源码GITHUB地址：
https://github.com/qqwweee/keras-yolo3
官方权值下载地址：
https://pjreddie.com/media/files/yolov3.weights
参考原文地址：
https://blog.csdn.net/u012746060/article/details/81183006

使用

在源码解压文件README.md中，有详细的使用说明。

快速应用

1. 根据上面地址下载权值，并保存到根目录keras-yolo3-master下。
2. 将Darknet YOLO模型转化为 Keras 模型，在终端执行以下语句实现转换（必须将终端切换到keras-yolo3-master路径下）：
     python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5
3. 运行yolo_video.py预测图片,命令设置即可：
     python yolo_video.py --image（图片预测）
   或者python yolo_video.py [video_path] [output_path (optional)]（视频预测）

Use --help to see usage of yolo_video.py
usage: yolo_video.py [-h] [--model MODEL] [--anchors ANCHORS]
                     [--classes CLASSES] [--gpu_num GPU_NUM] [--image]
                     [--input] [--output]

positional arguments:
  --input        Video input path
  --output       Video output path

optional arguments:
  -h, --help         show this help message and exit
  --model MODEL      path to model weight file, default model_data/yolo.h5
  --anchors ANCHORS  path to anchor definitions, default
                     model_data/yolo_anchors.txt
  --classes CLASSES  path to class definitions, default
                     model_data/coco_classes.txt
  --gpu_num GPU_NUM  Number of GPU to use, default 1
  --image            Image detection mode, will ignore all positional arguments

训练自己的数据

以VOC 数据集为例。其实可以根据自己的需要来建，不需要固定的套路。

1.制作数据集

1）建立标准VOC数据集文件夹结构，VOCdevkit/VOC2007下包含5个文件夹Annotations、ImageSets、JPEGImages、SegmentationClass、SegmentationObject。文件VOC数据集文件结构及内容如下，其中JPEGImages、Annotations放的分别是训练图片和对应图片标签（用labelImg软件制作 https://tzutalin.github.io/labelImg/）。

2.生成训练集、验证集等依赖的text文件

在VOC2007文件夹下新建test.py文件，内容如下,然后运行test.py，自动在VOCdevkit\VOC2007\ImageSets\Main下生成4个text文件，文件内容是训练数据按test.pyz中trainval_percent = 0.2，train_percent = 0.8分好集的文件名如下：

test.py

import os
import random

trainval_percent = 0.2 # 开发集所占比例
train_percent = 0.8 # 训练集所占比例
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()

3.将VOC文件转化成YOLOv3需要的训练格式文件

修改keras-yolo3-master目录下的voc_annotation.py，内容如下：
voc_annotation.py

import xml.etree.ElementTree as ET
from os import getcwd

sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]

# 修改成自己需要的类，与类别对应
# classes = ["cat","person"]

def convert_annotation(year, image_id, list_file):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    tree=ET.parse(in_file)
    root = tree.getroot()

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))

wd = getcwd()

for year, image_set in sets:
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg'%(wd, year, image_id))
        convert_annotation(year, image_id, list_file)
        list_file.write('\n')
    list_file.close()

运行voc_annotation.py，自动在keras-yolo3-master路径下生成yolo所需训练文件，其内容格式跟README.md中叙述的完全一致。

4.修改yolov3.cfg

需要修改三处地方，搜索yolo依次修改，每处修改filters=（3*（num_classes+5））和random=0。

5.修改voc_classes.txt

保持与voc_annotation.pyclasses修改一致。

5.模型保存的路径

keras-yolo3-master下新建logs/000文件夹用于保存模型，如下：

6.修改train.py文件

"""
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()

运行train.py就开始训练了。根据情况修改batch_size = 32和epochs = 100。

理解

每个格子可以预测 B 个 bounding box
class 信息是针对每个网格的，confidence 信息是针对每个 bounding box 的。

每个 bounding box 要预测 (x, y, w, h) 和 confidence 共5个值，每个网格还要预测一个类别信息，记为 C 类。则 SxS个 网格，每个网格要预测 B 个 bounding box 还要预测 C 个 categories。输出就是 S x S x (5*B+C) 的一个 tensor。

取 S=7，B=2，一共有20 个类别（C=20），则输出就是 7x7x30 的一个 tensor。

每个 grid 有 30 维，这 30 维中，8 维是回归 box 的坐标，2 维是 box的 confidence，还有 20 维是类别。