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)