The Regularization Cookbook by Vincent Vandenbussche

Author:Vincent Vandenbussche
Language: eng
Format: epub
Publisher: Packt Publishing Ltd.
Published: 2023-07-20T00:00:00+00:00

And we have some imports from torchvision:

MNIST for loading the dataset

transforms for transforming the dataset – both rescaling and flattening the data: import torch

import torch.nn as nn

import torch.nn.functional as F

from torch.utils.data import DataLoader

from torchvision.datasets import MNIST

import torchvision.transforms as transforms

import matplotlib.pyplot as plt

Instantiate the transformations. The Compose class is used here to compose three transformations:transforms.ToTensor(): Convert the input image in to torch.Tensor format

transforms.Normalize(): Normalize the image with the mean value and standard deviation. Will subtract the mean (i.e., 0.1307) and then divide it by the standard deviation (i.e., 0.3081) for each pixel value.

transforms.Lambda(torch.flatten): Flatten the 2D tensor in to a 1D tensor:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.