mobile_gallery_pytorch_01_preprocessing_and_dataloaders.py

# Let's start by loading in the image data
import torch
from torchvision import datasets, transforms

# Defining the transforms that we want to apply to the data.
# Resizing the image to (224,224),
# Randomly flipping the image horizontally(with the default probability of 0.5),
# Converting the image to Tensore (converting the pixel values btween 0 and 1), 
# Normalizing the 3-channel data using the 'Imagenet' stats
data_transforms = transforms.Compose([
        transforms.Resize((224, 224)), 
        transforms.RandomHorizontalFlip(), 
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
        ])

print('data_transforms: ', data_transforms)

dataset = datasets.ImageFolder(data_dir, transform = data_transforms)
print('dataset: ', dataset)

# We need to split the dataset between train and val datasets
train_percentage = 0.8
train_size = int(len(dataset)*train_percentage)
val_size = len(dataset) - train_size
train_dataset, val_dataset = torch.utils.data.random_split(dataset, [train_size, val_size])

print('\nnumber of examples in train_dataset: ', len(train_dataset))
print('number of examples in val_dataset  : ', len(val_dataset))

mobile_gallery_pytorch_01_preprocessing_and_dataloaders_output.py

data_transforms:  Compose(
    Resize(size=(224, 224), interpolation=PIL.Image.BILINEAR)
    RandomHorizontalFlip(p=0.5)
    ToTensor()
    Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
dataset:  Dataset ImageFolder
    Number of datapoints: 1266
    Root Location: mobile-gallery-image-classification-data/mobile_gallery_image_classification/train
    Transforms (if any): Compose(
                             Resize(size=(224, 224), interpolation=PIL.Image.BILINEAR)
                             RandomHorizontalFlip(p=0.5)
                             ToTensor()
                             Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
                         )
    Target Transforms (if any): None

number of examples in train_dataset:  1012
number of examples in val_dataset  :  254