Source code for cvpods.structures.boxes

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
import math
from enum import IntEnum, unique
from typing import Iterator, List, Tuple, Union

import numpy as np

import torch
from torchvision.ops.boxes import box_area

from cvpods.layers import cat

_RawBoxType = Union[List[float], Tuple[float, ...], torch.Tensor, np.ndarray]


[docs]@unique class BoxMode(IntEnum): """ Enum of different ways to represent a box. Attributes: XYXY_ABS: (x0, y0, x1, y1) in absolute floating points coordinates. The coordinates in range [0, width or height]. XYWH_ABS: (x0, y0, w, h) in absolute floating points coordinates. XYXY_REL: (x0, y0, x1, y1) in range [0, 1]. They are relative to the size of the image. XYWH_REL: (x0, y0, w, h) in range [0, 1]. They are relative to the size of the image. XYWHA_ABS: (xc, yc, w, h, a) in absolute floating points coordinates. (xc, yc) is the center of the rotated box, and the angle a is in degrees ccw. """ XYXY_ABS = 0 XYWH_ABS = 1 XYXY_REL = 2 XYWH_REL = 3 XYWHA_ABS = 4
[docs] @staticmethod def convert(box: _RawBoxType, from_mode: "BoxMode", to_mode: "BoxMode") -> _RawBoxType: """ Args: box: can be a k-tuple, k-list or an Nxk array/tensor, where k = 4 or 5 from_mode, to_mode (BoxMode) Returns: The converted box of the same type. """ if from_mode == to_mode: return box original_type = type(box) is_numpy = isinstance(box, np.ndarray) single_box = isinstance(box, (list, tuple)) if single_box: assert len(box) == 4 or len(box) == 5, ( "BoxMode.convert takes either a k-tuple/list or an Nxk array/tensor," " where k == 4 or 5" ) arr = torch.tensor(box)[None, :] else: # avoid modifying the input box if is_numpy: arr = torch.from_numpy(np.asarray(box)).clone() else: arr = box.clone() assert to_mode.value not in [ BoxMode.XYXY_REL, BoxMode.XYWH_REL, ] and from_mode.value not in [ BoxMode.XYXY_REL, BoxMode.XYWH_REL, ], "Relative mode not yet supported!" if from_mode == BoxMode.XYWHA_ABS and to_mode == BoxMode.XYXY_ABS: assert ( arr.shape[-1] == 5 ), "The last dimension of input shape must be 5 for XYWHA format" original_dtype = arr.dtype arr = arr.double() w = arr[:, 2] h = arr[:, 3] a = arr[:, 4] c = torch.abs(torch.cos(a * math.pi / 180.0)) s = torch.abs(torch.sin(a * math.pi / 180.0)) # This basically computes the horizontal bounding rectangle of the rotated box new_w = c * w + s * h new_h = c * h + s * w # convert center to top-left corner arr[:, 0] -= new_w / 2.0 arr[:, 1] -= new_h / 2.0 # bottom-right corner arr[:, 2] = arr[:, 0] + new_w arr[:, 3] = arr[:, 1] + new_h arr = arr[:, :4].to(dtype=original_dtype) elif from_mode == BoxMode.XYWH_ABS and to_mode == BoxMode.XYWHA_ABS: original_dtype = arr.dtype arr = arr.double() arr[:, 0] += arr[:, 2] / 2.0 arr[:, 1] += arr[:, 3] / 2.0 angles = torch.zeros((arr.shape[0], 1), dtype=arr.dtype) arr = torch.cat((arr, angles), axis=1).to(dtype=original_dtype) else: if to_mode == BoxMode.XYXY_ABS and from_mode == BoxMode.XYWH_ABS: arr[:, 2] += arr[:, 0] arr[:, 3] += arr[:, 1] elif from_mode == BoxMode.XYXY_ABS and to_mode == BoxMode.XYWH_ABS: arr[:, 2] -= arr[:, 0] arr[:, 3] -= arr[:, 1] else: raise NotImplementedError( "Conversion from BoxMode {} to {} is not supported yet".format( from_mode, to_mode ) ) if single_box: return original_type(arr.flatten()) if is_numpy: return arr.numpy() else: return arr
[docs]class Boxes: """ This structure stores a list of boxes as a Nx4 torch.Tensor. It supports some common methods about boxes (`area`, `clip`, `nonempty`, etc), and also behaves like a Tensor (support indexing, `to(device)`, `.device`, and iteration over all boxes) Attributes: tensor(torch.Tensor): float matrix of Nx4. """ BoxSizeType = Union[List[int], Tuple[int, int]]
[docs] def __init__(self, tensor: torch.Tensor): """ Args: tensor (Tensor[float]): a Nx4 matrix. Each row is (x1, y1, x2, y2). """ device = tensor.device if isinstance(tensor, torch.Tensor) else torch.device("cpu") tensor = torch.as_tensor(tensor, dtype=torch.float32, device=device) if tensor.numel() == 0: tensor = torch.zeros(0, 4, dtype=torch.float32, device=device) assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size() self.tensor = tensor
