Jovian
Sign In
Learn practical skills, build real-world projects, and advance your career
import os 
import torch 
import torchvision
import tarfile
from torchvision.datasets.utils import download_url
data_dir = './data/cifar10'

print(os.listdir(data_dir))
classes = os.listdir(data_dir + '/train')
print(classes)
['labels.txt', 'test', 'train'] ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
Key points

  1. Instead of setting aside 10-20% of the data from the training set for validation se, we will use entire set to train our model so that we can get some extra data.

  2. We will normalize the image tensors by subtracting the mean and dividing by the standard deviation across each channel. As a result, the mean of the data across each channel is 0, and standard deviation is 1. Normalizing the data prevents the values from disproportionately affecting the losses and gradients while training, simply by having a higher or wider range of values than others.

  3. We will apply randomly chosen transformations while loading images from the training dataset. Specifically, we will pad each image by 4 pixels, and then take a random crop of size 32 x 32 pixels, and then flip the image horizontaly with a 50% probability. Since the transformation will be applied randomly and dynamically each time a particular image is loaded, the model sees slightly different images in each epoch of training, which allows it generalize better.

from torchvision.datasets import ImageFolder
import torchvision.transforms as tt
# Data transforms (normalization & data augmentation)
stats = ((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
train_tfms = tt.Compose([tt.RandomCrop(32, padding=4, padding_mode='reflect'),
                        tt.RandomHorizontalFlip(),
                        tt.ToTensor(),
                        tt.Normalize(*stats)])
valid_tfms = tt.Compose([tt.ToTensor(), tt.Normalize(*stats)])