Yolov3 Keras版本训练详细教程

默认读者已经能利用官方给出的权重并且可以运行keras版本的Yolov3

一、新建文件夹VOCdevkit

严格按照上图建立VOCdevkit下的全部文件夹。

目录结构为VOCdevkit/VOC2007/,在下面就是新建几个默认名字的文件夹

Annotations

ImageSets（该目录还有三个文件需要建立）

JPEGImages(把你所有的图片都复制到该目录里面）

SegmentationClass

SegmentationObject

二、将图片放入JPEGImages文件里

三、使用labelImg标注图片 （标注完成时保存在Annotations文件夹下）

1、LabelImg下载：https://github.com/tzutalin/labelImg。

2、安装好python3.6，pyqt5, lxml必备包

3、CMD命令行模式进入LabelImg的文件目录，然后执行如下两个命令，完成LabelImg的启动

4、在左侧选择Yolo格式

5、快捷键

Ctrl + u  加载目录中的所有图像，鼠标点击Open dir同功能
Ctrl + r  更改默认注释目标目录(xml文件保存的地址) 
Ctrl + s  保存
Ctrl + d  复制当前标签和矩形框
space     将当前图像标记为已验证
w         创建一个矩形框
d         下一张图片
a         上一张图片
del       删除选定的矩形框
Ctrl++    放大
Ctrl--    缩小
↑→↓←        键盘箭头移动选定的矩形框

使用：https://www.cnblogs.com/Terrypython/p/9577657.html

四、制作VOC2007数据集

在VOC2007下新建一个python文件，复制如下代码（并运行）

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()

 

五、生成train.txt,val.txt,test.txt

运行自带的voc_annotation.py ，classes以检测一个类为例（方向盘），在voc_annotation.py需改你的数据集为：

 

六、修改参数文件yolo3.cfg 

参数含义：https://blog.csdn.net/ll_master/article/details/81487844

打开yolo3.cfg文件。搜索yolo(共出现三次)，每次按下图都要修改

 具体的参数按照如下的公式进行计算： 

filter：3*（5+len（classes）

classes:你要训练的类别数

random：原来是1，显存小改为0

 

七、修改model_data下的voc_classes.txt为自己训练的类别

 八、修改train.py代码（用下面代码直接替换原来的代码）

"""
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()

替换完成后，需要创建这样一个目录，这个目录的作用就是存放自己的数据集训练得到的模型。不然程序运行到最后会因为找不到该路径而发生错误。生成的模型trained_weights.h5如下：

注：训练时如果显存还是爆掉的话可以使用CPU来训练，笔者显存4GB，内存20GB，加入如下代码可以启动CPU训练（速度很慢，但是如果显存爆掉话可是使用CPU训练）

import os
GPU = 0 #Change it to 0 in order to use CPU
if GPU == 0:
    os.environ['CUDA_VISIBLE_DEVICES'] = '-1'

 

九、修改yolo.py文件，路径修改为各自对应的路径。 

运行代码即可实现预测。 

 

注：本篇文章来自https://blog.csdn.net/u012746060/article/details/81183006，感谢！