常用的工具函数模块汇总
目标检测图像预处理工具函数letterbox()
def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
# Resize and pad image while meeting stride-multiple constraints
shape = img.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better test mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return img, ratio, (dw, dh)
图像数据进入模型处理前的与操作
def preprocess(self, img):
img0 = img.copy()
img = letterbox(img, new_shape=self.img_size)[0]
img = img[:, :, ::-1].transpose(2, 0, 1) # 将图像有BGR--->RGB,并转成[通道，高度，宽度]
img = np.ascontiguousarray(img)
img = torch.from_numpy(img).to(self.device)
img = img.half() # 半精度
img /= 255.0 # 图像归一化
if img.ndimension() == 3:
img = img.unsqueeze(0)
return img0, img
def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
# Resize and pad image while meeting stride-multiple constraints
shape = img.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better test mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return img, ratio, (dw, dh)
坐标框格式转换xywh2xyxy()
def xywh2xyxy(x):
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
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
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
return y
将图像与处理后的图像检测框缩放至原始图像上的工具函数scale_coords()
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
"""
img1_shape:缩放后图像的尺寸
coords：坐标框数据
img0_shape：原始图像shape
ratio_pad：ratio_pad=None
"""
# Rescale coords (xyxy) from img1_shape to img0_shape
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]
coords[:, [0, 2]] -= pad[0] # x padding
coords[:, [1, 3]] -= pad[1] # y padding
coords[:, :4] /= gain
clip_coords(coords, img0_shape)
return coords
def clip_coords(boxes, img_shape):
# Clip bounding xyxy bounding boxes to image shape (height, width)
boxes[:, 0].clamp_(0, img_shape[1]) # x1
boxes[:, 1].clamp_(0, img_shape[0]) # y1
boxes[:, 2].clamp_(0, img_shape[1]) # x2
boxes[:, 3].clamp_(0, img_shape[0]) # y2
opencv读取视频数据
import numpy as np
import cv2 as cv
# 1.获取视频对象
cap = cv.VideoCapture('DOG.wmv')
# 2.判断是否读取成功
while(cap.isOpened()):
# 3.获取每一帧图像
ret, frame = cap.read()
# 4. 获取成功显示图像
if ret == True:
cv.imshow('frame',frame)
# 5.每一帧间隔为25ms
if cv.waitKey(25) & 0xFF == ord('q'):
break
# 6.释放视频对象
cap.release()
cv.destoryAllwindows()
opencv保存视频到本地
import cv2 as cv
import numpy as np
# 1. 读取视频
cap = cv.VideoCapture("DOG.wmv")
# 2. 获取图像的属性（宽和高，）,并将其转换为整数
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
# 3. 创建保存视频的对象，设置编码格式，帧率，图像的宽高等
out = cv.VideoWriter('outpy.avi',cv.VideoWriter_fourcc('M','J','P','G'), 10, (frame_width,frame_height))
while(True):
# 4.获取视频中的每一帧图像
ret, frame = cap.read()
if ret == True:
# 5.将每一帧图像写入到输出文件中
out.write(frame)
else:
break
# 6.释放资源
cap.release()
out.release()
cv.destroyAllWindows()
6
import torch
import torchvision.transforms as transforms
import numpy as np
import cv2
import logging
from .model import Net
'''
特征提取器：
提取对应bounding box中的特征, 得到一个固定维度的embedding作为该bounding box的代表，
供计算相似度时使用。
模型训练是按照传统ReID的方法进行，使用Extractor类的时候输入为一个list的图片，得到图片对应的特征。
'''
class Extractor(object):
def __init__(self, model_path, use_cuda=True):
self.net = Net(reid=True)
self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
state_dict = torch.load(model_path, map_location=lambda storage, loc: storage)['net_dict']
self.net.load_state_dict(state_dict)
logger = logging.getLogger("root.tracker")
logger.info("Loading weights from {}... Done!".format(model_path))
self.net.to(self.device)
self.size = (64, 128)
self.norm = transforms.Compose([
# RGB图片数据范围是[0-255]，需要先经过ToTensor除以255归一化到[0,1]之后，
# 再通过Normalize计算(x - mean)/std后，将数据归一化到[-1,1]。
transforms.ToTensor(),
# mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225]是从imagenet训练集中算出来的
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
def _preprocess(self, im_crops):
"""
TODO:
1. to float with scale from 0 to 1
2. resize to (64, 128) as Market1501 dataset did
3. concatenate to a numpy array
3. to torch Tensor
4. normalize
"""
def _resize(im, size):
return cv2.resize(im.astype(np.float32)/255., size)
im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(0) for im in im_crops], dim=0).float()
return im_batch
# __call__()是一个非常特殊的实例方法。该方法的功能类似于在类中重载 () 运算符，
# 使得类实例对象可以像调用普通函数那样，以“对象名()”的形式使用。
def __call__(self, im_crops):
im_batch = self._preprocess(im_crops)
with torch.no_grad():
im_batch = im_batch.to(self.device)
features = self.net(im_batch)
return features.cpu().numpy()
if __name__ == '__main__':
img = cv2.imread("demo.jpg")[:,:,(2,1,0)]
extr = Extractor("checkpoint/ckpt.t7")
feature = extr(img)
print(feature.shape)
非极大值抑制处理的一种实现
# vim: expandtab:ts=4:sw=4
import numpy as np
import cv2
def non_max_suppression(boxes, max_bbox_overlap, scores=None):
"""Suppress overlapping detections.
