from typing import Sequence
import torch
from torchvision.transforms import functional as F
from torchvision import transforms, models
from PIL import Image


def pad_to_square(img):
    w, h = img.size
    max_wh = max(w, h)
    pad = ((max_wh - w) // 2, (max_wh - h) // 2)
    padding = (pad[0], pad[1], max_wh - w - pad[0], max_wh - h - pad[1])
    return F.pad(img, padding, fill=0, padding_mode='constant')


def build_batch(paths: Sequence[str], transform=None) -> torch.Tensor:
    """Exercise 1.1

    @param paths: A sequence (e.g. list) of strings, each specifying the location of an image file.
    @param transform: One or multiple image transformations for augmenting the batch images.
    @return: Returns one single tensor that contains every image.
    """
    preprocess = transforms.Compose([
        transforms.Lambda(pad_to_square),
        transforms.Resize((224, 224)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225]),
    ])
    imgs = []
    for path in paths:
        img = Image.open(path).convert('RGB')
        img = preprocess(img)
        imgs.append(img)
    batch = torch.stack(imgs)
    return batch


def get_model() -> torch.nn.Module:
    """Exercise 1.2

    @return: Returns a neural network, initialised with pretrained weights.
    """
    model = models.resnet18(
        weights=models.ResNet18_Weights.DEFAULT)
    return model


def main():
    """Exercise 1.3

    Put all your code for exercise 1.3 here.
    """
    raise NotImplementedError()


if __name__ == "__main__":
    main()