Added data folder

data/__init__.py

@@ -0,0 +1,93 @@
+"""This package includes all the modules related to data loading and preprocessing
+
+ To add a custom dataset class called 'dummy', you need to add a file called 'dummy_dataset.py' and define a subclass 'DummyDataset' inherited from BaseDataset.
+ You need to implement four functions:
+    -- <__init__>:                      initialize the class, first call BaseDataset.__init__(self, opt).
+    -- <__len__>:                       return the size of dataset.
+    -- <__getitem__>:                   get a data point from data loader.
+    -- <modify_commandline_options>:    (optionally) add dataset-specific options and set default options.
+
+Now you can use the dataset class by specifying flag '--dataset_mode dummy'.
+See our template dataset class 'template_dataset.py' for more details.
+"""
+import importlib
+import torch.utils.data
+from data.base_dataset import BaseDataset
+
+
+def find_dataset_using_name(dataset_name):
+    """Import the module "data/[dataset_name]_dataset.py".
+
+    In the file, the class called DatasetNameDataset() will
+    be instantiated. It has to be a subclass of BaseDataset,
+    and it is case-insensitive.
+    """
+    dataset_filename = "data." + dataset_name + "_dataset"
+    datasetlib = importlib.import_module(dataset_filename)
+
+    dataset = None
+    target_dataset_name = dataset_name.replace('_', '') + 'dataset'
+    for name, cls in datasetlib.__dict__.items():
+        if name.lower() == target_dataset_name.lower() \
+           and issubclass(cls, BaseDataset):
+            dataset = cls
+
+    if dataset is None:
+        raise NotImplementedError("In %s.py, there should be a subclass of BaseDataset with class name that matches %s in lowercase." % (dataset_filename, target_dataset_name))
+
+    return dataset
+
+
+def get_option_setter(dataset_name):
+    """Return the static method <modify_commandline_options> of the dataset class."""
+    dataset_class = find_dataset_using_name(dataset_name)
+    return dataset_class.modify_commandline_options
+
+
+def create_dataset(opt):
+    """Create a dataset given the option.
+
+    This function wraps the class CustomDatasetDataLoader.
+        This is the main interface between this package and 'train.py'/'test.py'
+
+    Example:
+        >>> from data import create_dataset
+        >>> dataset = create_dataset(opt)
+    """
+    data_loader = CustomDatasetDataLoader(opt)
+    dataset = data_loader.load_data()
+    return dataset
+
+
+class CustomDatasetDataLoader():
+    """Wrapper class of Dataset class that performs multi-threaded data loading"""
+
+    def __init__(self, opt):
+        """Initialize this class
+
+        Step 1: create a dataset instance given the name [dataset_mode]
+        Step 2: create a multi-threaded data loader.
+        """
+        self.opt = opt
+        dataset_class = find_dataset_using_name(opt.dataset_mode)
+        self.dataset = dataset_class(opt)
+        print("dataset [%s] was created" % type(self.dataset).__name__)
+        self.dataloader = torch.utils.data.DataLoader(
+            self.dataset,
+            batch_size=opt.batch_size,
+            shuffle=not opt.serial_batches,
+            num_workers=int(opt.num_threads))
+
+    def load_data(self):
+        return self
+
+    def __len__(self):
+        """Return the number of data in the dataset"""
+        return min(len(self.dataset), self.opt.max_dataset_size)
+
+    def __iter__(self):
+        """Return a batch of data"""
+        for i, data in enumerate(self.dataloader):
+            if i * self.opt.batch_size >= self.opt.max_dataset_size:
+                break
+            yield data