Original code from [1]_ has been adapted to include confidence score.
.. [1] http://www.pyimagesearch.com/2015/02/16/
faster-non-maximum-suppression-python/
Examples
--------
>>> boxes = [d.roi for d in detections]
>>> scores = [d.confidence for d in detections]
>>> indices = non_max_suppression(boxes, max_bbox_overlap, scores)
>>> detections = [detections[i] for i in indices]
Parameters
----------
boxes : ndarray
Array of ROIs (x, y, width, height).
max_bbox_overlap : float
ROIs that overlap more than this values are suppressed.
scores : Optional[array_like]
Detector confidence score.
Returns
-------
List[int]
Returns indices of detections that have survived non-maxima suppression.
"""
if len(boxes) == 0:
return []
boxes = boxes.astype(np.float)
pick = []
x1 = boxes[:, 0]
y1 = boxes[:, 1]
x2 = boxes[:, 2] + boxes[:, 0]
y2 = boxes[:, 3] + boxes[:, 1]
area = (x2 - x1 + 1) * (y2 - y1 + 1)
if scores is not None:
idxs = np.argsort(scores)
else:
idxs = np.argsort(y2)
while len(idxs) > 0:
last = len(idxs) - 1
i = idxs[last]
pick.append(i)
xx1 = np.maximum(x1[i], x1[idxs[:last]])
yy1 = np.maximum(y1[i], y1[idxs[:last]])
xx2 = np.minimum(x2[i], x2[idxs[:last]])
yy2 = np.minimum(y2[i], y2[idxs[:last]])
w = np.maximum(0, xx2 - xx1 + 1)
h = np.maximum(0, yy2 - yy1 + 1)
overlap = (w * h) / area[idxs[:last]] # IOU
idxs = np.delete(
idxs, np.concatenate(
([last], np.where(overlap > max_bbox_overlap)[0])))
return pick
非极大值抑制处理的普遍实现
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
labels=()):
"""Runs Non-Maximum Suppression (NMS) on inference results
Returns:
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
"""
nc = prediction.shape[2] - 5 # number of classes
xc = prediction[..., 4] > conf_thres # candidates
# Settings
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
max_det = 300 # maximum number of detections per image
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
time_limit = 10.0 # seconds to quit after
redundant = True # require redundant detections
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
merge = False # use merge-NMS
t = time.time()
output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
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
# Cat apriori labels if autolabelling
if labels and len(labels[xi]):
l = labels[xi]
v = torch.zeros((len(l), nc + 5), device=x.device)
v[:, :4] = l[:, 1:5] # box
v[:, 4] = 1.0 # conf
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
x = torch.cat((x, v), 0)
# If none remain process next image
if not x.shape[0]:
continue
# Compute conf
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
box = xywh2xyxy(x[:, :4])
# Detections matrix nx6 (xyxy, conf, cls)
if multi_label:
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
else: # best class only
conf, j = x[:, 5:].max(1, keepdim=True)
x = torch.cat((box, conf, j.float()), 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)]
# Apply finite constraint
# if not torch.isfinite(x).all():
# x = x[torch.isfinite(x).all(1)]
# Check shape
n = x.shape[0] # number of boxes
if not n: # no boxes
continue
elif n > max_nms: # excess boxes
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
# 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
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
if i.shape[0] > max_det: # limit detections
i = i[:max_det]
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
weights = iou * scores[None] # box weights
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
if redundant:
i = i[iou.sum(1) > 1] # require redundancy
output[xi] = x[i]
if (time.time() - t) > time_limit:
print(f'WARNING: NMS time limit {time_limit}s exceeded')
break # time limit exceeded
return output
距离度量工具类–欧式距离、余弦距离
def _pdist(a, b):
"""Compute pair-wise squared distance between points in `a` and `b`.
计算两个矩阵的欧式距离
Parameters
----------
a : array_like
An NxM matrix of N samples of dimensionality M.
b : array_like
An LxM matrix of L samples of dimensionality M.
Returns
-------
ndarray
Returns a matrix of size len(a), len(b) such that element (i, j)
contains the squared distance between `a[i]` and `b[j]`.
