為什么我無法使用 load_data() 方法加載 mnist 數據集？

Question

我使用這行代碼來加載 mnist 數據集，並從 tensorflow 文檔中獲得它。 (trainX, trainY), (testX, testY) = load_data(path='mnist.npz')

但是當我執行文件時，我收到了證書錯誤

我得到的錯誤

Traceback (most recent call last):
  File "mnist_degit.py", line 18, in <module>
    (trainX, trainY), (testX, testY) = load_data(path='mnist.npz')
  File "/Users/muongkimhong/Desktop/ComputerVision_project/DigitRecognize/digit_recognize_env/lib/python3.7/site-packages/tensorflow/python/keras/datasets/mnist.py", line 62, in load_data
    '731c5ac602752760c8e48fbffcf8c3b850d9dc2a2aedcf2cc48468fc17b673d1')
  File "/Users/muongkimhong/Desktop/ComputerVision_project/DigitRecognize/digit_recognize_env/lib/python3.7/site-packages/tensorflow/python/keras/utils/data_utils.py", line 267, in get_file
    raise Exception(error_msg.format(origin, e.errno, e.reason))
Exception: URL fetch failure on https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz: None -- [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1076)

有人可以幫忙嗎？

Answer 1

也許你可以試試這個：

import tensorflow as tf
(trainX, trainY), (testX, testY) = tf.keras.datasets.mnist.load_data()

Answer 2

你可以試試這個：

import tensorflow as tf
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data(path='mnist.npz')

或者

import tensorflow as tf
(x_train, y_train), (x_test, y_test) = tf.compat.v1.keras.datasets.mnist.load_data()