![](/img/trans.png)
[英]How can i format my images from filepath to the same way as mnist.load_data() in python?
[英]How can i convert mnist data to RGB format?
我正在嘗試將 MNIST 數據集轉換為 RGB 格式,每個圖像的實際形狀是 (28, 28),但我需要 (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
)
但我收到以下錯誤:
ValueError: Dimension 1 in both shapes must be equal, but are 84 and 3. Shapes are [28,84] and [28,3].
您應該將重塑后的 3D [28x28x1] 圖像存儲在一個數組中:
X = X.reshape((70000, 28, 28, 1))
轉換時,將另一個數組設置為tf.image.grayscale_to_rgb()
function 的返回值:
X3 = tf.image.grayscale_to_rgb(
X,
name=None
)
最后,從matplotlib
和tf.session()
生成的張量圖像中,對 plot 給出一個示例:
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)
完整代碼:
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)
如果您在 tf.image.grayscale_to_rgb 之前打印 X 的形狀,您將看到 output 尺寸為 (70000, 28, 28)。 tf.image.grayscale 的輸入大小必須為 1,因為它是最終維度。
擴展X的最終尺寸使其與function兼容
tf.image.grayscale_to_rgb(tf.expand_dims(X, axis=3))
除了@DMolony 和@Aqwis01 答案之外,另一個簡單的解決方案可能是使用numpy.repeat
方法多次復制張量的最后一個維度:
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)
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.