# Ultralytics YOLO 🚀, AGPL-3.0 license
import contextlib
import math
import re
import time
import cv2
import numpy as np
import torch
import torch.nn.functional as F
import torchvision
from torch.nn import CosineSimilarity
from ultralytics.utils import LOGGER
class Profile(contextlib.ContextDecorator):
"""
YOLOv8 Profile class. Use as a decorator with @Profile() or as a context manager with 'with Profile():'.
Example:
```python
from ultralytics.utils.ops import Profile
with Profile() as dt:
pass # slow operation here
print(dt) # prints "Elapsed time is 9.5367431640625e-07 s"
```
"""
def __init__(self, t=0.0):
"""
Initialize the Profile class.
Args:
t (float): Initial time. Defaults to 0.0.
"""
self.t = t
self.cuda = torch.cuda.is_available()
def __enter__(self):
"""Start timing."""
self.start = self.time()
return self
def __exit__(self, type, value, traceback): # noqa
"""Stop timing."""
self.dt = self.time() - self.start # delta-time
self.t += self.dt # accumulate dt
def __str__(self):
return f'Elapsed time is {self.t} s'
def time(self):
"""Get current time."""
if self.cuda:
torch.cuda.synchronize()
return time.time()
def segment2box(segment, width=640, height=640):
"""
Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy).
Args:
segment (torch.Tensor): the segment label
width (int): the width of the image. Defaults to 640
height (int): The height of the image. Defaults to 640
Returns:
(np.ndarray): the minimum and maximum x and y values of the segment.
"""
# Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
x, y = segment.T # segment xy
inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
x, y, = x[inside], y[inside]
return np.array([x.min(), y.min(), x.max(), y.max()], dtype=segment.dtype) if any(x) else np.zeros(
4, dtype=segment.dtype) # xyxy
def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None, padding=True):
"""
Rescales bounding boxes (in the format of xyxy) from the shape of the image they were originally specified in
(img1_shape) to the shape of a different image (img0_shape).
Args:
img1_shape (tuple): The shape of the image that the bounding boxes are for, in the format of (height, width).
boxes (torch.Tensor): the bounding boxes of the objects in the image, in the format of (x1, y1, x2, y2)
img0_shape (tuple): the shape of the target image, in the format of (height, width).
ratio_pad (tuple): a tuple of (ratio, pad) for scaling the boxes. If not provided, the ratio and pad will be
calculated based on the size difference between the two images.
padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
rescaling.
Returns:
boxes (torch.Tensor): The scaled bounding boxes, in the format of (x1, y1, x2, y2)
"""
if ratio_pad is None: # calculate from img0_shape
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
pad = round((img1_shape[1] - img0_shape[1] * gain) / 2 - 0.1), round(
(img1_shape[0] - img0_shape[0] * gain) / 2 - 0.1) # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
if padding:
boxes[..., [0, 2]] -= pad[0] # x padding
boxes[..., [1, 3]] -= pad[1] # y padding
boxes[..., :4] /= gain
clip_boxes(boxes, img0_shape)
return boxes
def make_divisible(x, divisor):
"""
Returns the nearest number that is divisible by the given divisor.
Args:
x (int): The number to make divisible.
divisor (int | torch.Tensor): The divisor.
Returns:
(int): The nearest number divisible by the divisor.
"""
if isinstance(divisor, torch.Tensor):
divisor = int(divisor.max()) # to int
return math.ceil(x / divisor) * divisor
def downsample_masks(masks, scale_factor=1.0):
# Assuming masks are in (N, H, W) format
downsampled_masks = torch.nn.functional.interpolate(masks.float().unsqueeze(1), scale_factor=scale_factor, mode='bilinear', align_corners=False).squeeze(1)
return downsampled_masks.bool()
def custom_nms(iou_matrix, conf, iou_threshold):
conf_1d = conf.squeeze()
sorted_indices = conf_1d.argsort(descending=True)
keep = []
suppressed = torch.zeros(conf.size(0), dtype=torch.bool, device=conf.device) # Ensure suppressed is 1D
for idx in sorted_indices:
if suppressed[idx]:
continue # Skip if already suppressed
keep.append(idx.item()) # Add the current index to keep
# Suppress the masks with high IoU with the current mask, ensuring shapes match for in-place operation
suppressed |= (iou_matrix[idx] > iou_threshold).squeeze()
# Make sure the current mask is not suppressed by resetting its flag
suppressed[idx] = False
keep_indices = torch.tensor(keep, device=iou_matrix.device) # Convert kept indices to a tensor
return keep_indices
def non_max_suppression(
prediction,
mask_coef=None,
proto=None,
img_shape = None,
regression_var = None,
conf_thres=0.25,
iou_thres=0.45,
classes=None,
agnostic=False,
multi_label=False,
labels=(),
max_det=300,
nc=0, # number of classes (optional)
max_time_img=60.0,
max_nms=30000,
max_wh=7680,
):
"""
Perform non-maximum suppression (NMS) on a set of boxes, with support for masks and multiple labels per box.
