博客
关于我
数据增强--对于目标检测(边框、图像)
阅读量:559 次
发布时间:2019-03-09

本文共 6607 字,大约阅读时间需要 22 分钟。

import torchfrom PIL import Image, ImageFont, ImageDrawfrom functools import reduceimport scipy.io as sciofrom PIL import Imageimport cv2 as cvimport numpy as npimport randomimport imutilsfrom imgaug import augmenters as iaadef horisontal_flip(images, targets):    images = torch.flip(images, [-1])    targets[:, 2] = 1 - targets[:, 2]    return images, targetsdef compose(*funcs):    """Compose arbitrarily many functions, evaluated left to right.    Reference: https://mathieularose.com/function-composition-in-python/    """    # return lambda x: reduce(lambda v, f: f(v), funcs, x)    if funcs:        return reduce(lambda f, g: lambda *a, **kw: g(f(*a, **kw)), funcs)    else:        raise ValueError('Composition of empty sequence not supported.')def letterbox_image(image, size):    '''resize image with unchanged aspect ratio using padding'''    iw, ih = image.size    w, h = size    scale = min(w / iw, h / ih)    nw = int(iw * scale)    nh = int(ih * scale)    image = image.resize((nw, nh), Image.BICUBIC)    new_image = Image.new('RGB', size, (128, 128, 128))    new_image.paste(image, ((w - nw) // 2, (h - nh) // 2))    return new_imagedef rand(a=0, b=1):    return np.random.rand() * (b - a) + adef resize_3D_data(ima, size=(416, 416)):    dat = np.zeros([416, 416, 15])    for i in range(15):        slice = np.squeeze(ima[:, :, i])        re_slice = cv.resize(slice.astype('uint8'), size, interpolation=cv.INTER_AREA)        dat[:, :, i] = re_slice    return datdef random_crop(cell, boxes):    dx = random.randint(15, 20)    dy = random.randint(15, 20)    shape = cell.shape    nx = shape[0]    ny = shape[1]    boxes[:, [0, 2]] = boxes[:, [0, 2]] - dx    boxes[:, [1, 3]] = boxes[:, [1, 3]] - dy    new_cell = np.zeros_like(cell)    new_cell[0:int(nx - dx), 0:int(ny - dy)] = cell[dx:, dy:]    new_cell = Image.fromarray(new_cell.astype('uint8')).convert('RGB')    new_cell = cv.cvtColor(np.asarray(new_cell), cv.COLOR_RGB2BGR)    boxes = np.where(boxes < 0, 0, boxes)    return new_cell, boxesdef random_noise(cell, boxes):    image = Image.fromarray(cell.astype('uint8')).convert('RGB')    image = cv.cvtColor(np.asarray(image), cv.COLOR_RGB2BGR)    seq = iaa.Sequential(        [            iaa.AdditiveGaussianNoise(scale=0.05 * 255),            iaa.LinearContrast((0.75, 1.5)),            iaa.GaussianBlur(sigma=(0, 4.0)),            iaa.Dropout(p=(0, 0.2)),            iaa.CoarseDropout(0.02, size_percent=0.5)        ], random_order=True    )    images_aug = seq.augment_images([image])[0]    new_cell = Image.fromarray(cv.cvtColor(images_aug, cv.COLOR_BGR2RGB))    return new_cell, boxesdef gray_level_crop(cell, boxes):    max_val = random.randint(80, 255) / 255    new_cell = cell * max_val    new_cell = Image.fromarray(new_cell.astype('uint8')).convert('RGB')    new_cell = cv.cvtColor(np.asarray(new_cell), cv.COLOR_RGB2BGR)    return new_cell, boxesdef rotate_box(box, M, shape):    # print(box)    y1, x1, y2, x2 = box    p1 = np.array([x1, y1, 1]).reshape((3, 1))    p2 = np.array([x1, y2, 1]).reshape((3, 1))    p3 = np.array([x2, y2, 1]).reshape((3, 1))    p4 = np.array([x2, y1, 1]).reshape((3, 1))    p1 = np.matmul(M, p1)    p2 = np.matmul(M, p2)    p3 = np.matmul(M, p3)    p4 = np.matmul(M, p4)    x1 = np.min([p1[0, 0], p2[0, 0], p3[0, 0], p4[0, 0]])    x2 = np.max([p1[0, 0], p2[0, 0], p3[0, 0], p4[0, 0]])    y1 = np.min([p1[1, 0], p2[1, 0], p3[1, 0], p4[1, 0]])    y2 = np.max([p1[1, 0], p2[1, 0], p3[1, 0], p4[1, 0]])    if x1 < 0:        x1 = 0    if x1 > shape[1]:        x1 = shape[1] - 1    if