Mashinali o‘qitishga kirish Nosirov Xabibullo xikmatullo o‘gli Falsafa doktori (PhD), tret kafedrasi mudiri


The Problem: MNIST digit classification


Download 1.43 Mb.
bet6/6
Sana02.01.2022
Hajmi1.43 Mb.
#193367
1   2   3   4   5   6
Bog'liq
Mashinali oqitishga kirish 24-maruza Nosirov Kh

The Problem: MNIST digit classification

  • We’re going to tackle a classic machine learning problem: MNIST handwritten digit classification. It’s simple: given an image, classify it as a digit.
  • Each image in the MNIST dataset is 28x28 and contains a centered, grayscale digit. We’ll flatten each 28x28 into a 784 dimensional vector, which we’ll use as input to our neural network. Our output will be one of 10 possible classes: one for each digit.

Python dasturida Keras kutibxonasidan foydalanib neyron tarmog‘ini hosil qilish

pip install tensorflow numpy mnist //kutibxonalarni o‘rnatish


import numpy as np

import mnist from tensorflow

import keras # The first time you run this might be a bit slow, since the # mnist package has to download and cache the data.

train_images = mnist.train_images()

train_labels = mnist.train_labels()

print(train_images.shape) # (60000, 28, 28)



print(train_labels.shape) # (60000,)

Thank you! Contacts Khabibullo Nosirov, Phd Project Manager, Head Of The Department Tashkent University Of Information Technologies named after Muhammad Al-Khwarizmi Radio And Mobile Communications Faculty 100084, Amir Temur 108, Tashkent, Uzbekistan n.khabibullo1990@gmail.com +998 99 811 57 62 (WhatsApp) +998 90 911 57 62 (Telegram) www.tuit.uz www.spacecom.uz www.intras.uz


Download 1.43 Mb.

Do'stlaringiz bilan baham:
1   2   3   4   5   6




Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2024
ma'muriyatiga murojaat qiling