Args:
prediction (torch.Tensor): A tensor of shape (batch_size, num_classes + 4 + num_masks, num_boxes)
containing the predicted boxes, classes, and masks. The tensor should be in the format
output by a model, such as YOLO.
conf_thres (float): The confidence threshold below which boxes will be filtered out.
Valid values are between 0.0 and 1.0.
iou_thres (float): The IoU threshold below which boxes will be filtered out during NMS.
Valid values are between 0.0 and 1.0.
classes (List[int]): A list of class indices to consider. If None, all classes will be considered.
agnostic (bool): If True, the model is agnostic to the number of classes, and all
classes will be considered as one.
multi_label (bool): If True, each box may have multiple labels.
labels (List[List[Union[int, float, torch.Tensor]]]): A list of lists, where each inner
list contains the apriori labels for a given image. The list should be in the format
output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2).
max_det (int): The maximum number of boxes to keep after NMS.
nc (int, optional): The number of classes output by the model. Any indices after this will be considered masks.
max_time_img (float): The maximum time (seconds) for processing one image.
max_nms (int): The maximum number of boxes into torchvision.ops.nms().
max_wh (int): The maximum box width and height in pixels
Returns:
(List[torch.Tensor]): A list of length batch_size, where each element is a tensor of
shape (num_boxes, 6 + num_masks) containing the kept boxes, with columns
(x1, y1, x2, y2, confidence, class, mask1, mask2, ...).
"""
# Checks
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
if isinstance(prediction, (list, tuple)): # YOLOv8 model in validation model, output = (inference_out, loss_out)
prediction = prediction[0] # select only inference output
device = prediction.device
mps = 'mps' in device.type # Apple MPS
if mps: # MPS not fully supported yet, convert tensors to CPU before NMS
prediction = prediction.cpu()
bs = prediction.shape[0] # batch size
nc = nc or (prediction.shape[1] - 4) # number of classes
nm = prediction.shape[1] - nc - 4
mi = 4 + nc # mask start index
xc = prediction[:, 4:mi].amax(1) > conf_thres # candidates
# Settings
# min_wh = 2 # (pixels) minimum box width and height
time_limit = 0.5 + max_time_img * bs # seconds to quit after
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
prediction = prediction.transpose(-1, -2) # shape(1,84,6300) to shape(1,6300,84)
prediction[..., :4] = xywh2xyxy(prediction[..., :4]) # xywh to xyxy
t = time.time()
output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs
if regression_var is not None:
saved_reg_var = [torch.zeros((0, 6), device=prediction.device)] * bs
regression_var = regression_var.transpose(-1, -2)
for xi, x in enumerate(prediction): # image index, image inference
# Apply constraints
# x[((x[:, 2:4] < min_wh) | (x[:, 2:4] > max_wh)).any(1), 4] = 0 # width-height
x = x[xc[xi]] # confidence
# confident_mask = mask_coefficient
# Cat apriori labels if autolabelling
if labels and len(labels[xi]):
lb = labels[xi]
v = torch.zeros((len(lb), nc + nm + 4), device=x.device)
v[:, :4] = xywh2xyxy(lb[:, 1:5]) # box
v[range(len(lb)), lb[:, 0].long() + 4] = 1.0 # cls
x = torch.cat((x, v), 0)
# If none remain process next image
if not x.shape[0]:
continue
# Detections matrix nx6 (xyxy, conf, cls)
box, cls, mask = x.split((4, nc, nm), 1)
if multi_label:
i, j = torch.where(cls > conf_thres)
x = torch.cat((box[i], x[i, 4 + j, None], j[:, None].float(), mask[i]), 1)
else: # best class only
conf, j = cls.max(1, keepdim=True)
x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]
# Filter by class
if classes is not None:
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
# Check shape
n = x.shape[0] # number of boxes
if not n: # no boxes
continue
if n > max_nms: # excess boxes
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence and remove excess boxes
