utils.py

from typing import Union, Optional, List, Tuple, Text, BinaryIO
import pathlib
import torch
import math
import numpy as np
from PIL import Image, ImageDraw
from PIL import ImageFont

__all__ = ["make_grid", "save_image", "draw_bounding_boxes"]

irange = range


def make_grid(
    tensor: Union[torch.Tensor, List[torch.Tensor]],
    nrow: int = 8,
    padding: int = 2,
    normalize: bool = False,
    range: Optional[Tuple[int, int]] = None,
    scale_each: bool = False,
    pad_value: int = 0,
) -> torch.Tensor:
    """Make a grid of images.

    Args:
        tensor (Tensor or list): 4D mini-batch Tensor of shape (B x C x H x W)
            or a list of images all of the same size.
        nrow (int, optional): Number of images displayed in each row of the grid.
            The final grid size is ``(B / nrow, nrow)``. Default: ``8``.
        padding (int, optional): amount of padding. Default: ``2``.
        normalize (bool, optional): If True, shift the image to the range (0, 1),
            by the min and max values specified by :attr:`range`. Default: ``False``.
        range (tuple, optional): tuple (min, max) where min and max are numbers,
            then these numbers are used to normalize the image. By default, min and max
            are computed from the tensor.
        scale_each (bool, optional): If ``True``, scale each image in the batch of
            images separately rather than the (min, max) over all images. Default: ``False``.
        pad_value (float, optional): Value for the padded pixels. Default: ``0``.

    Example:
        See this notebook `here <https://gist.github.com/anonymous/bf16430f7750c023141c562f3e9f2a91>`_

    """
    if not (torch.is_tensor(tensor) or
            (isinstance(tensor, list) and all(torch.is_tensor(t) for t in tensor))):
        raise TypeError('tensor or list of tensors expected, got {}'.format(type(tensor)))

    # if list of tensors, convert to a 4D mini-batch Tensor
    if isinstance(tensor, list):
        tensor = torch.stack(tensor, dim=0)

    if tensor.dim() == 2:  # single image H x W
        tensor = tensor.unsqueeze(0)
    if tensor.dim() == 3:  # single image
        if tensor.size(0) == 1:  # if single-channel, convert to 3-channel
            tensor = torch.cat((tensor, tensor, tensor), 0)
        tensor = tensor.unsqueeze(0)

    if tensor.dim() == 4 and tensor.size(1) == 1:  # single-channel images
        tensor = torch.cat((tensor, tensor, tensor), 1)

    if normalize is True:
        tensor = tensor.clone()  # avoid modifying tensor in-place
        if range is not None:
            assert isinstance(range, tuple), \
                "range has to be a tuple (min, max) if specified. min and max are numbers"

        def norm_ip(img, low, high):
            img.clamp_(min=low, max=high)
            img.sub_(low).div_(max(high - low, 1e-5))

        def norm_range(t, range):
            if range is not None:
                norm_ip(t, range[0], range[1])
            else:
                norm_ip(t, float(t.min()), float(t.max()))

        if scale_each is True:
            for t in tensor:  # loop over mini-batch dimension
                norm_range(t, range)
        else:
            norm_range(tensor, range)

    if tensor.size(0) == 1:
        return tensor.squeeze(0)

    # make the mini-batch of images into a grid
    nmaps = tensor.size(0)
    xmaps = min(nrow, nmaps)
    ymaps = int(math.ceil(float(nmaps) / xmaps))
    height, width = int(tensor.size(2) + padding), int(tensor.size(3) + padding)
    num_channels = tensor.size(1)
    grid = tensor.new_full((num_channels, height * ymaps + padding, width * xmaps + padding), pad_value)
    k = 0
    for y in irange(ymaps):
        for x in irange(xmaps):
            if k >= nmaps:
                break
            # Tensor.copy_() is a valid method but seems to be missing from the stubs
            # https://pytorch.org/docs/stable/tensors.html#torch.Tensor.copy_
            grid.narrow(1, y * height + padding, height - padding).narrow(  # type: ignore[attr-defined]
                2, x * width + padding, width - padding
            ).copy_(tensor[k])
            k = k + 1
    return grid