data/aligned_dataset.py

@@ -0,0 +1,60 @@
+import os
+from data.base_dataset import BaseDataset, get_params, get_transform
+from data.image_folder import make_dataset
+from PIL import Image
+
+
+class AlignedDataset(BaseDataset):
+    """A dataset class for paired image dataset.
+
+    It assumes that the directory '/path/to/data/train' contains image pairs in the form of {A,B}.
+    During test time, you need to prepare a directory '/path/to/data/test'.
+    """
+
+    def __init__(self, opt):
+        """Initialize this dataset class.
+
+        Parameters:
+            opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
+        """
+        BaseDataset.__init__(self, opt)
+        self.dir_AB = os.path.join(opt.dataroot, opt.phase)  # get the image directory
+        self.AB_paths = sorted(make_dataset(self.dir_AB, opt.max_dataset_size))  # get image paths
+        assert(self.opt.load_size >= self.opt.crop_size)   # crop_size should be smaller than the size of loaded image
+        self.input_nc = self.opt.output_nc if self.opt.direction == 'BtoA' else self.opt.input_nc
+        self.output_nc = self.opt.input_nc if self.opt.direction == 'BtoA' else self.opt.output_nc
+
+    def __getitem__(self, index):
+        """Return a data point and its metadata information.
+
+        Parameters:
+            index - - a random integer for data indexing
+
+        Returns a dictionary that contains A, B, A_paths and B_paths
+            A (tensor) - - an image in the input domain
+            B (tensor) - - its corresponding image in the target domain
+            A_paths (str) - - image paths
+            B_paths (str) - - image paths (same as A_paths)
+        """
+        # read a image given a random integer index
+        AB_path = self.AB_paths[index]
+        AB = Image.open(AB_path).convert('RGB')
+        # split AB image into A and B
+        w, h = AB.size
+        w2 = int(w / 2)
+        A = AB.crop((0, 0, w2, h))
+        B = AB.crop((w2, 0, w, h))
+
+        # apply the same transform to both A and B
+        transform_params = get_params(self.opt, A.size)
+        A_transform = get_transform(self.opt, transform_params, grayscale=(self.input_nc == 1))
+        B_transform = get_transform(self.opt, transform_params, grayscale=(self.output_nc == 1))
+
+        A = A_transform(A)
+        B = B_transform(B)
+
+        return {'A': A, 'B': B, 'A_paths': AB_path, 'B_paths': AB_path}
+
+    def __len__(self):
+        """Return the total number of images in the dataset."""
+        return len(self.AB_paths)

data/base_dataset.py

@@ -0,0 +1,157 @@
+"""This module implements an abstract base class (ABC) 'BaseDataset' for datasets.
+
+It also includes common transformation functions (e.g., get_transform, __scale_width), which can be later used in subclasses.
+"""
+import random
+import numpy as np
+import torch.utils.data as data
+from PIL import Image
+import torchvision.transforms as transforms
+from abc import ABC, abstractmethod
+
+
+class BaseDataset(data.Dataset, ABC):
+    """This class is an abstract base class (ABC) for datasets.
+
+    To create a subclass, you need to implement the following four functions:
+    -- <__init__>:                      initialize the class, first call BaseDataset.__init__(self, opt).
+    -- <__len__>:                       return the size of dataset.
+    -- <__getitem__>:                   get a data point.
+    -- <modify_commandline_options>:    (optionally) add dataset-specific options and set default options.
+    """
+
+    def __init__(self, opt):
+        """Initialize the class; save the options in the class
+
+        Parameters:
+            opt (Option class)-- stores all the experiment flags; needs to be a subclass of BaseOptions
+        """
+        self.opt = opt
+        self.root = opt.dataroot
+
+    @staticmethod
+    def modify_commandline_options(parser, is_train):
+        """Add new dataset-specific options, and rewrite default values for existing options.
+
+        Parameters:
+            parser          -- original option parser
+            is_train (bool) -- whether training phase or test phase. You can use this flag to add training-specific or test-specific options.
+
+        Returns:
+            the modified parser.
+        """
+        return parser
+
+    @abstractmethod
+    def __len__(self):
+        """Return the total number of images in the dataset."""
+        return 0
+
+    @abstractmethod
+    def __getitem__(self, index):
+        """Return a data point and its metadata information.
+
+        Parameters:
+            index - - a random integer for data indexing
+
+        Returns:
+            a dictionary of data with their names. It ususally contains the data itself and its metadata information.
+        """
+        pass
+
+
+def get_params(opt, size):
+    w, h = size
+    new_h = h
+    new_w = w
+    if opt.preprocess == 'resize_and_crop':
+        new_h = new_w = opt.load_size
+    elif opt.preprocess == 'scale_width_and_crop':
+        new_w = opt.load_size
+        new_h = opt.load_size * h // w
+
+    x = random.randint(0, np.maximum(0, new_w - opt.crop_size))
+    y = random.randint(0, np.maximum(0, new_h - opt.crop_size))
+
+    flip = random.random() > 0.5
+
+    return {'crop_pos': (x, y), 'flip': flip}
+
+
+def get_transform(opt, params=None, grayscale=False, method=Image.BICUBIC, convert=True):
+    transform_list = []
+    if grayscale:
+        transform_list.append(transforms.Grayscale(1))
+    if 'resize' in opt.preprocess:
+        osize = [opt.load_size, opt.load_size]
+        transform_list.append(transforms.Resize(osize, method))
+    elif 'scale_width' in opt.preprocess:
+        transform_list.append(transforms.Lambda(lambda img: __scale_width(img, opt.load_size, opt.crop_size, method)))
+
+    if 'crop' in opt.preprocess:
+        if params is None:
+            transform_list.append(transforms.RandomCrop(opt.crop_size))
+        else:
+            transform_list.append(transforms.Lambda(lambda img: __crop(img, params['crop_pos'], opt.crop_size)))
+
+    if opt.preprocess == 'none':
+        transform_list.append(transforms.Lambda(lambda img: __make_power_2(img, base=4, method=method)))
+
+    if not opt.no_flip:
+        if params is None:
+            transform_list.append(transforms.RandomHorizontalFlip())
+        elif params['flip']:
+            transform_list.append(transforms.Lambda(lambda img: __flip(img, params['flip'])))
+
+    if convert:
+        transform_list += [transforms.ToTensor()]
+        if grayscale:
+            transform_list += [transforms.Normalize((0.5,), (0.5,))]
+        else:
+            transform_list += [transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
+    return transforms.Compose(transform_list)
+
+
+def __make_power_2(img, base, method=Image.BICUBIC):
+    ow, oh = img.size
+    h = int(round(oh / base) * base)
+    w = int(round(ow / base) * base)
+    if h == oh and w == ow:
+        return img
+
+    __print_size_warning(ow, oh, w, h)
+    return img.resize((w, h), method)
+
+
+def __scale_width(img, target_size, crop_size, method=Image.BICUBIC):
+    ow, oh = img.size
+    if ow == target_size and oh >= crop_size:
+        return img
+    w = target_size
+    h = int(max(target_size * oh / ow, crop_size))
+    return img.resize((w, h), method)
+
+
+def __crop(img, pos, size):
+    ow, oh = img.size
+    x1, y1 = pos
+    tw = th = size
+    if (ow > tw or oh > th):
+        return img.crop((x1, y1, x1 + tw, y1 + th))
+    return img
+
+
+def __flip(img, flip):
+    if flip:
+        return img.transpose(Image.FLIP_LEFT_RIGHT)
+    return img
+
+
+def __print_size_warning(ow, oh, w, h):
+    """Print warning information about image size(only print once)"""
+    if not hasattr(__print_size_warning, 'has_printed'):
+        print("The image size needs to be a multiple of 4. "
+              "The loaded image size was (%d, %d), so it was adjusted to "
+              "(%d, %d). This adjustment will be done to all images "
+              "whose sizes are not multiples of 4" % (ow, oh, w, h))
+        __print_size_warning.has_printed = True

