我如何将mnist数据转换为RGB格式？

Question

我正在尝试将MNIST数据集转换为RGB格式，每个图像的实际形状是（28，28），但是我需要（28，28，3）。

import numpy as np
import tensorflow as tf

mnist = tf.keras.datasets.mnist
(x_train, _), (x_test, _) = mnist.load_data()

X = np.concatenate([x_train, x_test])
X = X / 127.5 - 1

X.reshape((70000, 28, 28, 1))

tf.image.grayscale_to_rgb(
    X,
    name=None
)

但是我收到以下错误：

ValueError: Dimension 1 in both shapes must be equal, but are 84 and 3. Shapes are [28,84] and [28,3].

Answer 1

您应该将变形的3D [28x28x1]图像存储在数组中：

X = X.reshape((70000, 28, 28, 1))

[转换时，将另一个数组设置为tf.image.grayscale_to_rgb()函数的返回值：

X3 = tf.image.grayscale_to_rgb(
X,
name=None
)

最后，用matplotlib和tf.session()从所得张量图像中绘制出一个例子：

import matplotlib.pyplot as plt

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    image_to_plot = sess.run(image)
    plt.figure()
    plt.imshow(image_to_plot)
    plt.grid(False)

完整代码：

import numpy as np
import tensorflow as tf

mnist = tf.keras.datasets.mnist
(x_train, _), (x_test, _) = mnist.load_data()

X = np.concatenate([x_train, x_test])
X = X / 127.5 - 1

# Set reshaped array to X 
X = X.reshape((70000, 28, 28, 1))

# Convert images and store them in X3
X3 = tf.image.grayscale_to_rgb(
    X,
    name=None
)

# Get one image from the 3D image array to var. image
image = X3[0,:,:,:]

# Plot it out with matplotlib.pyplot
import matplotlib.pyplot as plt

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    image_to_plot = sess.run(image)
    plt.figure()
    plt.imshow(image_to_plot)
    plt.grid(False)

Answer 2

如果在tf.image.grayscale_to_rgb之前打印X的形状，您将看到输出尺寸为（70000，28，28）。 tf.image.grayscale的输入的最终尺寸必须为1。

展开X的最终尺寸以使其与功能兼容

tf.image.grayscale_to_rgb(tf.expand_dims(X, axis=3))

Answer 3

除了@DMolony和@ Aqwis01答案，另一个简单的解决方案可能是使用numpy.repeat方法多次复制张量的最后一个维度：

X = X.reshape((70000, 28, 28, 1))
X = X.repeat(3, -1)  # repeat the last (-1) dimension three times
X_t = tf.convert_to_tensor(X)
assert X_t.shape == (70000, 28, 28, 3)