# Batched NMS
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
# mask_coef = None
if mask_coef is not None:
ih, iw = img_shape
mask_coefficient = mask_coef[xi]
filtered_mask_coefficient = mask_coefficient[:, xc.squeeze()]
prototype = proto
c, mh, mw = prototype.shape[-3:] # CHW
masks = (filtered_mask_coefficient.T @ prototype.float().view(c, -1)).sigmoid().view(-1, mh, mw) # CHW
mask_coefficient = mask_coef[xi].detach()
filtered_mask_coefficient = mask_coefficient[:, xc.squeeze()].detach()
#filtered_mask_coefficient = filtered_mask_coefficient[:, kept_indices].detach()
#conf = conf[kept_indices].detach()
#masks = masks[kept_indices].detach()
downsampled_bboxes = boxes.clone().detach()
#downsampled_bboxes = boxes[kept_indices].clone().detach()
downsampled_bboxes[:, 0] *= mw / iw
downsampled_bboxes[:, 2] *= mw / iw
downsampled_bboxes[:, 3] *= mh / ih
downsampled_bboxes[:, 1] *= mh / ih
masks = crop_mask(masks, downsampled_bboxes) # CHW
masks.gt_(0.5)
# threshold masks:
#masks = (masks > 0.5).float()
downsampled_masks_bool = downsample_masks(masks, scale_factor=1.0).detach()
# Ensure masks are boolean and detach to avoid saving gradients
masks_bool = downsampled_masks_bool.detach() # Assuming downsampled_masks_bool is already defined
batch_size = 5 # Adjust based on your GPU memory and the size of masks_bool
num_masks = masks_bool.size(0)
intersections = []
unions = []
min_areas = [] # To store minimum areas for IoMin calculation
dices = [] # To store Dice Coefficients
for batch_start in range(0, num_masks, batch_size):
batch_end = min(batch_start + batch_size, num_masks)
masks_bool_batch = masks_bool[batch_start:batch_end]
# Compute intersection and union for the current batch
intersection_batch = (masks_bool_batch.unsqueeze(1) & masks_bool.unsqueeze(0)).float().sum(dim=(-1, -2))
union_batch = (masks_bool_batch.unsqueeze(1) | masks_bool.unsqueeze(0)).float().sum(dim=(-1, -2))
# Calculate areas for IoMin
area_batch = masks_bool_batch.float().sum(dim=(-1, -2)).unsqueeze(1) # Areas of masks in the current batch
area_all = masks_bool.float().sum(dim=(-1, -2)).unsqueeze(0) # Areas of all masks
min_area_batch = torch.min(area_batch, area_all) # Find the minimum area between each pair of masks
# Calculate Dice Coefficient for the current batch
dice_batch = (2 * intersection_batch) / (area_batch + area_all)
intersections.append(intersection_batch)
unions.append(union_batch)
min_areas.append(min_area_batch)
dices.append(dice_batch) # Append the calculated Dice Coefficients
# Concatenate the results from each batch
intersection = torch.cat(intersections, dim=0)
union = torch.cat(unions, dim=0)
min_area = torch.cat(min_areas, dim=0)
dice = torch.cat(dices, dim=0) # Concatenate all Dice Coefficients
# Compute IoMin by dividing intersection by the minimum area, handle division by zero
iou = intersection / union
iomin = intersection / min_area
iomin[min_area == 0] = 0 # Handle division by zero, if any
iou = iou.detach()
kept_indices = custom_nms(dice, conf, iou_thres)
# Map the IOU kept indices back to the original set
#original_indices_iou = kept_indices_cosine[kept_indices_iou].detach()
# Explicitly delete large unused tensors and call garbage collection to free up memory
del masks, downsampled_masks_bool, intersection, union, iou
import gc
gc.collect()
# Ensure CUDA cache is cleared, potentially freeing up unused memory
torch.cuda.empty_cache()
i = kept_indices
else:
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
i = i[:max_det] # limit detections
if regression_var is not None:
filtered_reg = regression_var[xi][xc[xi]]
saved_reg_var[xi] = filtered_reg[i]
output[xi] = x[i]
if mps:
output[xi] = output[xi].to(device)
if (time.time() - t) > time_limit:
LOGGER.warning(f'WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded')
break # time limit exceeded
if regression_var is not None:
return output, saved_reg_var
else:
return output
def clip_boxes(boxes, shape):
"""
Takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape.
