【目标检测】keras-yolo3-tiny训练自己的数据集（目标：人&车辆）

相关内容：【目标检测】基于YOLOv3的海上船舶目标检测分类（Tensorflow/keras）

---

一、环境配置

1.1 配置GPU环境。

使用GPU环境加快训练速度。

【TensorFlow】Window10搭建GPU环境（CUDA、cuDNN）

1.2 虚拟环境与依赖

使用Anaconda创建虚拟环境，并安装相关依赖。

Anaconda Prompt 常用命令

计算机环境：Win10 + Python3.5 + cuda10.2

主要依赖：

tensorflow-gpu 1.10.0
keras-gpu 2.2.2
opencv
pillow
numpy
matplotlib

二、数据集制作

2.1 数据集制作

由于收集数据集并标准过于麻烦，所以采用现有数据集进行训练。

使用Visual Object Classes Challenge 2012 (VOC2012)中的部分类别作为项目的数据集。

共包含20类目标，总计17125张图片。

该项目包含以下三个类别：person、car、bus。

关于数据集的制作、提取：【python】数据集修改：移除和修改xml类别

2.2 生成ImageSets

制作好的数据集放在如下目录内：

jpg文件在JPEGImages中；
xml文件在Annotations中；
ImageSets文件夹内新建Main备用。

使用代码make_main_txt.py在ImgeSets/Main目录下生成train.txt, trainval.txt, val.txt, test.txt。

该代码存放的目录如下图，make_main_txt.py与ImageSets同级。

# -*- coding:utf-8 -*-
import os
import random

trainval_percent = 0.2    # test和val所占的比例，（1-trainval_percent）是训练集的比例
train_percent = 0.8       # 其中在train时使用的test所占的比例

xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)     # 图片数量
list = range(num)
tv = int(num * trainval_percent)  # trainval的数量
tr = int(tv * train_percent)      # trainval中train的数量
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()

三、代码

3.1 下载源码

源码：https://github.com/qqwweee/keras-yolo3

3.2 修改yolov3-tiny.cfg

修改以下四部分：

filters = 3*(类别数+5)
classes = 类别数

当类别数量为2时，filters=21，classes=2

yolov3-tiny.cfg 注释参考：https://blog.csdn.net/weixin_44152895/article/details/106570976

3.3 转换权重文件

在YOLOv3下载yolov3-tiny.weights。

使用命令python convert.py yolov3-tiny.cfg yolov3-tiny.weights model_data/tiny_yolo_weights.h5将.weigth文件转换为.h5文件。

3.4 修改voc_annotation

# -*- coding:utf-8 -*-
import xml.etree.ElementTree as ET
from os import getcwd

sets = ['train', 'val', 'test']
classes = ["person", "vehicle"]


def convert_annotation(image_id, list_file):
    print(image_id)
    in_file = open('dataset/Annotations/%s.xml' % image_id,encoding='utf-8')
    tree = ET.parse(in_file)
    root = tree.getroot()

    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls not in classes:
            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 image_set in sets:
    image_ids = open('dataset/ImageSets/Main/%s.txt' % image_set).read().strip().split()
    print(image_ids)
    list_file = open('dataset/%s.txt' % image_set, 'w')

    for image_id in image_ids:
        list_file.write('dataset/JPEGImages/%s.jpg' % image_id)
        convert_annotation(image_id, list_file)
        list_file.write('\n')
    list_file.close()

运行代码将生产以下三个文件：

3.5 修改yolo.py

修改yolo.py的默认项设置。

class YOLO(object):
    _defaults = {
        "model_path": 'model_data/tiny_yolo_weights.h5',
        "anchors_path": 'model_data/tiny_yolo_anchors.txt',
        "classes_path": 'model_data/my_classes.txt',
        "score" : 0.3,
        "iou" : 0.45,
        "model_image_size" : (416, 416),
        "gpu_num" : 1,
    }