data/colorization_dataset.py

@@ -0,0 +1,68 @@
+import os
+from data.base_dataset import BaseDataset, get_transform
+from data.image_folder import make_dataset
+from skimage import color  # require skimage
+from PIL import Image
+import numpy as np
+import torchvision.transforms as transforms
+
+
+class ColorizationDataset(BaseDataset):
+    """This dataset class can load a set of natural images in RGB, and convert RGB format into (L, ab) pairs in Lab color space.
+
+    This dataset is required by pix2pix-based colorization model ('--model colorization')
+    """
+    @staticmethod
+    def modify_commandline_options(parser, is_train):
+        """Add new dataset-specific options, and rewrite default values for existing options.
+
+        Parameters:
+            parser          -- original option parser
+            is_train (bool) -- whether training phase or test phase. You can use this flag to add training-specific or test-specific options.
+
+        Returns:
+            the modified parser.
+
+        By default, the number of channels for input image  is 1 (L) and
+        the number of channels for output image is 2 (ab). The direction is from A to B
+        """
+        parser.set_defaults(input_nc=1, output_nc=2, direction='AtoB')
+        return parser
+
+    def __init__(self, opt):
+        """Initialize this dataset class.
+
+        Parameters:
+            opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
+        """
+        BaseDataset.__init__(self, opt)
+        self.dir = os.path.join(opt.dataroot, opt.phase)
+        self.AB_paths = sorted(make_dataset(self.dir, opt.max_dataset_size))
+        assert(opt.input_nc == 1 and opt.output_nc == 2 and opt.direction == 'AtoB')
+        self.transform = get_transform(self.opt, convert=False)
+
+    def __getitem__(self, index):
+        """Return a data point and its metadata information.
+
+        Parameters:
+            index - - a random integer for data indexing
+
+        Returns a dictionary that contains A, B, A_paths and B_paths
+            A (tensor) - - the L channel of an image
+            B (tensor) - - the ab channels of the same image
+            A_paths (str) - - image paths
+            B_paths (str) - - image paths (same as A_paths)
+        """
+        path = self.AB_paths[index]
+        im = Image.open(path).convert('RGB')
+        im = self.transform(im)
+        im = np.array(im)
+        lab = color.rgb2lab(im).astype(np.float32)
+        lab_t = transforms.ToTensor()(lab)
+        A = lab_t[[0], ...] / 50.0 - 1.0
+        B = lab_t[[1, 2], ...] / 110.0
+        return {'A': A, 'B': B, 'A_paths': path, 'B_paths': path}
+
+    def __len__(self):
+        """Return the total number of images in the dataset."""
+        return len(self.AB_paths)

