yolov5代码及原理详解

yolov5代码及原理解析

---

---

一、代码及原理解析

1、输入端

(1) letterbox

此模块作用为将原始图片统一缩放到一个标准尺寸，再送入检测网络中。

def letterbox(im, 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 = im.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 val 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
        im = cv2.resize(im, 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))
    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return im, ratio, (dw, dh)

步骤为：
1）计算new_shape[0] / shape[0]和new_shape[1] / shape[1]，选取其最小值r。
2）将原图像resize为int(round(shape[1] * r)), int(round(shape[0] * r))。
3）分别计算new_shape[1] - new_unpad[0]对stride（默认是32）取余数和new_shape[0] - new_unpad[1]对stride（默认是32）取余数的结果，记为dw和dh。
4）在resize后的图像的基础上填充dw和dh大小像素的空白边界像素。

(2) Mosaic增强

首先介绍一下load_image函数

def load_image(self, i):
    # Loads 1 image from dataset index 'i', returns (im, original hw, resized hw)
    im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i],
    if im is None:  # not cached in RAM
        if fn.exists():  # load npy
            im = np.load(fn)
        else:  # read image
            im = cv2.imread(f)  # BGR
            assert im is not None, f'Image Not Found {f}'
        h0, w0 = im.shape[:2]  # orig hw
        r = self.img_size / max(h0, w0)  # ratio
        if r != 1:  # if sizes are not equal
            im = cv2.resize(im,
                            (int(w0 * r), int(h0 * r)),
                            interpolation=cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA)
        return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
    else:
        return self.ims[i], self.im_hw0[i], self.im_hw[i]  # im, hw_original, hw_resized

其类似于letterbox，只是缺少了填充边缘的步骤。此函数将图像进行resize并输出resize前后的图像大小。

接下来看一下四张图进行Mosaic增强的函数load_mosaic：

def load_mosaic(self, index):
    # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
    labels4, segments4 = [], []
    s = self.img_size
    yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border)  # mosaic center x, y
    indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
    random.shuffle(indices)
    for i, index in enumerate(indices):
        # Load image
        img, _, (h, w) = self.load_image(index)

        # place img in img4
        if i == 0:  # top left
            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
        elif i == 1:  # top right
            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
        elif i == 2:  # bottom left
            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
        elif i == 3:  # bottom right
            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
        padw = x1a - x1b
        padh = y1a - y1b

        # Labels
        labels, segments = self.labels[index].copy(), self.segments[index].copy()
        if labels.size:
            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
            segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
        labels4.append(labels)
        segments4.extend(segments)

    # Concat/clip labels
    labels4 = np.concatenate(labels4, 0)
    for x in (labels4[:, 1:], *segments4):
        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
    # img4, labels4 = replicate(img4, labels4)  # replicate

    # Augment
    img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
    img4, labels4 = random_perspective(img4, labels4, segments4,
                                       degrees=self.hyp['degrees'],
                                       translate=self.hyp['translate'],
                                       scale=self.hyp['scale'],
                                       shear=self.hyp['shear'],
                                       perspective=self.hyp['perspective'],
                                       border=self.mosaic_border)  # border to remove

    return img4, labels4

步骤如下：
1）确定拼接的四张图片的相接的点yc, xc，其为（img_size//2，3img_size//2）中的随机点。
2）随机抽取序列号为index的图片，通过load_image函数将其resize并读取resize后的h和w。
3）生成（2img_size，2*img_size）的空白图片，并将resize后的小图片复制到大空白图片中。
注意：由于yc, xc是随机的，最终填充的图片中可能存在大量空白。

由上述程序可以看到，load_mosaic函数中还存在random_perspective函数，此函数中包含了一些其它的图像增强操作，包括degrees:旋转；translate:水平和垂直转换；scale:缩放；shear:图片裁剪；perspective:透视变换。
相应程序如下所示：

def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
                       border=(0, 0)):
    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
    # targets = [cls, xyxy]

    height = im.shape[0] + border[0] * 2  # shape(h,w,c)
    width = im.shape[1] + border[1] * 2

    # Center
    C = np.eye(3)
    C[0, 2] = -im.shape[1] / 2  # x translation (pixels)
    C[1, 2] = -im.shape[0] / 2  # y translation (pixels)

    # Perspective
    P = np.eye(3)
    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)

    # Rotation and Scale
    R = np.eye(3)
    a = random.uniform(-degrees, degrees)
    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
    s = random.uniform(1 - scale, 1 + scale)
    # s = 2 ** random.unifoonMatrix2D(angle=a, center=(0, 0), scale=s)
    rm(-scale, scale)
    R[:2] = cv2.getRotati
    # Shear
    S = np.eye(3)
    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)

    # Translation
    T = np.eye(3)
    T[0, 2] = random.