Args:
boxes (torch.Tensor): the bounding boxes to clip
shape (tuple): the shape of the image
"""
if isinstance(boxes, torch.Tensor): # faster individually
boxes[..., 0].clamp_(0, shape[1]) # x1
boxes[..., 1].clamp_(0, shape[0]) # y1
boxes[..., 2].clamp_(0, shape[1]) # x2
boxes[..., 3].clamp_(0, shape[0]) # y2
else: # np.array (faster grouped)
boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1]) # x1, x2
boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0]) # y1, y2
def clip_coords(coords, shape):
"""
Clip line coordinates to the image boundaries.
Args:
coords (torch.Tensor | numpy.ndarray): A list of line coordinates.
shape (tuple): A tuple of integers representing the size of the image in the format (height, width).
Returns:
(None): The function modifies the input `coordinates` in place, by clipping each coordinate to the image boundaries.
"""
if isinstance(coords, torch.Tensor): # faster individually
coords[..., 0].clamp_(0, shape[1]) # x
coords[..., 1].clamp_(0, shape[0]) # y
else: # np.array (faster grouped)
coords[..., 0] = coords[..., 0].clip(0, shape[1]) # x
coords[..., 1] = coords[..., 1].clip(0, shape[0]) # y
def scale_image(masks, im0_shape, ratio_pad=None):
"""
Takes a mask, and resizes it to the original image size
Args:
masks (np.ndarray): resized and padded masks/images, [h, w, num]/[h, w, 3].
im0_shape (tuple): the original image shape
ratio_pad (tuple): the ratio of the padding to the original image.
Returns:
masks (torch.Tensor): The masks that are being returned.
"""
# Rescale coordinates (xyxy) from im1_shape to im0_shape
im1_shape = masks.shape
if im1_shape[:2] == im0_shape[:2]:
return masks
if ratio_pad is None: # calculate from im0_shape
gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new
pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
top, left = int(pad[1]), int(pad[0]) # y, x
bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0])
if len(masks.shape) < 2:
raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}')
masks = masks[top:bottom, left:right]
masks = cv2.resize(masks, (im0_shape[1], im0_shape[0]))
if len(masks.shape) == 2:
masks = masks[:, :, None]
return masks
def xyxy2xywh(x):
"""
Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height) format where (x1, y1) is the
top-left corner and (x2, y2) is the bottom-right corner.
Args:
x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x1, y1, x2, y2) format.
Returns:
y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height) format.
"""
assert x.shape[-1] == 4, f'input shape last dimension expected 4 but input shape is {x.shape}'
y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy
y[..., 0] = (x[..., 0] + x[..., 2]) / 2 # x center
y[..., 1] = (x[..., 1] + x[..., 3]) / 2 # y center
y[..., 2] = x[..., 2] - x[..., 0] # width
y[..., 3] = x[..., 3] - x[..., 1] # height
return y
def xywh2xyxy(x):
"""
Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the
top-left corner and (x2, y2) is the bottom-right corner.
Args:
x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x, y, width, height) format.
Returns:
y (np.ndarray | torch.Tensor): The bounding box coordinates in (x1, y1, x2, y2) format.
"""
assert x.shape[-1] == 4, f'input shape last dimension expected 4 but input shape is {x.shape}'
y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy
dw = x[..., 2] / 2 # half-width
dh = x[..., 3] / 2 # half-height
y[..., 0] = x[..., 0] - dw # top left x
y[..., 1] = x[..., 1] - dh # top left y
y[..., 2] = x[..., 0] + dw # bottom right x
y[..., 3] = x[..., 1] + dh # bottom right y
return y
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
"""
Convert normalized bounding box coordinates to pixel coordinates.
Args:
x (np.ndarray | torch.Tensor): The bounding box coordinates.
w (int): Width of the image. Defaults to 640
h (int): Height of the image. Defaults to 640
padw (int): Padding width. Defaults to 0
padh (int): Padding height. Defaults to 0
Returns:
y (np.ndarray | torch.Tensor): The coordinates of the bounding box in the format [x1, y1, x2, y2] where
x1,y1 is the top-left corner, x2,y2 is the bottom-right corner of the bounding box.
