操作系统：Windows 10

IDE：Pycharm

Python： 3.6.2 且已安装好 tensorflow , keras，pyqt5,lxml包

二、快速使用yolo3预测图片

keras-yolo3源代码, 下载到本地后用 Pycharm 打开。

初始权重文件，在QQ群文件中，下载好后放在 上述文件keras-yolo3 一级目录下。

命令行中执行如下命令将 darknet 下的 yolov3 配置文件转换成 keras 适用的 .h5 文件。

命令：python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5

运行预测图像程序

命令：python yolo_video.py --image

一切正常的话，会让你输入待识别的图片路径，图片目录以keras-yolo3为一级目录。若待测图片放在该一级目录下，则直接输入图片名即可。

命令：Input image filename:test.jpg

三、训练自己的数据集进行目标检测

在该项目中新建文件夹如下所示：

安装数据标记工具 labelImg

用 powershell 进入到该项目根目录下，执行

命令：pyrcc5 -o resources.py resources.qrc

命令：python labelImg.py

弹出用户界面，使用如下：

在 keras-yolo3 一级目录下新建 test.py ,如上上图。复制如下代码：

/**华丽的代码分割线**/

import os

import random

trainval_percent = 0.2

train_percent = 0.8

xmlfilepath = 'Annotations'

txtsavepath = 'ImageSets\Main'

total_xml = os.listdir(xmlfilepath)

num = len(total_xml)

list = range(num)

tv = int(num * trainval_percent)

tr = int(tv * train_percent)

trainval = random.sample(list, tv)

train = random.sample(trainval, tr)

ftrainval = open('ImageSets/Main/trainval.txt', 'w')

ftest = open('ImageSets/Main/test.txt', 'w')

ftrain = open('ImageSets/Main/train.txt', 'w')

fval = open('ImageSets/Main/val.txt', 'w')

for i in list:

    name = total_xml[i][:-4] + '\n'

    if i in trainval:

        ftrainval.write(name)

        if i in train:

            ftest.write(name)

        else:

            fval.write(name)

    else:

        ftrain.write(name)

ftrainval.close()

ftrain.close()

fval.close()

ftest.close()

/**华丽的代码分割线**/

运行之后，在keras-yolo3-master\VOCdevkit\VOC2007\ImageSets\Main目录下就是制作好的数据集。

修改voc_annotion.py中的classes变量为自己需要的各式标签

/**华丽的代码分割线**/

classes = ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9"] #这里是10个数字标签

# classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]

/**华丽的代码分割线**/

然后运行该文件，会在keras-yolo3-master一级目录下生成三个2007_***.txt的文件。

修改参数文件yolo3.cfg

打开yolo3.cfg文件。搜索 yolo(共出现三次)，每次按下图都要修改。

/**华丽的代码分割线**/

[convolutional]

size=1

stride=1

pad=1

filters=45    # 3*(5+len(classes)).  original value = 255

activation=linear

[yolo]

mask = 6,7,8

anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326

classes=10      #train labels.  original value = 80

num=9

jitter=.3

ignore_thresh = .5

truth_thresh = 1

random=0        #if you memory is small, choice 0. origninal value = 1

/**华丽的代码分割线**/

修改model_data下的voc_classes.txt为自己训练的类别

/**华丽的代码分割线**/

label0

label2

...

...

label9

/**华丽的代码分割线**/

修改train.py代码如下，做训练。

/**华丽的代码分割线**/

Retrain the YOLO model for your own dataset.

