【SwinTransformer源码阅读一】build_loader部分代码

最近打算认真看下SwinTransformer算法,这里记录下今天看的build_loader部分的代码,步骤均加了汉语注释,希望可以帮到一些正在学习的朋友。

前言

build_loader是Swin Transformer代码中main.py的第一句,所以这里主要记录下Swin Transformer加载数据的过程。

【SwinTransformer源码阅读一】build_loader部分代码_第1张图片
在swin tranformer 中,数据预处理部分是在下面的文件夹中
【SwinTransformer源码阅读一】build_loader部分代码_第2张图片

build.py

try:
    from torchvision.transforms import InterpolationMode


    def _pil_interp(method):
        if method == 'bicubic':
            return InterpolationMode.BICUBIC
        elif method == 'lanczos':
            return InterpolationMode.LANCZOS
        elif method == 'hamming':
            return InterpolationMode.HAMMING
        else:
            # default bilinear, do we want to allow nearest?
            return InterpolationMode.BILINEAR


    import timm.data.transforms as timm_transforms

    timm_transforms._pil_interp = _pil_interp
except:
    from timm.data.transforms import _pil_interp

#建立数据加载器
def build_loader(config):
    #配置文件解冻 这一步是方便后续对配置文件config.MODEL.NUM_CLASSES 的更改
    config.defrost()
    #加载训练集
    dataset_train, config.MODEL.NUM_CLASSES = build_dataset(is_train=True, config=config)
    config.freeze()#配置文件锁
    print(f"local rank {config.LOCAL_RANK} / global rank {dist.get_rank()} successfully build train dataset")
    dataset_val, _ = build_dataset(is_train=False, config=config)#验证数据集
    print(f"local rank {config.LOCAL_RANK} / global rank {dist.get_rank()} successfully build val dataset")
    #分布式训练所需参数
    num_tasks = dist.get_world_size()
    global_rank = dist.get_rank()
    # 缓存模式为 part 即只取部分数据的情况
    if config.DATA.ZIP_MODE and config.DATA.CACHE_MODE == 'part':
        indices = np.arange(dist.get_rank(), len(dataset_train), dist.get_world_size())
        sampler_train = SubsetRandomSampler(indices)
    else:
        #将数据集均匀分散在不同的GPU上
        # 比如 GPU0:[0,2,4,6,8] GPU1:[1,3,5,7..]
        sampler_train = torch.utils.data.DistributedSampler(
            dataset_train, num_replicas=num_tasks, rank=global_rank, shuffle=True
        )
    #测试时候是否为顺序采样,即每次采样均为 0,1,2...顺序
    if config.TEST.SEQUENTIAL:
        sampler_val = torch.utils.data.SequentialSampler(dataset_val)
    else:
        #分布式采样
        sampler_val = torch.utils.data.distributed.DistributedSampler(
            dataset_val, shuffle=config.TEST.SHUFFLE
        )
    #训练集数据加载器
    data_loader_train = torch.utils.data.DataLoader(
        dataset_train, sampler=sampler_train,
        batch_size=config.DATA.BATCH_SIZE,
        num_workers=config.DATA.NUM_WORKERS,
        pin_memory=config.DATA.PIN_MEMORY,
        drop_last=True,
    )
    #验证集数据加载器
    data_loader_val = torch.utils.data.DataLoader(
        dataset_val, sampler=sampler_val,
        batch_size=config.DATA.BATCH_SIZE,
        shuffle=False,
        num_workers=config.DATA.NUM_WORKERS,
        pin_memory=config.DATA.PIN_MEMORY,
        drop_last=False
    )

    # setup mixup / cutmix
    mixup_fn = None
    # true
    mixup_active = config.AUG.MIXUP > 0 or config.AUG.CUTMIX > 0. or config.AUG.CUTMIX_MINMAX is not None
    if mixup_active: 
        mixup_fn = Mixup(
            mixup_alpha=config.AUG.MIXUP, cutmix_alpha=config.AUG.CUTMIX, cutmix_minmax=config.AUG.CUTMIX_MINMAX,
            prob=config.AUG.MIXUP_PROB, switch_prob=config.AUG.MIXUP_SWITCH_PROB, mode=config.AUG.MIXUP_MODE,
            label_smoothing=config.MODEL.LABEL_SMOOTHING, num_classes=config.MODEL.NUM_CLASSES)