[docs] def clone(self) -> "Boxes": """ Clone the Boxes. Returns: Boxes """ return Boxes(self.tensor.clone())
[docs] def to(self, device: str) -> "Boxes": return Boxes(self.tensor.to(device))
[docs] def area(self) -> torch.Tensor: """ Computes the area of all the boxes. Returns: torch.Tensor: a vector with areas of each box. """ box = self.tensor area = (box[:, 2] - box[:, 0]) * (box[:, 3] - box[:, 1]) return area
[docs] def clip(self, box_size: BoxSizeType) -> None: """ Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. Args: box_size (height, width): The clipping box's size. """ assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!" h, w = box_size self.tensor[:, 0].clamp_(min=0, max=w) self.tensor[:, 1].clamp_(min=0, max=h) self.tensor[:, 2].clamp_(min=0, max=w) self.tensor[:, 3].clamp_(min=0, max=h)
[docs] def nonempty(self, threshold: int = 0) -> torch.Tensor: """ Find boxes that are non-empty. A box is considered empty, if either of its side is no larger than threshold. Returns: Tensor: a binary vector which represents whether each box is empty (False) or non-empty (True). """ box = self.tensor widths = box[:, 2] - box[:, 0] heights = box[:, 3] - box[:, 1] keep = (widths > threshold) & (heights > threshold) return keep
[docs] def __getitem__(self, item: Union[int, slice, torch.BoolTensor]) -> "Boxes": """ Returns: Boxes: Create a new :class:`Boxes` by indexing. The following usage are allowed: 1. `new_boxes = boxes[3]`: return a `Boxes` which contains only one box. 2. `new_boxes = boxes[2:10]`: return a slice of boxes. 3. `new_boxes = boxes[vector]`, where vector is a torch.BoolTensor with `length = len(boxes)`. Nonzero elements in the vector will be selected. Note that the returned Boxes might share storage with this Boxes, subject to Pytorch's indexing semantics. """ if isinstance(item, int): return Boxes(self.tensor[item].view(1, -1)) b = self.tensor[item] assert b.dim() == 2, "Indexing on Boxes with {} failed to return a matrix!".format(item) return Boxes(b)
def __len__(self) -> int: return self.tensor.shape[0] def __repr__(self) -> str: return "Boxes(" + str(self.tensor) + ")"
[docs] def inside_box(self, box_size: BoxSizeType, boundary_threshold: int = 0) -> torch.Tensor: """ Args: box_size (height, width): Size of the reference box. boundary_threshold (int): Boxes that extend beyond the reference box boundary by more than boundary_threshold are considered "outside". Returns: a binary vector, indicating whether each box is inside the reference box. """ height, width = box_size inds_inside = ( (self.tensor[..., 0] >= -boundary_threshold) & (self.tensor[..., 1] >= -boundary_threshold) & (self.tensor[..., 2] < width + boundary_threshold) & (self.tensor[..., 3] < height + boundary_threshold) ) return inds_inside
[docs] def get_centers(self) -> torch.Tensor: """ Returns: The box centers in a Nx2 array of (x, y). """ return (self.tensor[:, :2] + self.tensor[:, 2:]) / 2
[docs] def scale(self, scale_x: float, scale_y: float) -> None: """ Scale the box with horizontal and vertical scaling factors """ self.tensor[:, 0::2] *= scale_x self.tensor[:, 1::2] *= scale_y
[docs] @classmethod def cat(cls, boxes_list: List["Boxes"]) -> "Boxes": """ Concatenates a list of Boxes into a single Boxes Arguments: boxes_list (list[Boxes]) Returns: Boxes: the concatenated Boxes """ assert isinstance(boxes_list, (list, tuple)) assert all(isinstance(box, Boxes) for box in boxes_list) if len(boxes_list) == 0: return cls(torch.empty(0)) cat_boxes = type(boxes_list[0])(cat([b.tensor for b in boxes_list], dim=0)) return cat_boxes
@property def device(self) -> torch.device: return self.tensor.device
[docs] def __iter__(self) -> Iterator[torch.Tensor]: """ Yield a box as a Tensor of shape (4,) at a time. """ yield from self.tensor
