cPickle.UnpicklingError:无效的加载密钥,''.？

Question

我正在尝试使用mnist_data进行手写数字识别.现在我尝试使用此代码加载数据.

import cPickle
import numpy as np


def load_data():
    f = open('G:/thesis paper/data sets/mnist.pkl.gz', 'rb')
    training_data, validation_data, test_data = cPickle.load(f)
    f.close()
    return (training_data, validation_data, test_data)


def load_data_nn():
    training_data, validation_data, test_data = load_data()
    inputs = [np.reshape(x, (784, 1)) for x in training_data[0]]
    results = [vectorized_result(y) for y in training_data[1]]
    training_data = zip(inputs, results)
    test_inputs = [np.reshape(x, (784, 1)) for x in test_data[0]]
    return (training_data, test_inputs, test_data[1])


def vectorized_result(j):
    e = np.zeros((10, 1))
    e[j] = 1.0
    return e


if __name__ == '__main__':
    tr_data,test_inp,test_data=load_data_nn()

但是我收到了这个错误.

   File "D:/NeuralNet/mnist_loader.py", line 42, in load_data
     training_data, validation_data, test_data = cPickle.load(f) cPickle.UnpicklingError: invalid load key, ''.

我无法理解错误是什么意思以及如何删除此错误..谢谢提前..

Answer 1

您传递给cPickle.load（）的参数必须是.pkl文件。mnist.pkl.gz内部提供了mnist.pkl

因此，您必须首先打开该.gz。尝试这个：

import gzip
f = gzip.open('mnist.pkl.gz', 'rb')
train_set, valid_set, test_set = cPickle.load(f)