2

在 python 中加载数据集时，我遇到了一个简单的问题。我想定义调用函数loading_dataset()以在训练自动编码器中使用它我的代码是

import matplotlib
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from urllib import urlretrieve
import cPickle as pickle
import os

import gzip
rom urllib import urlretrieve
import cPickle as pickle
import os
import gzip
import matplotlib.cm as cm
import theano
import lasagne
from lasagne import layers
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet
from nolearn.lasagne import visualize
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
#############################I tried to load data from open source
def load_dataset():
    url = 'ftp://ftp nrg.wustl.edu/data/oasis_cross-sectional_disc2.tar.gz'
    filename ='oasis_cross-sectional_disc2.tar.gz'
    if not os.path.exists(filename):
        print("Downloading MNIST dataset...")
        urlretrieve(url, filename)
    with gzip.open(filename, 'rb') as f:
        data = pickle.load(f)
    X_train, y_train = data[0]
        X_val, y_val = data[1]
        X_test, y_test = data[2]
        X_train = X_train.reshape((-1, 1, 28, 28))
        X_val = X_val.reshape((-1, 1, 28, 28))
        X_test = X_test.reshape((-1, 1, 28, 28))
        y_train = y_train.astype(np.uint8)
        y_val = y_val.astype(np.uint8)
        y_test = y_test.astype(np.uint8)
        return X_train, y_train, X_val, y_val, X_test, y_test
X_train, y_train, X_val, y_val, X_test, y_test = load_dataset()

正在下载 MNIST 数据集...

Traceback (most recent call last):
  File "<pyshell#46>", line 1, in <module>
    X_train, y_train, X_val, y_val, X_test, y_test = load_dataset()
  File "<pyshell#45>", line 6, in load_dataset
    urlretrieve(url, filename)
  File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib.py", line 98, in urlretrieve
    return opener.retrieve(url, filename, reporthook, data)
  File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib.py", line 245, in retrieve
    fp = self.open(url, data)
  File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib.py", line 213, in open
    return getattr(self, name)(url)
  File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib.py", line 526, in open_ftp
    host = socket.gethostbyname(host)
IOError: [Errno socket error] [Errno 8] nodename nor servname provided, or not known

出现了这个错误

我还尝试使用以下代码从桌面加载数据，用于 os.walk(pat) 中的路径、目录、文件： for filename in files: fullpath = os.path.join(path, filename) with open(fullpath, 'r ') as f: s=np.load(f) data = f.read() 打印数据

但我未能将数据加载为 X_train、y_train、X_val、y_val、X_test、y_test 的值

4

1 回答 1

0

如果可以使用keras搭建网络，这里是加载mnist数据集的方法

import keras
from keras.datasets import mnist
from keras.layers import Dense, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.models import Sequential

加载 MNIST 数据集，该数据集已经为我们分成训练集和测试集

(x_train, y_train), (x_test, y_test) = mnist.load_data()

如果您在下载数据集时收到任何错误，请从https://s3.amazonaws.com/img-datasets/mnist.npz下载数据集 并将其放入名为 ~/.keras/dataset 的文件夹中

于 2019-05-10T16:20:05.663 回答