data/image_folder.py

@@ -0,0 +1,65 @@
+"""A modified image folder class
+
+We modify the official PyTorch image folder (https://github.com/pytorch/vision/blob/master/torchvision/datasets/folder.py)
+so that this class can load images from both current directory and its subdirectories.
+"""
+
+import torch.utils.data as data
+
+from PIL import Image
+import os
+
+IMG_EXTENSIONS = [
+    '.jpg', '.JPG', '.jpeg', '.JPEG',
+    '.png', '.PNG', '.ppm', '.PPM', '.bmp', '.BMP',
+    '.tif', '.TIF', '.tiff', '.TIFF',
+]
+
+
+def is_image_file(filename):
+    return any(filename.endswith(extension) for extension in IMG_EXTENSIONS)
+
+
+def make_dataset(dir, max_dataset_size=float("inf")):
+    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[:min(max_dataset_size, len(images))]
+
+
+def default_loader(path):
+    return Image.open(path).convert('RGB')
+
+
+class ImageFolder(data.Dataset):
+
+    def __init__(self, root, transform=None, return_paths=False,
+                 loader=default_loader):
+        imgs = 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)

data/single_dataset.py

@@ -0,0 +1,40 @@
+from data.base_dataset import BaseDataset, get_transform
+from data.image_folder import make_dataset
+from PIL import Image
+
+
+class SingleDataset(BaseDataset):
+    """This dataset class can load a set of images specified by the path --dataroot /path/to/data.
+
+    It can be used for generating CycleGAN results only for one side with the model option '-model test'.
+    """
+
+    def __init__(self, opt):
+        """Initialize this dataset class.
+
+        Parameters:
+            opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
+        """
+        BaseDataset.__init__(self, opt)
+        self.A_paths = sorted(make_dataset(opt.dataroot, opt.max_dataset_size))
+        input_nc = self.opt.output_nc if self.opt.direction == 'BtoA' else self.opt.input_nc
+        self.transform = get_transform(opt, grayscale=(input_nc == 1))
+
+    def __getitem__(self, index):
+        """Return a data point and its metadata information.
+
+        Parameters:
+            index - - a random integer for data indexing
+
+        Returns a dictionary that contains A and A_paths
+            A(tensor) - - an image in one domain
+            A_paths(str) - - the path of the image
+        """
+        A_path = self.A_paths[index]
+        A_img = Image.open(A_path).convert('RGB')
+        A = self.transform(A_img)
+        return {'A': A, 'A_paths': A_path}
+
+    def __len__(self):
+        """Return the total number of images in the dataset."""
+        return len(self.A_paths)

data/template_dataset.py

@@ -0,0 +1,75 @@
+"""Dataset class template
+
+This module provides a template for users to implement custom datasets.
+You can specify '--dataset_mode template' to use this dataset.
+The class name should be consistent with both the filename and its dataset_mode option.
+The filename should be <dataset_mode>_dataset.py
+The class name should be <Dataset_mode>Dataset.py
+You need to implement the following functions:
+    -- <modify_commandline_options>:　Add dataset-specific options and rewrite default values for existing options.
+    -- <__init__>: Initialize this dataset class.
+    -- <__getitem__>: Return a data point and its metadata information.
+    -- <__len__>: Return the number of images.
+"""
+from data.base_dataset import BaseDataset, get_transform
+# from data.image_folder import make_dataset
+# from PIL import Image
+
+
+class TemplateDataset(BaseDataset):
+    """A template dataset class for you to implement custom datasets."""
+    @staticmethod
+    def modify_commandline_options(parser, is_train):
+        """Add new dataset-specific options, and rewrite default values for existing options.
+
+        Parameters:
+            parser          -- original option parser
+            is_train (bool) -- whether training phase or test phase. You can use this flag to add training-specific or test-specific options.
+
+        Returns:
+            the modified parser.
+        """
+        parser.add_argument('--new_dataset_option', type=float, default=1.0, help='new dataset option')
+        parser.set_defaults(max_dataset_size=10, new_dataset_option=2.0)  # specify dataset-specific default values
+        return parser
+
+    def __init__(self, opt):
+        """Initialize this dataset class.
+
+        Parameters:
+            opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
+
+        A few things can be done here.
+        - save the options (have been done in BaseDataset)
+        - get image paths and meta information of the dataset.
+        - define the image transformation.
+        """
+        # save the option and dataset root
+        BaseDataset.__init__(self, opt)
+        # get the image paths of your dataset;
+        self.image_paths = []  # You can call sorted(make_dataset(self.root, opt.max_dataset_size)) to get all the image paths under the directory self.root
+        # define the default transform function. You can use <base_dataset.get_transform>; You can also define your custom transform function
+        self.transform = get_transform(opt)
+
+    def __getitem__(self, index):
+        """Return a data point and its metadata information.
+
+        Parameters:
+            index -- a random integer for data indexing
+
+        Returns:
+            a dictionary of data with their names. It usually contains the data itself and its metadata information.
+
+        Step 1: get a random image path: e.g., path = self.image_paths[index]
+        Step 2: load your data from the disk: e.g., image = Image.open(path).convert('RGB').
+        Step 3: convert your data to a PyTorch tensor. You can use helpder functions such as self.transform. e.g., data = self.transform(image)
+        Step 4: return a data point as a dictionary.
+        """
+        path = 'temp'    # needs to be a string
+        data_A = None    # needs to be a tensor
+        data_B = None    # needs to be a tensor
+        return {'data_A': data_A, 'data_B': data_B, 'path': path}
+
+    def __len__(self):
+        """Return the total number of images."""
+        return len(self.image_paths)