"""
assert x.shape[-1] == 4, f'input shape last dimension expected 4 but input shape is {x.shape}'
y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy
y[..., 0] = w * (x[..., 0] - x[..., 2] / 2) + padw # top left x
y[..., 1] = h * (x[..., 1] - x[..., 3] / 2) + padh # top left y
y[..., 2] = w * (x[..., 0] + x[..., 2] / 2) + padw # bottom right x
y[..., 3] = h * (x[..., 1] + x[..., 3] / 2) + padh # bottom right y
return y
def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
"""
Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height, normalized) format.
x, y, width and height are normalized to image dimensions
Args:
x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x1, y1, x2, y2) format.
w (int): The width of the image. Defaults to 640
h (int): The height of the image. Defaults to 640
clip (bool): If True, the boxes will be clipped to the image boundaries. Defaults to False
eps (float): The minimum value of the box's width and height. Defaults to 0.0
Returns:
y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height, normalized) format
"""
if clip:
clip_boxes(x, (h - eps, w - eps)) # warning: inplace clip
assert x.shape[-1] == 4, f'input shape last dimension expected 4 but input shape is {x.shape}'
y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy
y[..., 0] = ((x[..., 0] + x[..., 2]) / 2) / w # x center
y[..., 1] = ((x[..., 1] + x[..., 3]) / 2) / h # y center
y[..., 2] = (x[..., 2] - x[..., 0]) / w # width
y[..., 3] = (x[..., 3] - x[..., 1]) / h # height
return y
def xywh2ltwh(x):
"""
Convert the bounding box format from [x, y, w, h] to [x1, y1, w, h], where x1, y1 are the top-left coordinates.
Args:
x (np.ndarray | torch.Tensor): The input tensor with the bounding box coordinates in the xywh format
Returns:
y (np.ndarray | torch.Tensor): The bounding box coordinates in the xyltwh format
"""
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 0] = x[..., 0] - x[..., 2] / 2 # top left x
y[..., 1] = x[..., 1] - x[..., 3] / 2 # top left y
return y
def xyxy2ltwh(x):
"""
Convert nx4 bounding boxes from [x1, y1, x2, y2] to [x1, y1, w, h], where xy1=top-left, xy2=bottom-right
Args:
x (np.ndarray | torch.Tensor): The input tensor with the bounding boxes coordinates in the xyxy format
Returns:
y (np.ndarray | torch.Tensor): The bounding box coordinates in the xyltwh format.
"""
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 2] = x[..., 2] - x[..., 0] # width
y[..., 3] = x[..., 3] - x[..., 1] # height
return y
def ltwh2xywh(x):
"""
Convert nx4 boxes from [x1, y1, w, h] to [x, y, w, h] where xy1=top-left, xy=center
Args:
x (torch.Tensor): the input tensor
Returns:
y (np.ndarray | torch.Tensor): The bounding box coordinates in the xywh format.
"""
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 0] = x[..., 0] + x[..., 2] / 2 # center x
y[..., 1] = x[..., 1] + x[..., 3] / 2 # center y
return y
def xyxyxyxy2xywhr(corners):
"""
Convert batched Oriented Bounding Boxes (OBB) from [xy1, xy2, xy3, xy4] to [xywh, rotation].
Args:
corners (numpy.ndarray | torch.Tensor): Input corners of shape (n, 8).
Returns:
(numpy.ndarray | torch.Tensor): Converted data in [cx, cy, w, h, rotation] format of shape (n, 5).
"""
is_numpy = isinstance(corners, np.ndarray)
atan2, sqrt = (np.arctan2, np.sqrt) if is_numpy else (torch.atan2, torch.sqrt)
x1, y1, x2, y2, x3, y3, x4, y4 = corners.T
cx = (x1 + x3) / 2
cy = (y1 + y3) / 2
dx21 = x2 - x1
dy21 = y2 - y1
w = sqrt(dx21 ** 2 + dy21 ** 2)
h = sqrt((x2 - x3) ** 2 + (y2 - y3) ** 2)
rotation = atan2(-dy21, dx21)
rotation *= 180.0 / math.pi # radians to degrees
return np.vstack((cx, cy, w, h, rotation)).T if is_numpy else torch.stack((cx, cy, w, h, rotation), dim=1)
def xywhr2xyxyxyxy(center):
"""
Convert batched Oriented Bounding Boxes (OBB) from [xywh, rotation] to [xy1, xy2, xy3, xy4].