def save_image(
    tensor: Union[torch.Tensor, List[torch.Tensor]],
    fp: Union[Text, pathlib.Path, BinaryIO],
    nrow: int = 8,
    padding: int = 2,
    normalize: bool = False,
    range: Optional[Tuple[int, int]] = None,
    scale_each: bool = False,
    pad_value: int = 0,
    format: Optional[str] = None,
) -> None:
    """Save a given Tensor into an image file.

    Args:
        tensor (Tensor or list): Image to be saved. If given a mini-batch tensor,
            saves the tensor as a grid of images by calling ``make_grid``.
        fp (string or file object): A filename or a file object
        format(Optional):  If omitted, the format to use is determined from the filename extension.
            If a file object was used instead of a filename, this parameter should always be used.
        **kwargs: Other arguments are documented in ``make_grid``.
    """
    grid = make_grid(tensor, nrow=nrow, padding=padding, pad_value=pad_value,
                     normalize=normalize, range=range, scale_each=scale_each)
    # Add 0.5 after unnormalizing to [0, 255] to round to nearest integer
    ndarr = grid.mul(255).add_(0.5).clamp_(0, 255).permute(1, 2, 0).to('cpu', torch.uint8).numpy()
    im = Image.fromarray(ndarr)
    im.save(fp, format=format)


@torch.no_grad()
def draw_bounding_boxes(
    image: torch.Tensor,
    boxes: torch.Tensor,
    labels: Optional[List[str]] = None,
    colors: Optional[List[Union[str, Tuple[int, int, int]]]] = None,
    width: int = 1,
    font: Optional[str] = None,
    font_size: int = 10
) -> torch.Tensor:

    """
    Draws bounding boxes on given image.
    The values of the input image should be uint8 between 0 and 255.

    Args:
        image (Tensor): Tensor of shape (C x H x W)
        bboxes (Tensor): Tensor of size (N, 4) containing bounding boxes in (xmin, ymin, xmax, ymax) format. Note that
            the boxes are absolute coordinates with respect to the image. In other words: `0 <= xmin < xmax < W` and
            `0 <= ymin < ymax < H`.
        labels (List[str]): List containing the labels of bounding boxes.
        colors (List[Union[str, Tuple[int, int, int]]]): List containing the colors of bounding boxes. The colors can
            be represented as `str` or `Tuple[int, int, int]`.
        width (int): Width of bounding box.
        font (str): A filename containing a TrueType font. If the file is not found in this filename, the loader may
            also search in other directories, such as the `fonts/` directory on Windows or `/Library/Fonts/`,
            `/System/Library/Fonts/` and `~/Library/Fonts/` on macOS.
        font_size (int): The requested font size in points.
    """

    if not isinstance(image, torch.Tensor):
        raise TypeError(f"Tensor expected, got {type(image)}")
    elif image.dtype != torch.uint8:
        raise ValueError(f"Tensor uint8 expected, got {image.dtype}")
    elif image.dim() != 3:
        raise ValueError("Pass individual images, not batches")

    ndarr = image.permute(1, 2, 0).numpy()
    img_to_draw = Image.fromarray(ndarr)

    img_boxes = boxes.to(torch.int64).tolist()

    draw = ImageDraw.Draw(img_to_draw)
    txt_font = ImageFont.load_default() if font is None else ImageFont.truetype(font=font, size=font_size)

    for i, bbox in enumerate(img_boxes):
        color = None if colors is None else colors[i]
        draw.rectangle(bbox, width=width, outline=color)

        if labels is not None:
            draw.text((bbox[0], bbox[1]), labels[i], fill=color, font=txt_font)

    return torch.from_numpy(np.array(img_to_draw)).permute(2, 0, 1)