import numpy as np

import keras.backend as K

from keras.layers import Input, Lambda

from keras.models import Model

from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping

from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss

from yolo3.utils import get_random_data

def _main():

    annotation_path = '2007_train.txt'

    log_dir = 'logs/000/'

    classes_path = 'model_data/voc_classes.txt'

    anchors_path = 'model_data/yolo_anchors.txt'

    class_names = get_classes(classes_path)

    anchors = get_anchors(anchors_path)

    input_shape = (416,416) # multiple of 32, hw

    model = create_model(input_shape, anchors, len(class_names) )

    train(model, annotation_path, input_shape, anchors, len(class_names), log_dir=log_dir)

def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):

    model.compile(optimizer='adam', loss={

        'yolo_loss': lambda y_true, y_pred: y_pred})

    logging = TensorBoard(log_dir=log_dir)

    checkpoint = ModelCheckpoint(log_dir + "ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5",

        monitor='val_loss', save_weights_only=True, save_best_only=True, period=1)

    batch_size = 10

    val_split = 0.1

    with open(annotation_path) as f:

        lines = f.readlines()

    np.random.shuffle(lines)

    num_val = int(len(lines)*val_split)

    num_train = len(lines) - num_val

    print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))

    model.fit_generator(data_generator_wrap(lines[:num_train], batch_size, input_shape, anchors, num_classes),

            steps_per_epoch=max(1, num_train//batch_size),

            validation_data=data_generator_wrap(lines[num_train:], batch_size, input_shape, anchors, num_classes),

            validation_steps=max(1, num_val//batch_size),

            epochs=500,

            initial_epoch=0)

    model.save_weights(log_dir + 'trained_weights.h5')

def get_classes(classes_path):

    with open(classes_path) as f:

        class_names = f.readlines()

    class_names = [c.strip() for c in class_names]

    return class_names

def get_anchors(anchors_path):

    with open(anchors_path) as f:

        anchors = f.readline()

    anchors = [float(x) for x in anchors.split(',')]

    return np.array(anchors).reshape(-1, 2)

def create_model(input_shape, anchors, num_classes, load_pretrained=False, freeze_body=False,

            weights_path='model_data/yolo_weights.h5'):

    K.clear_session() # get a new session

    image_input = Input(shape=(None, None, 3))

    h, w = input_shape

    num_anchors = len(anchors)

    y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \

        num_anchors//3, num_classes+5)) for l in range(3)]

    model_body = yolo_body(image_input, num_anchors//3, num_classes)

    print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))

    if load_pretrained:

        model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)

        print('Load weights {}.'.format(weights_path))

        if freeze_body:

            # Do not freeze 3 output layers.

            num = len(model_body.layers)-7

            for i in range(num): model_body.layers[i].trainable = False

            print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))

    model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',

        arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(

        [*model_body.output, *y_true])

    model = Model([model_body.input, *y_true], model_loss)

    return model

def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):

    n = len(annotation_lines)

    np.random.shuffle(annotation_lines)

    i = 0

    while True:

        image_data = []

        box_data = []

        for b in range(batch_size):

            i %= n

            image, box = get_random_data(annotation_lines[i], input_shape, random=True)

            image_data.append(image)

            box_data.append(box)

            i += 1

        image_data = np.array(image_data)

        box_data = np.array(box_data)

        y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)

        yield [image_data, *y_true], np.zeros(batch_size)

def data_generator_wrap(annotation_lines, batch_size, input_shape, anchors, num_classes):

    n = len(annotation_lines)

    if n==0 or batch_size<=0: return None

    return data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)

if __name__ == '__main__':

    _main()

/**华丽的代码分割线**/

记得在keras-yolo3-master中新建文件logs\000，这个文件是用来存放自己的数据集训练得到的模型。

修改yolo.py文件

/**华丽的代码分割线**/

    _defaults = {

        "model_path": 'logs/000/trained_weights.h5', #此处修改成自己的路径

        "anchors_path": 'model_data/yolo_anchors.txt', #此处修改成自己的路径

        "classes_path": 'model_data/voc_classes.txt', #此处修改成自己的路径

        "score" : 0.3,

        "iou" : 0.45,

        "model_image_size" : (416, 416),

        "gpu_num" : 1,

    }

/**华丽的代码分割线**/

运行预测图像程序

/**华丽的代码分割线**/

python yolo_video.py --image

/**华丽的代码分割线**/