# implementation from https://github.com/kuangliu/torchcv/blob/master/torchcv/utils/box.py # with slight modifications
[docs]def pairwise_iou(boxes1: Boxes, boxes2: Boxes) -> torch.Tensor: """ Given two lists of boxes of size N and M, compute the IoU (intersection over union) between __all__ N x M pairs of boxes. The box order must be (xmin, ymin, xmax, ymax). Args: boxes1,boxes2 (Boxes): two `Boxes`. Contains N & M boxes, respectively. Returns: Tensor: IoU, sized [N,M]. """ area1 = boxes1.area() area2 = boxes2.area() boxes1, boxes2 = boxes1.tensor, boxes2.tensor width_height = torch.min(boxes1[:, None, 2:], boxes2[:, 2:]) - torch.max( boxes1[:, None, :2], boxes2[:, :2] ) # [N,M,2] width_height.clamp_(min=0) # [N,M,2] inter = width_height.prod(dim=2) # [N,M] del width_height # handle empty boxes iou = torch.where( inter > 0, inter / (area1[:, None] + area2 - inter), torch.zeros(1, dtype=inter.dtype, device=inter.device), ) return iou
[docs]def pairwise_ioa(gt: Boxes, boxes: Boxes, labels, ignore_label=-1) -> torch.Tensor: """ Given two lists of boxes of size N and M, compute the IoU (intersection over union) between __all__ N x M pairs of boxes. The box order must be (xmin, ymin, xmax, ymax). Args: boxes1,boxes2 (Boxes): two `Boxes`. Contains N & M boxes, respectively. Returns: Tensor: IoU, sized [N,M]. """ area_boxes = boxes.area() gt, boxes = gt.tensor, boxes.tensor width_height = torch.min(gt[:, None, 2:], boxes[:, 2:]) - torch.max( gt[:, None, :2], boxes[:, :2] ) # [N,M,2] width_height.clamp_(min=0) # [N,M,2] inter = width_height.prod(dim=2) # [N,M] del width_height # handle empty boxes ioa = torch.where( inter > 0, inter / (area_boxes), torch.zeros(1, dtype=inter.dtype, device=inter.device), ) gt_ignore_mask = labels.eq(ignore_label).unsqueeze(1) ioa *= gt_ignore_mask return ioa
def matched_boxlist_iou(boxes1: Boxes, boxes2: Boxes) -> torch.Tensor: """ Compute pairwise intersection over union (IOU) of two sets of matched boxes. The box order must be (xmin, ymin, xmax, ymax). Similar to boxlist_iou, but computes only diagonal elements of the matrix Arguments: boxes1: (Boxes) bounding boxes, sized [N,4]. boxes2: (Boxes) bounding boxes, sized [N,4]. Returns: (tensor) iou, sized [N]. """ assert len(boxes1) == len(boxes2), ( "boxlists should have the same" "number of entries, got {}, {}".format(len(boxes1), len(boxes2)) ) area1 = boxes1.area() # [N] area2 = boxes2.area() # [N] box1, box2 = boxes1.tensor, boxes2.tensor lt = torch.max(box1[:, :2], box2[:, :2]) # [N,2] rb = torch.min(box1[:, 2:], box2[:, 2:]) # [N,2] wh = (rb - lt).clamp(min=0) # [N,2] inter = wh[:, 0] * wh[:, 1] # [N] iou = inter / (area1 + area2 - inter) # [N] return iou # added for DETR # TODO @wangfeng02, use BoxMode instead and provide a better func def box_cxcywh_to_xyxy(x): x_c, y_c, w, h = x.unbind(-1) b = [(x_c - 0.5 * w), (y_c - 0.5 * h), (x_c + 0.5 * w), (y_c + 0.5 * h)] return torch.stack(b, dim=-1) def box_xyxy_to_cxcywh(x): x0, y0, x1, y1 = x.unbind(-1) b = [(x0 + x1) / 2, (y0 + y1) / 2, (x1 - x0), (y1 - y0)] return torch.stack(b, dim=-1) def generalized_box_iou(boxes1, boxes2): """ Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where N = len(boxes1) and M = len(boxes2) """ # degenerate boxes gives inf / nan results # so do an early check assert (boxes1[:, 2:] >= boxes1[:, :2]).all() assert (boxes2[:, 2:] >= boxes2[:, :2]).all() # vallina box iou # modified from torchvision to also return the union area1 = box_area(boxes1) area2 = box_area(boxes2) lt = torch.max(boxes1[:, None, :2], boxes2[:, :2]) # [N,M,2] rb = torch.min(boxes1[:, None, 2:], boxes2[:, 2:]) # [N,M,2] wh = (rb - lt).clamp(min=0) # [N,M,2] inter = wh[:, :, 0] * wh[:, :, 1] # [N,M] union = area1[:, None] + area2 - inter iou = inter / union # iou, union = box_iou(boxes1, boxes2) lt = torch.min(boxes1[:, None, :2], boxes2[:, :2]) rb = torch.max(boxes1[:, None, 2:], boxes2[:, 2:]) wh = (rb - lt).clamp(min=0) # [N,M,2] area = wh[:, :, 0] * wh[:, :, 1] return iou - (area - union) / area def masks_to_boxes(masks): """ Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spatial dimensions. Returns a [N, 4] tensors, with the boxes in xyxy format """ if masks.numel() == 0: return torch.zeros((0, 4), device=masks.device) h, w = masks.shape[-2:] y = torch.arange(0, h, dtype=torch.float) x = torch.arange(0, w, dtype=torch.float) y, x = torch.meshgrid(y, x) x_mask = masks * x.unsqueeze(0) x_max = x_mask.flatten(1).max(-1)[0] x_min = x_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0] y_mask = masks * y.unsqueeze(0) y_max = y_mask.flatten(1).max(-1)[0] y_min = y_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0] return torch.stack([x_min, y_min, x_max, y_max], 1)