Args:
center (numpy.ndarray | torch.Tensor): Input data in [cx, cy, w, h, rotation] format of shape (n, 5).
Returns:
(numpy.ndarray | torch.Tensor): Converted corner points of shape (n, 8).
"""
is_numpy = isinstance(center, np.ndarray)
cos, sin = (np.cos, np.sin) if is_numpy else (torch.cos, torch.sin)
cx, cy, w, h, rotation = center.T
rotation *= math.pi / 180.0 # degrees to radians
dx = w / 2
dy = h / 2
cos_rot = cos(rotation)
sin_rot = sin(rotation)
dx_cos_rot = dx * cos_rot
dx_sin_rot = dx * sin_rot
dy_cos_rot = dy * cos_rot
dy_sin_rot = dy * sin_rot
x1 = cx - dx_cos_rot - dy_sin_rot
y1 = cy + dx_sin_rot - dy_cos_rot
x2 = cx + dx_cos_rot - dy_sin_rot
y2 = cy - dx_sin_rot - dy_cos_rot
x3 = cx + dx_cos_rot + dy_sin_rot
y3 = cy - dx_sin_rot + dy_cos_rot
x4 = cx - dx_cos_rot + dy_sin_rot
y4 = cy + dx_sin_rot + dy_cos_rot
return np.vstack((x1, y1, x2, y2, x3, y3, x4, y4)).T if is_numpy else torch.stack(
(x1, y1, x2, y2, x3, y3, x4, y4), dim=1)
def ltwh2xyxy(x):
"""
It converts the bounding box from [x1, y1, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
Args:
x (np.ndarray | torch.Tensor): the input image
Returns:
y (np.ndarray | torch.Tensor): the xyxy coordinates of the bounding boxes.
"""
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 2] = x[..., 2] + x[..., 0] # width
y[..., 3] = x[..., 3] + x[..., 1] # height
return y
def segments2boxes(segments):
"""
It converts segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
Args:
segments (list): list of segments, each segment is a list of points, each point is a list of x, y coordinates
Returns:
(np.ndarray): the xywh coordinates of the bounding boxes.
"""
boxes = []
for s in segments:
x, y = s.T # segment xy
boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy
return xyxy2xywh(np.array(boxes)) # cls, xywh
def resample_segments(segments, n=1000):
"""
Inputs a list of segments (n,2) and returns a list of segments (n,2) up-sampled to n points each.
Args:
segments (list): a list of (n,2) arrays, where n is the number of points in the segment.
n (int): number of points to resample the segment to. Defaults to 1000
Returns:
segments (list): the resampled segments.
"""
for i, s in enumerate(segments):
s = np.concatenate((s, s[0:1, :]), axis=0)
x = np.linspace(0, len(s) - 1, n)
xp = np.arange(len(s))
segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)],
dtype=np.float32).reshape(2, -1).T # segment xy
return segments
def crop_mask(masks, boxes):
"""
It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box.
Args:
masks (torch.Tensor): [n, h, w] tensor of masks
boxes (torch.Tensor): [n, 4] tensor of bbox coordinates in relative point form
Returns:
(torch.Tensor): The masks are being cropped to the bounding box.
"""
n, h, w = masks.shape
x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1) # x1 shape(n,1,1)
r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :] # rows shape(1,1,w)
c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None] # cols shape(1,h,1)
return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))
def process_mask_upsample(protos, masks_in, bboxes, shape):
"""
Takes the output of the mask head, and applies the mask to the bounding boxes. This produces masks of higher
quality but is slower.
Args:
protos (torch.Tensor): [mask_dim, mask_h, mask_w]
masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms
bboxes (torch.Tensor): [n, 4], n is number of masks after nms
shape (tuple): the size of the input image (h,w)
Returns:
(torch.Tensor): The upsampled masks.
"""
c, mh, mw = protos.shape # CHW
masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW
masks = crop_mask(masks, bboxes) # CHW
return masks.gt_(0.5)
def process_mask(protos, masks_in, bboxes, shape, upsample=False):
"""
Apply masks to bounding boxes using the output of the mask head.
Args:
protos (torch.Tensor): A tensor of shape [mask_dim, mask_h, mask_w].
masks_in (torch.Tensor): A tensor of shape [n, mask_dim], where n is the number of masks after NMS.
bboxes (torch.Tensor): A tensor of shape [n, 4], where n is the number of masks after NMS.
shape (tuple): A tuple of integers representing the size of the input image in the format (h, w).
upsample (bool): A flag to indicate whether to upsample the mask to the original image size. Default is False.