    return dataset_train, dataset_val, data_loader_train, data_loader_val, mixup_fn

#建立数据集
#is_train : true:train dataset false:val dataset
def build_dataset(is_train, config):
    #进行数据变换
    transform = build_transform(is_train, config)
    #依据不同的数据格式进行划分数据
    if config.DATA.DATASET == 'imagenet':
        prefix = 'train' if is_train else 'val'
        #如果使用的是zip格式的数据集 具体可以参看 get_start.md的数据集例子
        if config.DATA.ZIP_MODE:
            ann_file = prefix + "_map.txt"
            prefix = prefix + ".zip@/"
            dataset = CachedImageFolder(config.DATA.DATA_PATH, ann_file, prefix, transform,
                                        cache_mode=config.DATA.CACHE_MODE if is_train else 'part')
        else:
            root = os.path.join(config.DATA.DATA_PATH, prefix)
            dataset = datasets.ImageFolder(root, transform=transform)
        nb_classes = 1000#数据的类别
    elif config.DATA.DATASET == 'imagenet22K':
        prefix = 'ILSVRC2011fall_whole'
        if is_train:
            ann_file = prefix + "_map_train.txt"
        else:
            ann_file = prefix + "_map_val.txt"
        dataset = IN22KDATASET(config.DATA.DATA_PATH, ann_file, transform)
        nb_classes = 21841
    else:
        raise NotImplementedError("We only support ImageNet Now.")

    return dataset, nb_classes

#数据变换 预处理
def build_transform(is_train, config):
    #判断输入图像尺寸大小是否大于32 相关配置在 config.py 中
    resize_im = config.DATA.IMG_SIZE > 32
    if is_train:
        # this should always dispatch to transforms_imagenet_train
        #相关参数可以在 config.py 找到
        transform = create_transform(
            input_size=config.DATA.IMG_SIZE,
            is_training=True,
            color_jitter=config.AUG.COLOR_JITTER if config.AUG.COLOR_JITTER > 0 else None,
            auto_augment=config.AUG.AUTO_AUGMENT if config.AUG.AUTO_AUGMENT != 'none' else None,
            re_prob=config.AUG.REPROB,
            re_mode=config.AUG.REMODE,
            re_count=config.AUG.RECOUNT,
            interpolation=config.DATA.INTERPOLATION,
        )
        #如果输入图像大小过小  则采用随即裁剪的方式
        if not resize_im:
            # replace RandomResizedCropAndInterpolation with
            # RandomCrop
            transform.transforms[0] = transforms.RandomCrop(config.DATA.IMG_SIZE, padding=4)
        return transform
    # 非训练数据集的扩增方式
    t = []
    if resize_im:
        #如果测试过程中使用中心裁剪 先放大输入图像的尺寸 再中心裁剪
        #否则直接使用对应的插值策略进行设置输入图像大小
        if config.TEST.CROP:
            size = int((256 / 224) * config.DATA.IMG_SIZE)
            t.append(
                transforms.Resize(size, interpolation=_pil_interp(config.DATA.INTERPOLATION)),
                # to maintain same ratio w.r.t. 224 images
            )
            t.append(transforms.CenterCrop(config.DATA.IMG_SIZE))
        else:
            t.append(
                transforms.Resize((config.DATA.IMG_SIZE, config.DATA.IMG_SIZE),
                                  interpolation=_pil_interp(config.DATA.INTERPOLATION))
            )

    t.append(transforms.ToTensor())#将数据转为 tensor类型 (H*W*C)->(C*H*W)
    #进行归一化
    t.append(transforms.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD))
    return transforms.Compose(t)#把多个数据处理步骤整合到一起

cached_image_folder.py


import io
import os
import time
import torch.distributed as dist
import torch.utils.data as data
from PIL import Image

from .zipreader import is_zip_path, ZipReader

#检验文件是否符合所要求的文件后缀格式
def has_file_allowed_extension(filename, extensions):
    """Checks if a file is an allowed extension.
    Args:
        filename (string): path to a file
    Returns:
        bool: True if the filename ends with a known image extension
    """
    filename_lower = filename.lower()
    return any(filename_lower.endswith(ext) for ext in extensions)

