From keras datasets import mnist

print('Y_test: ' + str(test_y.shape))

Biz quyidagi natijani olamiz:

X_train: (60000, 28, 28)
Y_train: (60000,)
X_test: (10000, 28, 28)
Y_test: (10000,)
Bu erdan biz MNIST ma'lumotlar to'plami haqida quyidagi xulosalar chiqarishimiz mumkin:

1.Trening to'plamida 60 ming tasvir mavjud va test to'plamida 10 ming tasvir mavjud.

2.Kirish o'rganish vektori [60000 X 28 X 28] o'lchamiga ega.
3.Chiqish o'rganish vektori [60000 X 1] o'lchamiga ega.
4.Har bir kirish vektorining o'lchami [28 X 28].
5.Har bir alohida chiqish vektori [1] o'lchamiga ega.

MNIST ma'lumotlar to'plamini yaratish
Keling, MNIST ma'lumotlar to'plamida tasvirlarni ko'rsatishga harakat qilaylik. Matplotlibni import qilish bilan boshlang.

from matplotlib import pyplot

Ma'lumotlarni chizish uchun quyidagi kod parchasidan foydalaning:

from matplotlib import pyplot
for i in range(9):
pyplot.subplot(330 + 1 + i)
pyplot.imshow(train_X[i], cmap=pyplot.get_cmap('gray'))
pyplot.show()

Chiqish quyidagicha chiqadi:

Python-da MNIST ma'lumotlar to'plamini yuklash va yaratish uchun to'liq kod

Ushbu qo'llanma uchun to'liq kod quyida keltirilgan:

from keras.datasets import mnist
from matplotlib import pyplot
#loading
(train_X, train_y), (test_X, test_y) = mnist.load_data()
#shape of dataset
print('X_train: ' + str(train_X.shape))
print('Y_train: ' + str(train_y.shape))
print('X_test: ' + str(test_X.shape))
print('Y_test: ' + str(test_y.shape))

#plotting

from matplotlib import pyplot
for i in range(9):
pyplot.subplot(330 + 1 + i)