recon/misc_utils.py

import os
from collections import OrderedDict
import numpy as np
import math
from datetime import datetime
import random
import logging
import torch
from torchvision.utils import make_grid
import cv2

import yaml
try:
    from yaml import CLoader as Loader, CDumper as Dumper
except ImportError:
    from yaml import Loader, Dumper


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


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


def get_paths_from_images(path):
    '''get image path list from image folder'''
    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 OrderedYaml():
    '''yaml orderedDict support'''
    _mapping_tag = yaml.resolver.BaseResolver.DEFAULT_MAPPING_TAG

    def dict_representer(dumper, data):
        return dumper.represent_dict(data.items())

    def dict_constructor(loader, node):
        return OrderedDict(loader.construct_pairs(node))

    Dumper.add_representer(OrderedDict, dict_representer)
    Loader.add_constructor(_mapping_tag, dict_constructor)
    return Loader, Dumper

####################
# miscellaneous
####################


def get_timestamp():
    return datetime.now().strftime('%y%m%d-%H%M%S')


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)


def mkdir_and_rename(path):
    if os.path.exists(path):
        new_name = path + '_archived_' + get_timestamp()
        print('Path already exists. Rename it to [{:s}]'.format(new_name))
        logger = logging.getLogger('base')
        logger.info('Path already exists. Rename it to [{:s}]'.format(new_name))
        os.rename(path, new_name)
    os.makedirs(path)


def set_random_seed(seed):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)


def setup_logger(logger_name, root, phase, level=logging.INFO, screen=False, tofile=False):
    '''set up logger'''
    lg = logging.getLogger(logger_name)
    formatter = logging.Formatter('%(asctime)s.%(msecs)03d - %(levelname)s: %(message)s',
                                  datefmt='%y-%m-%d %H:%M:%S')
    lg.setLevel(level)
    if tofile:
        log_file = os.path.join(root, phase + '_{}.log'.format(get_timestamp()))
        fh = logging.FileHandler(log_file, mode='w')
        fh.setFormatter(formatter)
        lg.addHandler(fh)
    if screen:
        sh = logging.StreamHandler()
        sh.setFormatter(formatter)
        lg.addHandler(sh)


####################
# image convert
####################


def tensor2img(tensor, out_type=np.uint8, min_max=(0, 1)):
    '''
    Converts a torch Tensor into an image Numpy array
    Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order
    Output: 3D(H,W,C) or 2D(H,W), [0,255], np.uint8 (default)
    '''
    tensor = tensor.squeeze().float().cpu().clamp_(*min_max)  # clamp
    tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0])  # to range [0,1]
    n_dim = tensor.dim()
    if n_dim == 4:
        n_img = len(tensor)
        img_np = make_grid(tensor, nrow=int(math.sqrt(n_img)), normalize=False).numpy()
        img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0))  # HWC, BGR
    elif n_dim == 3:
        img_np = tensor.numpy()
        img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0))  # HWC, BGR
    elif n_dim == 2:
        img_np = tensor.numpy()
    else:
        raise TypeError(
            'Only support 4D, 3D and 2D tensor. But received with dimension: {:d}'.format(n_dim))
    if out_type == np.uint8:
        img_np = (img_np * 255.0).round()
        # Important. Unlike matlab, numpy.unit8() WILL NOT round by default.
    return img_np.astype(out_type)

def tensor2img_Real(tensor, out_type=np.uint8, min_max=(0, 1)):
    '''
    Converts a torch Tensor into an image Numpy array
    Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order
    Output: 3D(H,W,C) or 2D(H,W), [0,255], np.uint8 (default)
    '''
    tensor = tensor.squeeze().float().cpu().clamp_(*min_max)  # clamp
    tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0])  # to range [0,1]
    n_dim = tensor.dim()
    if n_dim == 4:
        # n_img = len(tensor)
        # img_np = make_grid(tensor, nrow=int(math.sqrt(n_img)), normalize=False).numpy()
        img_np = tensor.numpy()
        # img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0))  # HWC, BGR
    elif n_dim == 3:
        img_np = tensor.numpy()
        # img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0))  # HWC, BGR
    elif n_dim == 2:
        img_np = tensor.numpy()
    else:
        raise TypeError(
            'Only support 4D, 3D and 2D tensor. But received with dimension: {:d}'.format(n_dim))
    if out_type == np.uint8:
        img_np = (img_np * 255.0).round()
        # Important. Unlike matlab, numpy.unit8() WILL NOT round by default.
    return img_np.astype(out_type)

def save_img(img, img_path, mode='RGB'):
    cv2.imwrite(img_path, img)


####################
# metric
####################


def calculate_psnr(img1, img2):
    # img1 and img2 have range [0, 255]
    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)
    mse = np.mean((img1 - img2)**2)
    if mse == 0:
        return float('inf')
    return 20 * math.log10(255.0 / math.sqrt(mse))


def ssim(img1, img2):
    C1 = (0.01 * 255)**2
    C2 = (0.03 * 255)**2

    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)
    kernel = cv2.getGaussianKernel(11, 1.5)
    window = np.outer(kernel, kernel.transpose())

    mu1 = cv2.filter2D(img1, -1, window)[5:-5, 5:-5]  # valid
    mu2 = cv2.filter2D(img2, -1, window)[5:-5, 5:-5]
    mu1_sq = mu1**2
    mu2_sq = mu2**2
    mu1_mu2 = mu1 * mu2
    sigma1_sq = cv2.filter2D(img1**2, -1, window)[5:-5, 5:-5] - mu1_sq
    sigma2_sq = cv2.filter2D(img2**2, -1, window)[5:-5, 5:-5] - mu2_sq
    sigma12 = cv2.filter2D(img1 * img2, -1, window)[5:-5, 5:-5] - mu1_mu2

    ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) *
                                                            (sigma1_sq + sigma2_sq + C2))
    return ssim_map.mean()


def calculate_ssim(img1, img2):
    '''calculate SSIM
    the same outputs as MATLAB's
    img1, img2: [0, 255]
    '''
    if not img1.shape == img2.shape:
        raise ValueError('Input images must have the same dimensions.')
    if img1.ndim == 2:
        return ssim(img1, img2)
    elif img1.ndim == 3:
        if img1.shape[2] == 3:
            ssims = []
            for i in range(3):
                ssims.append(ssim(img1, img2))
            return np.array(ssims).mean()
        elif img1.shape[2] == 1:
            return ssim(np.squeeze(img1), np.squeeze(img2))
    else:
        raise ValueError('Wrong input image dimensions.')

def calculate_epe(flow_pr, flow_gt, valid, max_flow=400):
    # taken from raft
    # epe = torch.sum((flow_pr[0].detach().cpu() - flow_gt[0].detach().cpu())**2, dim=0).sqrt()
    # mag = torch.sum(flow_gt**2, dim=1).sqrt()
    # valid = (valid >= 0.5) & (mag < max_flow)
    # return epe.view(-1)[valid[0].view(-1)].numpy()

    #larger bt version
    epe = torch.sum((flow_pr.detach().cpu() - flow_gt.detach().cpu())**2, dim=1).sqrt()
    mag = torch.sum(flow_gt**2, dim=1).sqrt()
    valid = (valid >= 0.5) & (mag < max_flow)
    return epe.view(-1)[valid.view(-1)].numpy()




#######################