#获得数据集中的种类
def find_classes(dir):
    #通过数据集文件夹下的子文件夹名称来获取类名
    classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]
    classes.sort()#进行类名排序
    #将类名进行映射为从0开始的类别索引 {类名:类索引}
    class_to_idx = {classes[i]: i for i in range(len(classes))}
    #返回类别列表和类别索引字典
    return classes, class_to_idx

#获取数据集中的所有图像数据
def make_dataset(dir, class_to_idx, extensions):
    images = []
    #如果是"~"开始的则进入系统根目录,如果不为"~"开头的则保持原路径
    dir = os.path.expanduser(dir)
    #获取文件列表
    for target in sorted(os.listdir(dir)):
        d = os.path.join(dir, target)
        #如果不为文件夹则跳过
        if not os.path.isdir(d):
            continue
        #便利文件子文件夹
        for root, _, fnames in sorted(os.walk(d)):
            for fname in sorted(fnames):#遍历所有文件
                #判断文件后缀是否正确
                if has_file_allowed_extension(fname, extensions):
                    #图片的绝对路径
                    path = os.path.join(root, fname)
                    #构建图片路径和类别索引元组
                    item = (path, class_to_idx[target])
                    images.append(item)
    #返回images列表 元素为图片路径和类别索引元组
    #[("./img1.jpg",0),("./img2.jpg",0),...]
    return images

#生成带有标注文件的图像列表
def make_dataset_with_ann(ann_file, img_prefix, extensions):
    images = []
    #读取标注文件
    with open(ann_file, "r") as f:
        contents = f.readlines()#读取所有的行
        #遍历内容列表
        for line_str in contents:
            # 遍历每一行的内容("\t")划分
            path_contents = [c for c in line_str.split('\t')]
            im_file_name = path_contents[0]#图片名字
            class_index = int(path_contents[1])#图片所属类别
            #判断文件后缀是否正确
            assert str.lower(os.path.splitext(im_file_name)[-1]) in extensions
            #构建图片路径和类别索引元组
            item = (os.path.join(img_prefix, im_file_name), class_index)

            images.append(item)
    #返回images列表 元素为图片路径和类别索引元组
    #[("./img1.jpg",0),("./img2.jpg",0),...]
    return images


class DatasetFolder(data.Dataset):
    """A generic data loader where the samples are arranged in this way: ::
        root/class_x/xxx.ext
        root/class_x/xxy.ext
        root/class_x/xxz.ext
        root/class_y/123.ext
        root/class_y/nsdf3.ext
        root/class_y/asd932_.ext
    Args:
        root (string): Root directory path.
        loader (callable): A function to load a sample given its path.
        extensions (list[string]): A list of allowed extensions.
        transform (callable, optional): A function/transform that takes in
            a sample and returns a transformed version.
            E.g, ``transforms.RandomCrop`` for images.
        target_transform (callable, optional): A function/transform that takes
            in the target and transforms it.
     Attributes:
        samples (list): List of (sample path, class_index) tuples
    """

    def __init__(self, root, loader, extensions, ann_file='', img_prefix='', transform=None, target_transform=None,
                 cache_mode="no"):
        #根据不同数据集类型读取数据
        # image folder mode
        if ann_file == '':
            _, class_to_idx = find_classes(root)
            samples = make_dataset(root, class_to_idx, extensions)
        # zip mode
        else:
            samples = make_dataset_with_ann(os.path.join(root, ann_file),
                                            os.path.join(root, img_prefix),
                                            extensions)

        if len(samples) == 0:
            raise (RuntimeError("Found 0 files in subfolders of: " + root + "\n" +
                                "Supported extensions are: " + ",".join(extensions)))

        self.root = root
        self.loader = loader#声明加载器
        self.extensions = extensions
        #samples为images列表 元素为图片路径和类别索引元组
        #[("./img1.jpg",0),("./img2.jpg",0),...]
        self.samples = samples
        self.labels = [y_1k for _, y_1k in samples]#得到样本的类别索引
        self.classes = list(set(self.labels))#去重并构建类别索引列表

        self.transform = transform#样本的数据变换策略
        self.target_transform = target_transform#类标数据的变换

        self.cache_mode = cache_mode
        if self.cache_mode != "no":
            self.init_cache()

