没有这样的文件或目录:'E:/ MNIST / train-labels-idx1-ubyte'

时间:2018-09-22 17:10:28

标签: python mnist

我正在尝试为MNIST编码CNN。但是,一旦我运行了以下几行:

import tensorflow
import mnist
from mnist import MNIST
import numpy as np

mntrain = MNIST("E:/MNIST/")
mntrain.load_training()

此框弹出:

FileNotFoundError                         Traceback (most recent call last)
<ipython-input-22-4e645408be54> in <module>()
      1 mntrain = MNIST("E:/MNIST/")
----> 2 mntrain.load_training()

c:\users\thang\appdata\local\programs\python\python35\lib\site-packages\mnist\loader.py in load_training(self)
    124     def load_training(self):
    125         ims, labels = self.load(os.path.join(self.path, self.train_img_fname),
--> 126                                 os.path.join(self.path, self.train_lbl_fname))
    127
    128         self.train_images = self.process_images(ims)

c:\users\thang\appdata\local\programs\python\python35\lib\site-packages\mnist\loader.py in load(self, path_img, path_lbl, batch)
    245                                  '(start_point, batch_size)')
    246
--> 247         with self.opener(path_lbl, 'rb') as file:
    248             magic, size = struct.unpack(">II", file.read(8))
    249             if magic != 2049:

c:\users\thang\appdata\local\programs\python\python35\lib\site-packages\mnist\loader.py in opener(self, path_fn, *args, **kwargs)
    237             return gzip.open(path_fn + '.gz', *args, **kwargs)
    238         else:
--> 239             return open(path_fn, *args, **kwargs)
    240
    241     def load(self, path_img, path_lbl, batch=None):

FileNotFoundError: [Errno 2] No such file or directory: 'E:/MNIST/train-labels-idx1-ubyte'
<script src="https://ajax.googleapis.com/ajax/libs/angularjs/1.2.12/angular.min.js"></script>

我相信我已经为MNIST设置了绝对路径,但是没有用。反正有我可以解决的吗?

0 个答案:

没有答案