data/unaligned_dataset.py

@@ -0,0 +1,71 @@
+import os
+from data.base_dataset import BaseDataset, get_transform
+from data.image_folder import make_dataset
+from PIL import Image
+import random
+
+
+class UnalignedDataset(BaseDataset):
+    """
+    This dataset class can load unaligned/unpaired datasets.
+
+    It requires two directories to host training images from domain A '/path/to/data/trainA'
+    and from domain B '/path/to/data/trainB' respectively.
+    You can train the model with the dataset flag '--dataroot /path/to/data'.
+    Similarly, you need to prepare two directories:
+    '/path/to/data/testA' and '/path/to/data/testB' during test time.
+    """
+
+    def __init__(self, opt):
+        """Initialize this dataset class.
+
+        Parameters:
+            opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
+        """
+        BaseDataset.__init__(self, opt)
+        self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')  # create a path '/path/to/data/trainA'
+        self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')  # create a path '/path/to/data/trainB'
+
+        self.A_paths = sorted(make_dataset(self.dir_A, opt.max_dataset_size))   # load images from '/path/to/data/trainA'
+        self.B_paths = sorted(make_dataset(self.dir_B, opt.max_dataset_size))    # load images from '/path/to/data/trainB'
+        self.A_size = len(self.A_paths)  # get the size of dataset A
+        self.B_size = len(self.B_paths)  # get the size of dataset B
+        btoA = self.opt.direction == 'BtoA'
+        input_nc = self.opt.output_nc if btoA else self.opt.input_nc       # get the number of channels of input image
+        output_nc = self.opt.input_nc if btoA else self.opt.output_nc      # get the number of channels of output image
+        self.transform_A = get_transform(self.opt, grayscale=(input_nc == 1))
+        self.transform_B = get_transform(self.opt, grayscale=(output_nc == 1))
+
+    def __getitem__(self, index):
+        """Return a data point and its metadata information.
+
+        Parameters:
+            index (int)      -- a random integer for data indexing
+
+        Returns a dictionary that contains A, B, A_paths and B_paths
+            A (tensor)       -- an image in the input domain
+            B (tensor)       -- its corresponding image in the target domain
+            A_paths (str)    -- image paths
+            B_paths (str)    -- image paths
+        """
+        A_path = self.A_paths[index % self.A_size]  # make sure index is within then range
+        if self.opt.serial_batches:   # make sure index is within then range
+            index_B = index % self.B_size
+        else:   # randomize the index for domain B to avoid fixed pairs.
+            index_B = random.randint(0, self.B_size - 1)
+        B_path = self.B_paths[index_B]
+        A_img = Image.open(A_path).convert('RGB')
+        B_img = Image.open(B_path).convert('RGB')
+        # apply image transformation
+        A = self.transform_A(A_img)
+        B = self.transform_B(B_img)
+
+        return {'A': A, 'B': B, 'A_paths': A_path, 'B_paths': B_path}
+
+    def __len__(self):
+        """Return the total number of images in the dataset.
+
+        As we have two datasets with potentially different number of images,
+        we take a maximum of
+        """
+        return max(self.A_size, self.B_size)