    def init_cache(self):
        assert self.cache_mode in ["part", "full"]
        n_sample = len(self.samples)#获取图像的数量
        #分布式采样
        global_rank = dist.get_rank()
        world_size = dist.get_world_size()
        #声明一个与样本数量同样大小的数据列表 默认为None
        samples_bytes = [None for _ in range(n_sample)]
        start_time = time.time()#记录开始时间
        for index in range(n_sample):
            # 每n_sample // 10个样本为一个数据缓存块
            if index % (n_sample // 10) == 0:
                t = time.time() - start_time
                print(f'global_rank {dist.get_rank()} cached {index}/{n_sample} takes {t:.2f}s per block')
                start_time = time.time()
            path, target = self.samples[index]#path路径和类别索引
            if self.cache_mode == "full":
                samples_bytes[index] = (ZipReader.read(path), target)
            elif self.cache_mode == "part" and index % world_size == global_rank:
                samples_bytes[index] = (ZipReader.read(path), target)
            else:
                samples_bytes[index] = (path, target)
        self.samples = samples_bytes#[(path1, 0),(path2, 1),...]
    #返回变换过的图像数据和类标
    def __getitem__(self, index):
        """
        Args:
            index (int): Index
        Returns:
            tuple: (sample, target) where target is class_index of the target class.
        """
        path, target = self.samples[index]
        sample = self.loader(path)
        if self.transform is not None:
            sample = self.transform(sample)
        if self.target_transform is not None:
            target = self.target_transform(target)

        return sample, target

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

    def __repr__(self):
        fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
        fmt_str += '    Number of datapoints: {}\n'.format(self.__len__())
        fmt_str += '    Root Location: {}\n'.format(self.root)
        tmp = '    Transforms (if any): '
        fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
        tmp = '    Target Transforms (if any): '
        fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
        return fmt_str


IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif']

#根据路径打开图片 并转为RGB
def pil_loader(path):
    # open path as file to avoid ResourceWarning (https://github.com/python-pillow/Pillow/issues/835)
    if isinstance(path, bytes):
        img = Image.open(io.BytesIO(path))
    elif is_zip_path(path):
        data = ZipReader.read(path)
        img = Image.open(io.BytesIO(data))
    else:
        with open(path, 'rb') as f:
            img = Image.open(f)
            return img.convert('RGB')
    return img.convert('RGB')

#使用accimage 进行加载图像数据(是比PIL Image更快的一种库)
def accimage_loader(path):
    import accimage
    try:
        return accimage.Image(path)
    except IOError:
        # Potentially a decoding problem, fall back to PIL.Image
        return pil_loader(path)


def default_img_loader(path):
    from torchvision import get_image_backend
    if get_image_backend() == 'accimage':
        return accimage_loader(path)
    else:
        return pil_loader(path)

#DatasetFolder的继承类
class CachedImageFolder(DatasetFolder):
    """A generic data loader where the images are arranged in this way: ::
        root/dog/xxx.png
        root/dog/xxy.png
        root/dog/xxz.png
        root/cat/123.png
        root/cat/nsdf3.png
        root/cat/asd932_.png
    Args:
        root (string): Root directory path.
        transform (callable, optional): A function/transform that  takes in an PIL image
            and returns a transformed version. E.g, ``transforms.RandomCrop``
        target_transform (callable, optional): A function/transform that takes in the
            target and transforms it.
        loader (callable, optional): A function to load an image given its path.
     Attributes:
        imgs (list): List of (image path, class_index) tuples
    """

    def __init__(self, root, ann_file='', img_prefix='', transform=None, target_transform=None,
                 loader=default_img_loader, cache_mode="no"):
        super(CachedImageFolder, self).__init__(root, loader, IMG_EXTENSIONS,
                                                ann_file=ann_file, img_prefix=img_prefix,
                                                transform=transform, target_transform=target_transform,
                                                cache_mode=cache_mode)
        self.imgs = self.samples

    def __getitem__(self, index):
        """
        Args:
            index (int): Index
        Returns:
            tuple: (image, target) where target is class_index of the target class.
        """
        path, target = self.samples[index]
        image = self.loader(path)
        if self.transform is not None:
            img = self.transform(image)
        else:
            img = image
        if self.target_transform is not None:
            target = self.target_transform(target)

        return img, target

你可能感兴趣的:(Python,机器学习,目标检测,深度学习,python,人工智能)