close

undefined

實作mnist資料集時有遇到下述的錯誤訊息:

Please use alternatives such as official/mnist/dataset.py from tensorflow/models.

 

原始碼(下述程式是要將mnist資料集的圖片顯示出來):

import tensorflow.examples.tutorials.mnist.input_data as input
import numpy as np

mnist_data = input.read_data_sets("MNIST_DATA/",one_hot=False)
import matplotlib.pyplot as plt
# example = mnist_data.train.next_batch(10)
pixels, real_values = mnist_data.train.next_batch(10)
image = pixels[5,:]
image = np.reshape(image,[28,28])
plt.imshow(image)
plt.show()

 

這時候只要設定log的級別，就可以忽略掉此錯誤並且正確執行: (放在import numpy as np之後)

import tensorflow as tf
old_v = tf.logging.get_verbosity()
tf.logging.set_verbosity(tf.logging.ERROR)

 

執行結果:

Extracting MNIST_DATA/train-images-idx3-ubyte.gz

Extracting MNIST_DATA/train-labels-idx1-ubyte.gz

Extracting MNIST_DATA/t10k-images-idx3-ubyte.gz

Extracting MNIST_DATA/t10k-labels-idx1-ubyte.gz

 

1.jpg

arrow
arrow
    全站熱搜

    葛瑞斯肯 發表在 痞客邦 留言(0) 人氣()

    E-mail轉寄