3.6 修改train.py

17-20行的路径设置：

52行的if True改成if False，因为这部分的训练效果不好，使用下一部分的训练。也就是从70行开始。

修改batch_size、epochs。

显存较小就讲bathsize设置的小一点。

最后，运行main.py。

四、测试

4.1 测试集检测

创建main_yolo.py，依照yolo.py进行修改。修改目录信息即可运行。可生成result文件夹，里面包含对测试集的检测结果。

main_yolo.py

# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""

import colorsys
import os
import time
from timeit import default_timer as timer

import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw

from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolo3.utils import letterbox_image
import os
from keras.utils import multi_gpu_model


dir_project = os.getcwd()  # 获取当前目录

# 创建创建一个存储检测结果的dir
result_path = './result'
if not os.path.exists(result_path):
    os.makedirs(result_path)

# result如果之前存放的有文件，全部清除
for i in os.listdir(result_path):
    path_file = os.path.join(result_path, i)
    if os.path.isfile(path_file):
        os.remove(path_file)

# 创建一个记录检测结果的文件
txt_path = result_path + '/result.txt'
file = open(txt_path, 'w')


class YOLO(object):
    _defaults = {
        "model_path": 'logs/000/trained_weights_final.h5',
        "anchors_path": 'model_data/tiny_yolo_anchors.txt',
        "classes_path": 'model_data/my_classes.txt',
        "score" : 0.3,
        "iou" : 0.45,
        "model_image_size" : (416, 416),
        "gpu_num" : 1,
    }

    @classmethod
    def get_defaults(cls, n):
        if n in cls._defaults:
            return cls._defaults[n]
        else:
            return "Unrecognized attribute name '" + n + "'"

    def __init__(self, **kwargs):
        self.__dict__.update(self._defaults) # set up default values
        self.__dict__.update(kwargs) # and update with user overrides
        self.class_names = self._get_class()
        self.anchors = self._get_anchors()
        self.sess = K.get_session()
        self.boxes, self.scores, self.classes = self.generate()

    def _get_class(self):
        classes_path = os.path.expanduser(self.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(self):
        anchors_path = os.path.expanduser(self.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 generate(self):
        model_path = os.path.expanduser(self.model_path)
        assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'

        # Load model, or construct model and load weights.
        num_anchors = len(self.anchors)
        num_classes = len(self.class_names)
        is_tiny_version = num_anchors==6 # default setting
        try:
            self.yolo_model = load_model(model_path, compile=False)
        except:
            self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
                if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
            self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
        else:
            assert self.yolo_model.layers[-1].output_shape[-1] == \
                num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
                'Mismatch between model and given anchor and class sizes'

        print('{} model, anchors, and classes loaded.'.format(model_path))

        # Generate colors for drawing bounding boxes.
        hsv_tuples = [(x / len(self.class_names), 1., 1.)
                      for x in range(len(self.class_names))]
        self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
        self.colors = list(
            map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
                self.colors))
        np.random.seed(10101)  # Fixed seed for consistent colors across runs.
        np.random.shuffle(self.colors)  # Shuffle colors to decorrelate adjacent classes.
        np.random.seed(None)  # Reset seed to default.

        # Generate output tensor targets for filtered bounding boxes.
        self.input_image_shape = K.placeholder(shape=(2, ))
        if self.gpu_num>=2:
            self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num)
        boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
                len(self.class_names), self.input_image_shape,
                score_threshold=self.score, iou_threshold=self.iou)
        return boxes, scores, classes

    def detect_image(self, image):
        start = timer()

        if self.model_image_size != (None, None):
            assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
            assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
            boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
        else:
            new_image_size = (image.width - (image.width % 32),
                              image.height - (image.height % 32))
            boxed_image = letterbox_image(image, new_image_size)
        image_data = np.array(boxed_image, dtype='float32')

        print(image_data.shape)
        image_data /= 255.
        image_data = np.expand_dims(image_data, 0)  # Add batch dimension.