Returns:
(torch.Tensor): A binary mask tensor of shape [n, h, w], where n is the number of masks after NMS, and h and w
are the height and width of the input image. The mask is applied to the bounding boxes.
"""
c, mh, mw = protos.shape # CHW
ih, iw = shape
masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) # CHW
downsampled_bboxes = bboxes.clone()
downsampled_bboxes[:, 0] *= mw / iw
downsampled_bboxes[:, 2] *= mw / iw
downsampled_bboxes[:, 3] *= mh / ih
downsampled_bboxes[:, 1] *= mh / ih
masks = crop_mask(masks, downsampled_bboxes) # CHW
if upsample:
masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW
return masks.gt_(0.5)
def process_mask_native(protos, masks_in, bboxes, shape):
"""
It takes the output of the mask head, and crops it after upsampling to the bounding boxes.
Args:
protos (torch.Tensor): [mask_dim, mask_h, mask_w]
masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms
bboxes (torch.Tensor): [n, 4], n is number of masks after nms
shape (tuple): the size of the input image (h,w)
Returns:
masks (torch.Tensor): The returned masks with dimensions [h, w, n]
"""
c, mh, mw = protos.shape # CHW
masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
masks = scale_masks(masks[None], shape)[0] # CHW
masks = crop_mask(masks, bboxes) # CHW
return masks.gt_(0.5)
def scale_masks(masks, shape, padding=True):
"""
Rescale segment masks to shape.
Args:
masks (torch.Tensor): (N, C, H, W).
shape (tuple): Height and width.
padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
rescaling.
"""
mh, mw = masks.shape[2:]
gain = min(mh / shape[0], mw / shape[1]) # gain = old / new
pad = [mw - shape[1] * gain, mh - shape[0] * gain] # wh padding
if padding:
pad[0] /= 2
pad[1] /= 2
top, left = (int(pad[1]), int(pad[0])) if padding else (0, 0) # y, x
bottom, right = (int(mh - pad[1]), int(mw - pad[0]))
masks = masks[..., top:bottom, left:right]
masks = F.interpolate(masks, shape, mode='bilinear', align_corners=False) # NCHW
return masks
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None, normalize=False, padding=True):
"""
Rescale segment coordinates (xy) from img1_shape to img0_shape
Args:
img1_shape (tuple): The shape of the image that the coords are from.
coords (torch.Tensor): the coords to be scaled of shape n,2.
img0_shape (tuple): the shape of the image that the segmentation is being applied to.
ratio_pad (tuple): the ratio of the image size to the padded image size.
normalize (bool): If True, the coordinates will be normalized to the range [0, 1]. Defaults to False.
padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
rescaling.
Returns:
coords (torch.Tensor): The scaled coordinates.
"""
if ratio_pad is None: # calculate from img0_shape
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
if padding:
coords[..., 0] -= pad[0] # x padding
coords[..., 1] -= pad[1] # y padding
coords[..., 0] /= gain
coords[..., 1] /= gain
clip_coords(coords, img0_shape)
if normalize:
coords[..., 0] /= img0_shape[1] # width
coords[..., 1] /= img0_shape[0] # height
return coords
def masks2segments(masks, strategy='largest'):
"""
It takes a list of masks(n,h,w) and returns a list of segments(n,xy)
Args:
masks (torch.Tensor): the output of the model, which is a tensor of shape (batch_size, 160, 160)
strategy (str): 'concat' or 'largest'. Defaults to largest
Returns:
segments (List): list of segment masks
"""
segments = []
for x in masks.int().cpu().numpy().astype('uint8'):
c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
if c:
if strategy == 'concat': # concatenate all segments
c = np.concatenate([x.reshape(-1, 2) for x in c])
elif strategy == 'largest': # select largest segment
c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2)
else:
c = np.zeros((0, 2)) # no segments found
segments.append(c.astype('float32'))
return segments
def clean_str(s):
"""
Cleans a string by replacing special characters with underscore _
Args:
s (str): a string needing special characters replaced
Returns:
(str): a string with special characters replaced by an underscore _
"""
return re.sub(pattern='[|@#!¡·$€%&()=?¿^*;:,¨´><+]', repl='_', string=s)