data.py

import torch.utils.data as data
import os.path
from PIL import Image
from torch.utils.data import DataLoader
from torchvision.transforms import transforms
import torchvision

torchvision.models.densenet121()


def default_loader(path):
    return Image.open(path).convert('RGB')


def default_flist_reader(flist, root=None):
    """
    flist format: impath label\nimpath label\n ...(same to caffe's filelist)
    """
    imlist = []
    with open(flist, 'r') as rf:
        for line in rf.readlines():
            impath = line.strip()
            impath = impath if root is None else os.path.join(root, impath)
            imlist.append(impath)

    return imlist


class ImageFilelist(data.Dataset):
    def __init__(self, root, flist, transform=None,
                 flist_reader=default_flist_reader, loader=default_loader):
        self.root = root
        self.imlist = flist_reader(os.path.join(root, flist))
        self.transform = transform
        self.loader = loader

    def __getitem__(self, index):
        impath = self.imlist[index]
        img = self.loader(os.path.join(self.root, impath))
        if self.transform is not None:
            img = self.transform(img)

        return img

    def __len__(self):
        return len(self.imlist)


class ImageLabelFilelist(data.Dataset):
    def __init__(self, root, flist, transform=None,
                 flist_reader=default_flist_reader, loader=default_loader):
        self.root = root
        self.imlist = flist_reader(os.path.join(self.root, flist), root=root)
        self.transform = transform
        self.loader = loader
        self.imgs = [(impath.split(' ')[0], impath.split(' ')[1]) for impath in self.imlist]

    def __getitem__(self, index):
        impath, label = self.imgs[index]
        img = self.loader(os.path.join(self.root, impath))
        label = int(label)
        if self.transform is not None:
            img = self.transform(img)
        return img, label

    def __len__(self):
        return len(self.imgs)


###############################################################################
# Code from
# https://github.com/pytorch/vision/blob/master/torchvision/datasets/folder.py
# Modified the original code so that it also loads images from the current
# directory as well as the subdirectories
###############################################################################


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


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


def make_dataset(dir):
    images = []
    assert os.path.isdir(dir), '%s is not a valid directory' % dir

    for root, _, fnames in sorted(os.walk(dir)):
        for fname in fnames:
            if is_image_file(fname):
                path = os.path.join(root, fname)
                images.append(path)

    return images


class ImageFolder(data.Dataset):

    def __init__(self, root, transform=None, return_paths=False,
                 loader=default_loader):
        imgs = sorted(make_dataset(root))
        if len(imgs) == 0:
            raise (RuntimeError("Found 0 images in: " + root + "\n"
                                                               "Supported image extensions are: " +
                                ",".join(IMG_EXTENSIONS)))

        self.root = root
        self.imgs = imgs
        self.transform = transform
        self.return_paths = return_paths
        self.loader = loader

    def __getitem__(self, index):
        path = self.imgs[index]
        img = self.loader(path)
        if self.transform is not None:
            img = self.transform(img)
        if self.return_paths:
            return img, path
        else:
            return img

    def __len__(self):
        return len(self.imgs)


def get_data_file_list(root, file_list, batch_size, train, num_workers=0, new_size=236, crop_size=224):
    if train:
        transform = transforms.Compose([
                    transforms.Scale(new_size),
                    transforms.RandomSizedCrop(crop_size),
                    transforms.RandomHorizontalFlip(),
                    transforms.ToTensor(),
                    transforms.Normalize((0.485, 0.456, 0.406),
                                         (0.229, 0.224, 0.225))])
    else:
        transform = transforms.Compose([
                    transforms.Resize((crop_size, crop_size)),
                    transforms.ToTensor(),
                    transforms.Normalize((0.485, 0.456, 0.406),
                                         (0.229, 0.224, 0.225))])

    dataset = ImageLabelFilelist(root, file_list, transform=transform)
    loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=train, drop_last=True, num_workers=num_workers)
    return loader


def get_all_data_loaders(conf, train_file_name='train.txt', test_file_name='test.txt', keep_ori=False):
    batch_size = conf['batch_size']
    num_workers = conf['num_workers']
    if 'new_size' in conf:
        new_size = conf['new_size']
    else:
        new_size = conf['new_size']
    height = conf['crop_image_height']

    if keep_ori:
        new_size = None
        train_flag = False
    else:
        train_flag = True

    train_loader_with_atk = get_data_file_list(conf['data_root'], train_file_name, batch_size,
                                               train_flag, num_workers, new_size=new_size, crop_size=height)
    test_loader = get_data_file_list(conf['data_root'], test_file_name, batch_size, False,
                                     num_workers, new_size=new_size, crop_size=height)

    return train_loader_with_atk, test_loader