摘要：在中導(dǎo)入本地?cái)?shù)據(jù)文件時(shí)，總是無(wú)法得到正確的數(shù)據(jù)。此時(shí)，如果直接輸出，會(huì)看到以下結(jié)果可見，如果本地文件包含了額外的信息，則單純使用無(wú)法直接讀取到所需數(shù)據(jù)，還應(yīng)該補(bǔ)充一行對(duì)應(yīng)的代碼。

問題代碼如下：

from numpy import *
import scipy.io

mnist_train = "D:Machine LearningTensorFlowSoftmax Regressionmnist_datasetmnist_train.mat"
mnist_train_labels = "D:Machine LearningTensorFlowSoftmax Regressionmnist_datasetmnist_train_labels.mat"

x = scipy.io.loadmat(mnist_train)
label = scipy.io.loadmat(mnist_train_labels)

print(x.shape)

"""
[[ {"__version__": "1.0", "__header__": b"MATLAB 5.0 MAT-file, Platform: PCWIN, Created on: Tue Nov 29 12:43:31 2011", 
"mnist_train": array([[ 0.,  0.,  0., ...,  0.,  0.,  0.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.],
       ...,
       [ 0.,  0.,  0., ...,  0.,  0.,  0.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.]], dtype=float32), "__globals__": []}]]
"""

x = scipy.io.loadmat(mnist_train)
train_x = x["mnist_train"]
label = scipy.io.loadmat(mnist_train_labels)
train_label = label["mnist_train_labels"]