resolve issue 1818 by modifying mean and standard deviation in the transforms.Normalize

[zabboud]

Fixes #1818

Description

Modified transforms.Normalize mean and standard deviation values to reflect CIFAR10 train mean and standard deviations

from

transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

to

transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2470, 0.2435, 0.2616))])

Modified the docstring to reflect the change, that the new mean and standard deviation will be 0 and 1, respectively. Also, additional details were added to explain how those values were generated:

#   The values passed to the transform are the means (first tuple) and the
#    standard deviations (second tuple) of the rgb values of the images in
#    the dataset. You can calculate these values yourself by running these
#    few lines of code:
#          ```
#           from torch.utils.data import ConcatDataset
#           transform = transforms.Compose([transforms.ToTensor()])
#           trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
#                                        download=True, transform=transform)
#
#           #stack all train images together into a tensor of shape 
#           #(50000, 3, 32, 32)
#           x = torch.stack([sample[0] for sample in ConcatDataset([trainset])])
#           
#           #get the mean of each channel            
#           mean = torch.mean(x, dim=(0,2,3)) #tensor([0.4914, 0.4822, 0.4465])
#           std = torch.std(x, dim=(0,2,3)) #tensor([0.2470, 0.2435, 0.2616])  
# 
#          ```   

Checklist

• The issue that is being fixed is referred in the description (see above "Fixes Comment inconsistent with the code related to Normalize transformation #1818")
• Only one issue is addressed in this pull request
• Labels from the issue that this PR is fixing are added to this pull request
• No unnecessary issues are included into this pull request.

cc @suraj813

[netlify]

✅ Deploy Preview for pytorch-tutorials-preview ready!

Name	Link
🔨 Latest commit	d1b9d71
🔍 Latest deploy log	https://app.netlify.com/sites/pytorch-tutorials-preview/deploys/64793d5f8a198d000842fd02
😎 Deploy Preview	https://deploy-preview-2405--pytorch-tutorials-preview.netlify.app/beginner/introyt/introyt1_tutorial
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site settings.