utils/preprocessing.py

from torchvision import transforms
from PIL import Image

class MaxResize(object):
    def __init__(self, max_size=800):
        self.max_size = max_size

    def __call__(self, image):
        width, height = image.size
        current_max_size = max(width, height)
        scale = self.max_size / current_max_size
        resized_image = image.resize((int(round(scale*width)), int(round(scale*height))))
        return resized_image

detection_transform = transforms.Compose([
    MaxResize(800),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])

structure_transform = transforms.Compose([
    MaxResize(1000),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])

def prepare_image(image, device):
    pixel_values = detection_transform(image).unsqueeze(0)
    pixel_values = pixel_values.to(device)
    return pixel_values

def prepare_cropped_image(cropped_image, device):
    pixel_values = structure_transform(cropped_image).unsqueeze(0)
    pixel_values = pixel_values.to(device)
    return pixel_values