import mmcv
import numpy as np
import torch
[docs]def bbox_flip(bboxes, img_shape):
"""Flip bboxes horizontally.
Args:
bboxes(Tensor or ndarray): Shape (..., 4*k)
img_shape(tuple): Image shape.
Returns:
Same type as `bboxes`: Flipped bboxes.
"""
if isinstance(bboxes, torch.Tensor):
assert bboxes.shape[-1] % 4 == 0
flipped = bboxes.clone()
flipped[:, 0::4] = img_shape[1] - bboxes[:, 2::4]
flipped[:, 2::4] = img_shape[1] - bboxes[:, 0::4]
return flipped
elif isinstance(bboxes, np.ndarray):
return mmcv.bbox_flip(bboxes, img_shape)
[docs]def bbox_mapping(bboxes, img_shape, scale_factor, flip):
"""Map bboxes from the original image scale to testing scale"""
new_bboxes = bboxes * bboxes.new_tensor(scale_factor)
if flip:
new_bboxes = bbox_flip(new_bboxes, img_shape)
return new_bboxes
[docs]def bbox_mapping_back(bboxes, img_shape, scale_factor, flip):
"""Map bboxes from testing scale to original image scale"""
new_bboxes = bbox_flip(bboxes, img_shape) if flip else bboxes
new_bboxes = new_bboxes / new_bboxes.new_tensor(scale_factor)
return new_bboxes
[docs]def bbox2roi(bbox_list):
"""Convert a list of bboxes to roi format.
Args:
bbox_list (list[Tensor]): a list of bboxes corresponding to a batch
of images.
Returns:
Tensor: shape (n, 5), [batch_ind, x1, y1, x2, y2]
"""
rois_list = []
for img_id, bboxes in enumerate(bbox_list):
if bboxes.size(0) > 0:
img_inds = bboxes.new_full((bboxes.size(0), 1), img_id)
rois = torch.cat([img_inds, bboxes[:, :4]], dim=-1)
else:
rois = bboxes.new_zeros((0, 5))
rois_list.append(rois)
rois = torch.cat(rois_list, 0)
return rois
def roi2bbox(rois):
bbox_list = []
img_ids = torch.unique(rois[:, 0].cpu(), sorted=True)
for img_id in img_ids:
inds = (rois[:, 0] == img_id.item())
bbox = rois[inds, 1:]
bbox_list.append(bbox)
return bbox_list
[docs]def bbox2result(bboxes, labels, num_classes):
"""Convert detection results to a list of numpy arrays.
Args:
bboxes (Tensor): shape (n, 5)
labels (Tensor): shape (n, )
num_classes (int): class number, including background class
Returns:
list(ndarray): bbox results of each class
"""
if bboxes.shape[0] == 0:
return [np.zeros((0, 5), dtype=np.float32) for i in range(num_classes)]
else:
bboxes = bboxes.cpu().numpy()
labels = labels.cpu().numpy()
return [bboxes[labels == i, :] for i in range(num_classes)]
[docs]def distance2bbox(points, distance, max_shape=None):
"""Decode distance prediction to bounding box.
Args:
points (Tensor): Shape (n, 2), [x, y].
distance (Tensor): Distance from the given point to 4
boundaries (left, top, right, bottom).
max_shape (tuple): Shape of the image.
Returns:
Tensor: Decoded bboxes.
"""
x1 = points[:, 0] - distance[:, 0]
y1 = points[:, 1] - distance[:, 1]
x2 = points[:, 0] + distance[:, 2]
y2 = points[:, 1] + distance[:, 3]
if max_shape is not None:
x1 = x1.clamp(min=0, max=max_shape[1])
y1 = y1.clamp(min=0, max=max_shape[0])
x2 = x2.clamp(min=0, max=max_shape[1])
y2 = y2.clamp(min=0, max=max_shape[0])
return torch.stack([x1, y1, x2, y2], -1)