用于计算成对点之间的平方距离
a :NxM 矩阵，代表 N 个样本，每个样本 M 个数值
b :LxM 矩阵，代表 L 个样本，每个样本有 M 个数值
返回的是 NxL 的矩阵，比如 dist[i][j] 代表 a[i] 和 b[j] 之间的平方和距离
参考:https://blog.csdn.net/frankzd/article/details/80251042
"""
a, b = np.asarray(a), np.asarray(b)
if len(a) == 0 or len(b) == 0:
return np.zeros((len(a), len(b)))
a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1)
r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :]
r2 = np.clip(r2, 0., float(np.inf)) # 对数据进行限制
return r2
def _cosine_distance(a, b, data_is_normalized=False):
"""Compute pair-wise cosine distance between points in `a` and `b`.
Parameters
----------
a : array_like
An NxM matrix of N samples of dimensionality M.
b : array_like
An LxM matrix of L samples of dimensionality M.
data_is_normalized : Optional[bool]
If True, assumes rows in a and b are unit length vectors.
Otherwise, a and b are explicitly normalized to lenght 1.
Returns
-------
ndarray
Returns a matrix of size len(a), len(b) such that eleement (i, j)
contains the squared distance between `a[i]` and `b[j]`.
用于计算成对点之间的余弦距离
a :NxM 矩阵，代表 N 个样本，每个样本 M 个数值
b :LxM 矩阵，代表 L 个样本，每个样本有 M 个数值
返回的是 NxL 的矩阵，比如 c[i][j] 代表 a[i] 和 b[j] 之间的余弦距离
参考：
https://blog.csdn.net/u013749540/article/details/51813922
"""
if not data_is_normalized:
# np.linalg.norm 求向量的范式，默认是 L2 范式
a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True)
b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True)
return 1. - np.dot(a, b.T) # 余弦距离 = 1 - 余弦相似度
最近邻距离求解
def _pdist(a, b):
"""Compute pair-wise squared distance between points in `a` and `b`.
计算两个矩阵的欧式距离
Parameters
----------
a : array_like
An NxM matrix of N samples of dimensionality M.
b : array_like
An LxM matrix of L samples of dimensionality M.
Returns
-------
ndarray
Returns a matrix of size len(a), len(b) such that element (i, j)
contains the squared distance between `a[i]` and `b[j]`.
用于计算成对点之间的平方距离
a :NxM 矩阵，代表 N 个样本，每个样本 M 个数值
b :LxM 矩阵，代表 L 个样本，每个样本有 M 个数值
返回的是 NxL 的矩阵，比如 dist[i][j] 代表 a[i] 和 b[j] 之间的平方和距离
参考:https://blog.csdn.net/frankzd/article/details/80251042
"""
a, b = np.asarray(a), np.asarray(b)
if len(a) == 0 or len(b) == 0:
return np.zeros((len(a), len(b)))
a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1)
r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :]
r2 = np.clip(r2, 0., float(np.inf)) # 对数据进行限制
return r2
def _cosine_distance(a, b, data_is_normalized=False):
"""Compute pair-wise cosine distance between points in `a` and `b`.
Parameters
----------
a : array_like
An NxM matrix of N samples of dimensionality M.
b : array_like
An LxM matrix of L samples of dimensionality M.
data_is_normalized : Optional[bool]
If True, assumes rows in a and b are unit length vectors.
Otherwise, a and b are explicitly normalized to lenght 1.
Returns
-------
ndarray
Returns a matrix of size len(a), len(b) such that eleement (i, j)
contains the squared distance between `a[i]` and `b[j]`.
用于计算成对点之间的余弦距离
a :NxM 矩阵，代表 N 个样本，每个样本 M 个数值
b :LxM 矩阵，代表 L 个样本，每个样本有 M 个数值
返回的是 NxL 的矩阵，比如 c[i][j] 代表 a[i] 和 b[j] 之间的余弦距离
参考：
https://blog.csdn.net/u013749540/article/details/51813922
"""
if not data_is_normalized:
# np.linalg.norm 求向量的范式，默认是 L2 范式
a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True)
b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True)
return 1. - np.dot(a, b.T) # 余弦距离 = 1 - 余弦相似度
def _nn_euclidean_distance(x, y):
""" Helper function for nearest neighbor distance metric (Euclidean).
使用欧式距离来求得最近邻距离
Parameters
----------
x : ndarray
A matrix of N row-vectors (sample points).
y : ndarray
A matrix of M row-vectors (query points).
Returns
-------
ndarray
A vector of length M that contains for each entry in `y` the
smallest Euclidean distance to a sample in `x`.
"""
distances = _pdist(x, y)
return np.maximum(0.0, distances.min(axis=0))
def _nn_cosine_distance(x, y):
""" Helper function for nearest neighbor distance metric (cosine).
使用余弦距离求得最近邻
Parameters
----------
x : ndarray
A matrix of N row-vectors (sample points).
y : ndarray
A matrix of M row-vectors (query points).
Returns
-------
ndarray
A vector of length M that contains for each entry in `y` the
smallest cosine distance to a sample in `x`.
"""
distances = _cosine_distance(x, y)
return distances.min(axis=0)
版权声明：本文为guoqingru0311原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。