Python, keras, load_data function extremely slow

user_8902495 0
Viewed 1096

I was trying to load the dataset mnist/cifar10 from keras, but it takes like forever to download it(the downloading speed gradually slows down, in the beginning it was quick, but then it gets slower and slower),e.g. still not be able to download the dataset in several hours. Here is my code:

from keras.datasets import mnist
from matplotlib import pyplot
from scipy.misc import toimage

(X_train, Y_train),(X_test,Y_test) = mnist.load_data()

for i in range(0.9):
   pyplot.subplot(330+1+i)
   pyplot.imshow(toimage(X_train[i]))
pyplot.show()

I have looked on the web, people usually don't encounter these problems, normally the dataset can be downloaded in several minutes. I have tried reinstalling python and other packages, but it did not help. Can anyone help me please?

keras deep-learning dataset python performance
1 Answers

I had the same issue. The problem is the IDLE not the code, the IDLE runs slower for every line printed. Instead run the python code in a terminal, power-shell or command prompt. Then it should run in about 5 seconds, the file is only 52 MB.

user_100737850
Related