x2 < 0:        x2 = 0    if x2 > shape[1]:        x2 = shape[1] - 1    if y1 < 0:        y1 = 0    if y1 > shape[0]:        y1 = shape[0] - 1    if y2 < 0:        y2 = 0    if y2 > shape[0]:        y2 = shape[0] - 1    box = [y1, x1, y2, x2]    # print(box)    # print('--------------')    return boxdef random_rotate(cell, boxes, angle=45):    (h, w) = cell.shape    (cX, cY) = (w // 2, h // 2)    new_cell = imutils.rotate_bound(cell.astype('uint8'), angle)    M = cv.getRotationMatrix2D((cX, cY), -angle, 1.0)    cos = np.abs(M[0, 0])    sin = np.abs(M[0, 1])    # compute the new bounding dimensions of the image    nW = int((h * sin) + (w * cos))    nH = int((h * cos) + (w * sin))    # adjust the rotation matrix to take into account translation    M[0, 2] += (nW / 2) - cX    M[1, 2] += (nH / 2) - cY    new_boxes = []    for i in range(len(boxes)):        new_boxes.append(rotate_box(boxes[i], M, new_cell.shape))    if len(new_boxes) > 0:        new_boxes = np.array(new_boxes)    new_cell = Image.fromarray(new_cell.astype('uint8')).convert('RGB')    new_cell = cv.cvtColor(np.asarray(new_cell), cv.COLOR_RGB2BGR)    return new_cell, new_boxesdef random_argument(data, cell, boxes):    # crop region ...    if rand() < .5:        cell, boxes = random_crop(cell, boxes)    # add noise ...    if rand() < .5:        cell, boxes = random_noise(cell, boxes)    # add noise ...    if rand() < .5:        cell, boxes = gray_level_crop(cell, boxes)    # rotate ...    if rand() < .5:       cell, boxes = random_rotate(cell, boxes, random.randint(0, 90))    return cell, boxesdef pad_to_square(img, pad_value):    h, w, c = img.shape    dim_diff = np.abs(h - w)    # (upper / left) padding and (lower / right) padding    pad1, pad2 = dim_diff // 2, dim_diff - dim_diff // 2    # Determine padding    pad = ((0, 0), (pad1, pad2), (0, 0)) if w <= h else ((pad1, pad2), (0, 0), (0, 0))    # Add padding    img = np.pad(img, pad, "constant", constant_values=pad_value)    return img, padif __name__ == '__main__':    dat = scio.loadmat(        '/home/xuxu/Data/CTC_Signal_Datasets/Processed/20200616_cell_signalmark_39frames/Green/653802_650142_0_675.mat')    cell = dat['signal'].astype('uint8')    boxe = dat['rects']    print('boxe', boxe)    # image = Image.fromarray(cell.astype('uint8')).convert('RGB')    # image = cv.cvtColor(np.asarray(image), cv.COLOR_RGB2BGR)    # for x1, y1, x2, y2 in boxes:    #     cv.rectangle(image, (y1, x1), (y2, x2), (255, 255, 255), thickness=1)    # cv.imwrite('1.jpg', image)    new_cell, new_boxes = random_rotate(cell, boxe)    # new_cell, new_boxes = gray_level_crop(cell, boxe)    # print('new_boxes', new_boxes)    # new_boxes = np.where(new_boxes < 0, 0, new_boxes)    # print('new_boxes', new_boxes)    # image = Image.fromarray(new_cell.astype('uint8')).convert('RGB')    # image = cv.cvtColor(np.asarray(image), cv.COLOR_RGB2BGR)    for x1, y1, x2, y2 in new_boxes:        cv.rectangle(new_cell, (int(y1), int(x1)), (int(y2), int(x2)), (255, 255, 255), thickness=1)    cv.imwrite('1.jpg', new_cell)

其中图像加噪使用的是imgaug库

转载地址:http://ewhsz.baihongyu.com/

你可能感兴趣的文章
mongodb定时备份数据库
查看>>
mppt算法详解-ChatGPT4o作答
查看>>
mpvue的使用(一)必要的开发环境
查看>>
MQ 重复消费如何解决?
查看>>
mqtt broker服务端
查看>>
MQTT 保留消息
查看>>
MQTT 持久会话与 Clean Session 详解
查看>>
MQTT工作笔记0007---剩余长度
查看>>
MQTT工作笔记0009---订阅主题和订阅确认
查看>>
Mqtt搭建代理服务器进行通信-浅析
查看>>
MS Edge浏览器“STATUS_INVALID_IMAGE_HASH“兼容性问题
查看>>
ms sql server 2008 sp2更新异常
查看>>
MS UC 2013-0-Prepare Tool
查看>>
MSBuild 教程(2)
查看>>
msbuild发布web应用程序
查看>>
MSB与LSB
查看>>
MSCRM调用外部JS文件
查看>>
MSCRM调用外部JS文件
查看>>
MSEdgeDriver (Chromium) 不适用于版本 >= 79.0.313 (Canary)
查看>>
MsEdgeTTS开源项目使用教程
查看>>