keras-tensorflow-yolo-v3 win10目标检测训练自己的数据集（一）

Chapter 0:准备工作

配置：

• Windows 10
• Pycharm
• tensorflow-gpu 1.9.0
• keras 2.2.4
• cudnn 7.6.0
• cudatoolkit 9.0

文件下载地址：
keras-yolo3-master
VOC2007
yolov3.weights
labelImg

---

Chapter 1:数据集制作

下载VOC2007数据集将VOCdevkit文件夹放至keras-yolo-master文件夹下,并将里面的图片、文件全部删掉，只保留文件夹，如下：
——VOCdevkit
————VOC2007
——————Annotations
——————ImageSets
————————Layout
————————Main
————————Segmentation
——————JPEGImages
——————SegmentationsClass
——————SegmentationObject

1.1:导入自己的数据集

把自己的数据集，放至JPEGImage文件夹下

1.2:图像标注

用labelImg对数据集进行标注（关于labelImg的安装使用详见：图像标注软件——labelImg使用教程）

标注完成的.xml文件保存至Annotations文件夹

1.3：生成训练-验证-测试文件

在VOC2007文件夹下新建 test.py

test.py完整代码：

import os
import random

trainval_percent = 0.1
train_percent = 0.9
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()

运行test.py文件，ImageSets/Main目录下生成如下四个文件

Chapter 2:修改类别

1.打开keras-yolo3-master目录下voc_annotation.py文件
2.修改你数据集的类别名称

3.运行该文件之后会在主目录keras-yolo3-master下生成3个.txt文件，手动将文件名修改为train.txt \ val.txt \ test.txt

Chapter 3:参数设定

3.1 修改yolo3.cfg

修改yolo3.cfg文件参数
1.Pycharm打开yolo3.cfg
2.快捷键Ctrl + F 查找yolo（一共3个yolo），每一处的filter 、classes、random都需做相应更改
filter = 3*(len(classes)+5) #我这里只有一类，所以是18
classes = 1 #有几类写几类
random = 0 #显存小设为0，否则为1

3.2:修改classes.txt

打开model_data/coco_classes.txt 和 voc_classes.txt 文件，修改classes

Chapter 4:训练

在主目录下新建文件夹 logs/000

修改 train.py

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 = '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()

运行train.py 观察loss损失值，降到十几左右就可以停止训练了,logs/000目录下生成trained-weights.h5


问题

• ResourcesExhaustion报错:减小Batch (我是4GB运存，Batch=4，仅供参考)
• tensorflow版本与cudnn版本不兼容报错，建议使用我前面给出的相关版本

Chapter 5:重新设置参数文件路径

打开 yolo.py 文件夹，修改
1.权重文件路径
2.分类路径

Chapter 6：测试

6.1 检测图片

法一：在Pycharm的Terminal里输入：python yolo_video.py --image
法二：cmd->cd 至文件夹keras-yolo3-master所在路径 输入：python yolo_video.py --image

6.2 视频检测

法一：在Pycharm的Terminal里输入：python yolo_video.py --input=run.mp4
法二：cmd->cd 至文件夹keras-yolo3-master所在路径 输入：python yolo_video.py --input=run.mp4