dnlcrl / pydatset Goto Github PK

Hi guys,

I am already imported the MNIST dataset and train on to the DBN, from the following code

from sklearn import datasets
print "[X] downloading data..."
dataset = datasets.fetch_mldata("MNIST Original")

(trainX, testX, trainY, testY) = train_test_split(
dataset.data / 255.0, dataset.target.astype("int0"), test_size = 0.16)

and the data was in this shape

trainX = [58000L,784L)
testX = [12000L, 10L)
trainX = [58000L,)
testX = [12000L, )

Please, I need help to import the cifar10 in the same way I imported the MNIST and return the same format. I have tried researching on the internet but there is hardly any help available. Any expert help related to solving this error will be much appreciated.

regards

can anyone explain stepwise procedure for load cifar 10 dataset in python from downloading to loading data python

I have downloaded the CIFAR-10 data from http://www.cs.toronto.edu/~kriz/cifar.html and uncompressed it into my destination folder. By using the Python environment, the following codes are passed at first stage but found the problem in calling this data. I am newbie user please help.

import numpy as np
Xtr, Ytr, Xte, Yte = load_CIFAR10('data/cifar10/')

I found the below mentioned error
Traceback (most recent call last):
File "", line 1, in
NameError: name 'load_CIFAR10' is not defined