![](/img/trans.png)
[英]How to apply tf.image.per_image_standardization() to a tensor with the wrong shape?
[英]TypeError: Image data cannot be converted to float after tf.image.per_image_standardization(x)
我在plt.imshow
遇到以下錯誤
TypeError: Image data cannot be converted to float
對於此代碼:
import keras
import tensorflow as tf
import matplotlib.pyplot as plt
mnist = keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
def preprocess(x):
x = tf.image.per_image_standardization(x)
return x
train_images = preprocess(train_images)
test_images = preprocess(test_images)
plt.figure()
plt.imshow(train_images[1])
plt.colorbar()
plt.grid(False)
plt.show()
任何想法為什么會這樣? 謝謝!
在您的腳本中, train_images
不包含實際數據,而只是占位符張量:
train_images[1]
<tf.Tensor 'strided_slice_2:0' shape=(28, 28) dtype=float32>
最簡單的解決方案是在腳本頂部啟用急切執行:
tf.enable_eager_execution()
這意味着在運行時,張量實際上將包含您嘗試繪制的數據:
train_images[1]
<tf.Tensor: id=95, shape=(28, 28), dtype=float32, numpy=
array([[-0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 ,
-0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 ,
-0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 ,
-0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 ,
-0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 , -0.4250042 ,
-0.4250042 , -0.4250042 , -0.4250042 ], # etc
哪個應該解決您的錯誤。 您可以在TF的網站上了解有關急切執行的更多信息。
或者,您也可以通過在會話中實際評估圖像張量來繪制圖:
with tf.Session() as sess:
img = sess.run(train_images[1])
plt.figure()
plt.imshow(img)
plt.colorbar()
plt.grid(False)
plt.show()
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.