utils.py

import torch
from PIL import Image
from torchvision.transforms import v2


def train_transform(image_size):
    _transform = v2.Compose([
        v2.ToImage(),
        v2.Resize(image_size),
        v2.CenterCrop(image_size),
        v2.ToDtype(torch.float32, scale=True),
        v2.Normalize(mean=[0.0, 0.0, 0.0], std=[1 / 255.0, 1 / 255.0, 1 / 255.0])
    ])

    return _transform


def style_transform():
    """style_transform() function can be used for style transform and content transform"""
    _transform = v2.Compose([
        v2.ToImage(),
        v2.ToDtype(torch.float32, scale=True),
        v2.Normalize(mean=[0.0, 0.0, 0.0], std=[1 / 255.0, 1 / 255.0, 1 / 255.0])
    ])

    return _transform


content_transform = style_transform()


def load_image(filename, size=None, scale=None):
    img = Image.open(filename).convert('RGB')
    if size is not None:
        img = img.resize((size, size), Image.ANTIALIAS)
    elif scale is not None:
        img = img.resize((int(img.size[0] / scale), int(img.size[1] / scale)), Image.ANTIALIAS)
    return img


def save_image(filename, data):
    img = data.clone().clamp(0, 255).numpy()
    img = img.transpose(1, 2, 0).astype("uint8")
    img = Image.fromarray(img)
    img.save(filename)


def gram_matrix(y):
    (b, ch, h, w) = y.size()
    features = y.view(b, ch, w * h)
    features_t = features.transpose(1, 2)
    gram = features.bmm(features_t) / (ch * h * w)
    return gram


def normalize_batch(batch):
    # normalize using imagenet mean and std
    mean = batch.new_tensor([0.485, 0.456, 0.406]).view(-1, 1, 1)
    std = batch.new_tensor([0.229, 0.224, 0.225]).view(-1, 1, 1)
    batch = batch.div_(255.0)
    return (batch - mean) / std