Pytorch數據變換（Transform）

實例化數據庫的時候，有一個可選的參數可以對數據進行轉換，滿足大多神經網絡的要求輸入固定尺寸的圖片，因此要對原圖進行Rescale或者Crop操作，然后返回的數據需要轉換成Tensor如：

import FaceLandmarksDataset
face_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv',
                                    root_dir='data/faces/',
                                    transform=transforms.Compose([ Rescale(256), RandomCrop(224), ToTensor()]) )

數據轉換（Transfrom）發生在數據庫中的__getitem__操作中。以上代碼中，transforms.Compose(transform_list)，Compose即組合的意思，其參數是一個轉換操作的列表。如上是[ Rescale(256), RandomCrop(224), ToTensor()]，以下是實現這三個轉換類。我們將把它們寫成可調用的類，而不是簡單的函數，這樣在每次調用轉換時就不需要傳遞它的參數。為此，我們只需要實現__call__方法，如果需要，還需要實現__init__方法。然后我們可以使用這樣的變換:

 

#創建一個轉換可調用類的實例
tsfm = Transform(params)
#使用轉換操作實例對樣本sample進行轉換
transformed_sample = tsfm(sample)

 

下面觀察這些轉換是如何應用於圖像和標注的。（注：每一個操作對應一個類）

class Rescale(object):
    """Rescale the image in a sample to a given size.

    Args:
        output_size (tuple or int): Desired output size. If tuple, output is
            matched to output_size. If int, smaller of image edges is matched
            to output_size keeping aspect ratio the same.
    """

    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        self.output_size = output_size

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        h, w = image.shape[:2]
        if isinstance(self.output_size, int):
            if h > w:
                new_h, new_w = self.output_size * h / w, self.output_size
            else:
                new_h, new_w = self.output_size, self.output_size * w / h
        else:
            new_h, new_w = self.output_size

        new_h, new_w = int(new_h), int(new_w)

        img = transform.resize(image, (new_h, new_w))

        # h and w are swapped for landmarks because for images,
        # x and y axes are axis 1 and 0 respectively
        landmarks = landmarks * [new_w / w, new_h / h]

        return {'image': img, 'landmarks': landmarks}


class RandomCrop(object):
    """Crop randomly the image in a sample.

    Args:
        output_size (tuple or int): Desired output size. If int, square crop
            is made.
    """

    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        if isinstance(output_size, int):
            self.output_size = (output_size, output_size)
        else:
            assert len(output_size) == 2
            self.output_size = output_size

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        h, w = image.shape[:2]
        new_h, new_w = self.output_size

        top = np.random.randint(0, h - new_h)
        left = np.random.randint(0, w - new_w)

        image = image[top: top + new_h,
                      left: left + new_w]

        landmarks = landmarks - [left, top]

        return {'image': image, 'landmarks': landmarks}


class ToTensor(object):
    """Convert ndarrays in sample to Tensors."""

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        # swap color axis because
        # numpy image: H x W x C
        # torch image: C X H X W
        image = image.transpose((2, 0, 1))
        return {'image': torch.from_numpy(image),
                'landmarks': torch.from_numpy(landmarks)}

以下來介紹轉換的用法。

#獲取一條數據
sample = face_dataset[index]
#單獨進行操作
scale = Rescale(256)
crope= RandomCrop(224)
scale(sample)
crope(sample)
#使用Compose組合操作
compose = transforms.Compose([Rescale(256),RandomCrop(224)])
compose(sample)

上述轉換后數據仍然是PIL類型，如果要求返回是一個tensor,那么還得在Compose的最后一個元素進行Totensor操作。