utils/utils_image.py

import os
import numpy as np
import torch
import cv2

os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"


IMG_EXTENSIONS = ['.jpg', '.JPG', '.jpeg', '.JPEG', '.png', '.PNG', '.ppm', '.PPM', '.bmp', '.BMP', '.tif']

def is_image_file(filename):
    return any(filename.endswith(extension) for extension in IMG_EXTENSIONS)


def get_image_paths(dataroot):
    paths = None  # return None if dataroot is None
    if dataroot is not None:
        paths = sorted(_get_paths_from_images(dataroot))
    return paths


def _get_paths_from_images(path):
    assert os.path.isdir(path), '{:s} is not a valid directory'.format(path)
    images = []
    for dirpath, _, fnames in sorted(os.walk(path)):
        for fname in sorted(fnames):
            if is_image_file(fname):
                img_path = os.path.join(dirpath, fname)
                images.append(img_path)
    assert images, '{:s} has no valid image file'.format(path)
    return images

def mkdir(path):
    if not os.path.exists(path):
        os.makedirs(path)


def mkdirs(paths):
    if isinstance(paths, str):
        mkdir(paths)
    else:
        for path in paths:
            mkdir(path)

# --------------------------------------------
# get uint8 image of size HxWxn_channles (RGB)
# --------------------------------------------
def imread_uint(path, n_channels=3):
    #  input: path
    # output: HxWx3(RGB or GGG), or HxWx1 (G)
    if n_channels == 1:
        img = cv2.imread(path, 0)  # cv2.IMREAD_GRAYSCALE
        img = np.expand_dims(img, axis=2)  # HxWx1
    elif n_channels == 3:
        # img = cv2.imread(path, cv2.IMREAD_UNCHANGED)  # BGR or G
        img = cv2.imread(path)  # BGR or G
        if img is None:
            import PIL
            img = np.array(PIL.Image.open(path).convert('RGB'))
            return img
        if img.ndim == 2:
            img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)  # GGG
        else:
            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # RGB
    return img

def imsave(img, img_path):
    img = np.squeeze(img)
    if img.ndim == 3:
        img = img[:, :, [2, 1, 0]]
    cv2.imwrite(img_path, img)

# convert uint to 4-dimensional torch tensor
def uint2tensor4(img):
    if img.ndim == 2:
        img = np.expand_dims(img, axis=2)
    return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().div(255.).unsqueeze(0)

# convert 2/3/4-dimensional torch tensor to uint
def tensor2uint(img):
    img = img.data.squeeze().float().clamp_(0, 1).cpu().numpy()
    if img.ndim == 3:
        img = np.transpose(img, (1, 2, 0))
    return np.uint8((img*255.0).round())


if __name__ == '__main__':
    print('test util functions')