Deep Learning的案例-YoloV5中的数据增强

mAP@[.5:.95](someone denoted mAP@[.5,.95]) means average mAP over different IoU thresholds, from 0.5 to 0.95, step 0.05 (0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95).

hyp参数列表

lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.2  # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.937  # SGD momentum/Adam beta1
weight_decay: 0.0005  # optimizer weight decay 5e-4
warmup_epochs: 3.0  # warmup epochs (fractions ok)
warmup_momentum: 0.8  # warmup initial momentum
warmup_bias_lr: 0.1  # warmup initial bias lr
box: 0.05  # box loss gain
cls: 0.5  # cls loss gain
cls_pw: 1.0  # cls BCELoss positive_weight
obj: 1.0  # obj loss gain (scale with pixels)
obj_pw: 1.0  # obj BCELoss positive_weight
iou_t: 0.20  # IoU training threshold
anchor_t: 4.0  # anchor-multiple threshold
# anchors: 3  # anchors per output layer (0 to ignore)
fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
============================分割线==================================================
hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4  # image HSV-Value augmentation (fraction)
degrees: 0.0  # image rotation (+/- deg)
translate: 0.1  # image translation (+/- fraction)
scale: 0.5  # image scale (+/- gain)
shear: 0.0  # image shear (+/- deg)
perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
flipud: 0.0  # image flip up-down (probability)
fliplr: 0.5  # image flip left-right (probability)
mosaic: 1.0  # image mosaic (probability)
mixup: 0.0  # image mixup (probability)
copy_paste: 0.0  # segment copy-paste (probability)

其中hsv以下属于数据增强的内容，基本都在datasets.py这个文件中，新的版本调整到augmentations.py文件并增加了copy paste，说明对此越来越重视了。 对照参考B站的up主BAI Yong绘制的网络结构图

• 首先loadimage， 把image resize成按照长边原图像比例，defualt = 640

def load_image(self, index):
    # loads 1 image from dataset, returns img, original hw, resized hw
    img = self.imgs[index]
    if img is None:  # not cached
        path = self.img_files[index]
        img = cv2.imread(path)  # BGR
        assert img is not None, 'Image Not Found ' + path
        h0, w0 = img.shape[:2]  # orig hw
        r = self.img_size / max(h0, w0)  # ratio
        if r != 1:  # if sizes are not equal
            img = cv2.resize(img, (int(w0 * r), int(h0 * r)),
                             interpolation=cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR)
        return img, (h0, w0), img.shape[:2]  # img, hw_original, hw_resized
    else:
        return self.imgs[index], self.img_hw0[index], self.img_hw[index]  # img, hw_original, hw_resized

• 然后进行letterbox填充
  参考https://blog.csdn.net/ChuiGeDaQiQiu/article/details/113048124

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)

• 然后随机是否进行mosaic 4张图拼接增强
  参考https://blog.csdn.net/weixin_44791964/article/details/105996954

• 然后随机random_perspective,里面包含了degrees，translate，scale，shear，perspective因素

    # Center
    C = np.eye(3)
    C[0, 2] = -img.shape[1] / 2  # x translation (pixels)
    C[1, 2] = -img.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.uniform(-scale, scale)
    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)

    # 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.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)

    # Combined rotation matrix
    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
        if perspective:
            img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114))
        else:  # affine
            img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114))

• 颜色随机

def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5):
    if hgain or sgain or vgain:
        r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains
        hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
        dtype = img.dtype  # uint8

        x = np.arange(0, 256, dtype=r.dtype)
        lut_hue = ((x * r[0]) % 180).astype(dtype)
        lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
        lut_val = np.clip(x * r[2], 0, 255).astype(dtype)

        img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
        cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)  # no return needed

• mixup

def mixup(im, labels, im2, labels2):
    # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
    r = np.random.beta(32.0, 32.0)  # mixup ratio, alpha=beta=32.0
    im = (im * r + im2 * (1 - r)).astype(np.uint8)
    labels = np.concatenate((labels, labels2), 0)
    return im, labels

• copy_paste

def copy_paste(im, labels, segments, p=0.5):
    # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
    n = len(segments)
    if p and n:
        h, w, c = im.shape  # height, width, channels
        im_new = np.zeros(im.shape, np.uint8)
        for j in random.sample(range(n), k=round(p * n)):
            l, s = labels[j], segments[j]
            box = w - l[3], l[2], w - l[1], l[4]
            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
            if (ioa < 0.30).all():  # allow 30% obscuration of existing labels
                labels = np.concatenate((labels, [[l[0], *box]]), 0)
                segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
                cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)

        result = cv2.bitwise_and(src1=im, src2=im_new)
        result = cv2.flip(result, 1)  # augment segments (flip left-right)
        i = result > 0  # pixels to replace
        # i[:, :] = result.max(2).reshape(h, w, 1)  # act over ch
        im[i] = result[i]  # cv2.imwrite('debug.jpg', im)  # debug

    return im, labels, segments

题外

如果遇到_pickle.UnpicklingError: STACK_GLOBAL requires str问题，需要删除一下dataset中的缓存文件xxx.cache