saicinpainting/evaluation/utils.py

from enum import Enum

import numpy as np
from PIL import Image
import yaml
from easydict import EasyDict as edict
import torch.nn as nn
import torch
import cv2

def load_image(fname, mode='RGB', return_orig=False):
    img = np.array(Image.open(fname).convert(mode))
    if img.ndim == 3:
        img = np.transpose(img, (2, 0, 1))
    out_img = img.astype('float32') / 255
    if return_orig:
        return out_img, img
    else:
        return out_img
    
def prepare_image(input_img: Image, mode='RGB', return_orig=False):
    img = np.array(input_img.convert(mode))
    if img.ndim == 3:
        img = np.transpose(img, (2, 0, 1))
    out_img = img.astype('float32') / 255
    if return_orig:
        return out_img, img
    else:
        return out_img


def ceil_modulo(x, mod):
    if x % mod == 0:
        return x
    return (x // mod + 1) * mod


def pad_img_to_modulo(img, mod):
    channels, height, width = img.shape
    out_height = ceil_modulo(height, mod)
    out_width = ceil_modulo(width, mod)
    return np.pad(img, ((0, 0), (0, out_height - height), (0, out_width - width)), mode='symmetric')


def scale_image(img, factor, interpolation=cv2.INTER_AREA):
    if img.shape[0] == 1:
        img = img[0]
    else:
        img = np.transpose(img, (1, 2, 0))

    img = cv2.resize(img, dsize=None, fx=factor, fy=factor, interpolation=interpolation)

    if img.ndim == 2:
        img = img[None, ...]
    else:
        img = np.transpose(img, (2, 0, 1))
    return img


def load_yaml(path):
    with open(path, 'r') as f:
        return edict(yaml.safe_load(f))


def move_to_device(obj, device):
    if isinstance(obj, nn.Module):
        return obj.to(device)
    if torch.is_tensor(obj):
        return obj.to(device)
    if isinstance(obj, (tuple, list)):
        return [move_to_device(el, device) for el in obj]
    if isinstance(obj, dict):
        return {name: move_to_device(val, device) for name, val in obj.items()}
    raise ValueError(f'Unexpected type {type(obj)}')


class SmallMode(Enum):
    DROP = "drop"
    UPSCALE = "upscale"