pytorch-image-models/timm/data/transforms.py

import torch
import torchvision.transforms.functional as F
from torchvision.transforms import InterpolationMode

import warnings
import math
import random
import numpy as np


class ToNumpy:

    def __call__(self, pil_img):
        np_img = np.array(pil_img, dtype=np.uint8)
        if np_img.ndim < 3:
            np_img = np.expand_dims(np_img, axis=-1)
        np_img = np.rollaxis(np_img, 2)  # HWC to CHW
        return np_img


class ToTensor:

    def __init__(self, dtype=torch.float32):
        self.dtype = dtype

    def __call__(self, pil_img):
        np_img = np.array(pil_img, dtype=np.uint8)
        if np_img.ndim < 3:
            np_img = np.expand_dims(np_img, axis=-1)
        np_img = np.rollaxis(np_img, 2)  # HWC to CHW
        return torch.from_numpy(np_img).to(dtype=self.dtype)


class ToTensorNormalize:

    def __init__(self, mean, std, dtype=torch.float32, device=torch.device('cpu')):
        self.dtype = dtype
        mean = torch.as_tensor(mean, dtype=dtype, device=device)
        std = torch.as_tensor(std, dtype=dtype, device=device)
        if (std == 0).any():
            raise ValueError('std evaluated to zero after conversion to {}, leading to division by zero.'.format(dtype))
        if mean.ndim == 1:
            mean = mean.view(-1, 1, 1)
        if std.ndim == 1:
            std = std.view(-1, 1, 1)
        self.mean = mean
        self.std = std

    def __call__(self, pil_img):
        mode_to_nptype = {'I': np.int32, 'I;16': np.int16, 'F': np.float32}
        img = torch.from_numpy(
            np.array(pil_img, mode_to_nptype.get(pil_img.mode, np.uint8))
        )
        if pil_img.mode == '1':
            img = 255 * img
        img = img.view(pil_img.size[1], pil_img.size[0], len(pil_img.getbands()))
        img = img.permute((2, 0, 1))
        if isinstance(img, torch.ByteTensor):
            img = img.to(self.dtype)
            img.sub_(self.mean * 255.).div_(self.std * 255.)
        else:
            img = img.to(self.dtype)
            img.sub_(self.mean).div_(self.std)
        return img


_RANDOM_INTERPOLATION = (InterpolationMode.BILINEAR, InterpolationMode.BICUBIC)


class RandomResizedCropAndInterpolation:
    """Crop the given PIL Image to random size and aspect ratio with random interpolation.

    A crop of random size (default: of 0.08 to 1.0) of the original size and a random
    aspect ratio (default: of 3/4 to 4/3) of the original aspect ratio is made. This crop
    is finally resized to given size.
    This is popularly used to train the Inception networks.

    Args:
        size: expected output size of each edge
        scale: range of size of the origin size cropped
        ratio: range of aspect ratio of the origin aspect ratio cropped
        interpolation: Default: PIL.Image.BILINEAR
    """

    def __init__(self, size, scale=(0.08, 1.0), ratio=(3. / 4., 4. / 3.),
                 interpolation='bilinear'):
        if isinstance(size, (list, tuple)):
            self.size = tuple(size)
        else:
            self.size = (size, size)
        if (scale[0] > scale[1]) or (ratio[0] > ratio[1]):
            warnings.warn("range should be of kind (min, max)")

        if interpolation == 'random':
            self.interpolation = _RANDOM_INTERPOLATION
        else:
            self.interpolation = InterpolationMode(interpolation)
        self.scale = scale
        self.ratio = ratio

    @staticmethod
    def get_params(img, scale, ratio):
        """Get parameters for ``crop`` for a random sized crop.

        Args:
            img (PIL Image): Image to be cropped.
            scale (tuple): range of size of the origin size cropped
            ratio (tuple): range of aspect ratio of the origin aspect ratio cropped

        Returns:
            tuple: params (i, j, h, w) to be passed to ``crop`` for a random
                sized crop.
        """
        area = img.size[0] * img.size[1]

        for attempt in range(10):
            target_area = random.uniform(*scale) * area
            log_ratio = (math.log(ratio[0]), math.log(ratio[1]))
            aspect_ratio = math.exp(random.uniform(*log_ratio))

            w = int(round(math.sqrt(target_area * aspect_ratio)))
            h = int(round(math.sqrt(target_area / aspect_ratio)))

            if w <= img.size[0] and h <= img.size[1]:
                i = random.randint(0, img.size[1] - h)
                j = random.randint(0, img.size[0] - w)
                return i, j, h, w

        # Fallback to central crop
        in_ratio = img.size[0] / img.size[1]
        if in_ratio < min(ratio):
            w = img.size[0]
            h = int(round(w / min(ratio)))
        elif in_ratio > max(ratio):
            h = img.size[1]
            w = int(round(h * max(ratio)))
        else:  # whole image
            w = img.size[0]
            h = img.size[1]
        i = (img.size[1] - h) // 2
        j = (img.size[0] - w) // 2
        return i, j, h, w

    def __call__(self, img):
        """
        Args:
            img (PIL Image): Image to be cropped and resized.

        Returns:
            PIL Image: Randomly cropped and resized image.
        """
        i, j, h, w = self.get_params(img, self.scale, self.ratio)
        if isinstance(self.interpolation, (tuple, list)):
            interpolation = random.choice(self.interpolation)
        else:
            interpolation = self.interpolation
        return F.resized_crop(img, i, j, h, w, self.size, interpolation)

    def __repr__(self):
        if isinstance(self.interpolation, (tuple, list)):
            interpolate_str = ' '.join([x.value for x in self.interpolation])
        else:
            interpolate_str = self.interpolation.value
        format_string = self.__class__.__name__ + '(size={0}'.format(self.size)
        format_string += ', scale={0}'.format(tuple(round(s, 4) for s in self.scale))
        format_string += ', ratio={0}'.format(tuple(round(r, 4) for r in self.ratio))
        format_string += ', interpolation={0})'.format(interpolate_str)
        return format_string