        out_boxes, out_scores, out_classes = self.sess.run(
            [self.boxes, self.scores, self.classes],
            feed_dict={
                self.yolo_model.input: image_data,
                self.input_image_shape: [image.size[1], image.size[0]],
                K.learning_phase(): 0
            })

        print('Found {} boxes for {}'.format(len(out_boxes), 'img'))

        font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
                    size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
        thickness = (image.size[0] + image.size[1]) // 300

        # # 保存框检测出的框的个数   (添加)
        # file.write('find  ' + str(len(out_boxes)) + ' target(s) \n')

        for i, c in reversed(list(enumerate(out_classes))):
            predicted_class = self.class_names[c]
            box = out_boxes[i]
            score = out_scores[i]

            label = '{} {:.2f}'.format(predicted_class, score)
            draw = ImageDraw.Draw(image)
            label_size = draw.textsize(label, font)

            top, left, bottom, right = box
            top = max(0, np.floor(top + 0.5).astype('int32'))
            left = max(0, np.floor(left + 0.5).astype('int32'))
            bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
            right = min(image.size[0], np.floor(right + 0.5).astype('int32'))

            # # 写入检测位置（添加）
            # file.write(
            #     predicted_class + '  score: ' + str(score) + ' \nlocation: top: ' + str(top) + '、 bottom: ' + str(
            #         bottom) + '、 left: ' + str(left) + '、 right: ' + str(right) + '\n')

            file.write(predicted_class + ' ' + str(score) + ' ' + str(left) + ' ' + str(top) + ' ' + str(right) + ' ' + str(bottom) + ';')

            print(label, (left, top), (right, bottom))

            if top - label_size[1] >= 0:
                text_origin = np.array([left, top - label_size[1]])
            else:
                text_origin = np.array([left, top + 1])

            # My kingdom for a good redistributable image drawing library.
            for i in range(thickness):
                draw.rectangle(
                    [left + i, top + i, right - i, bottom - i],
                    outline=self.colors[c])
            draw.rectangle(
                [tuple(text_origin), tuple(text_origin + label_size)],
                fill=self.colors[c])
            draw.text(text_origin, label, fill=(0, 0, 0), font=font)
            del draw
        end = timer()
        print(end - start)
        return image

    def close_session(self):
        self.sess.close()



def detect_video(yolo, video_path, output_path=""):
    import cv2
    vid = cv2.VideoCapture(video_path)
    if not vid.isOpened():
        raise IOError("Couldn't open webcam or video")
    video_FourCC    = int(vid.get(cv2.CAP_PROP_FOURCC))        # 获得视频编码MPEG4/H264
    video_fps       = vid.get(cv2.CAP_PROP_FPS)
    video_size      = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
                        int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
    isOutput = True if output_path != "" else False
    if isOutput:
        print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))
        out = cv2.VideoWriter(output_path, video_FourCC, video_fps, video_size)
    accum_time = 0
    curr_fps = 0
    fps = "FPS: ??"
    prev_time = timer()
    while True:
        return_value, frame = vid.read()
        image = Image.fromarray(frame)           # 从array转换成image
        image = yolo.detect_image(image)
        result = np.asarray(image)
        curr_time = timer()
        exec_time = curr_time - prev_time
        prev_time = curr_time
        accum_time = accum_time + exec_time
        curr_fps = curr_fps + 1
        if accum_time > 1:
            accum_time = accum_time - 1
            fps = "FPS: " + str(curr_fps)
            curr_fps = 0
        cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
                    fontScale=0.50, color=(255, 0, 0), thickness=2)
        cv2.namedWindow("result", cv2.WINDOW_NORMAL)
        cv2.imshow("result", result)
        if isOutput:
            out.write(result)
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
    yolo.close_session()


# 批量处理文件
if __name__ == '__main__':
    if True:
        # 读取test文件
        with open("dataset/ImageSets/Main/test.txt", 'r') as f:  # 打开文件
            test_list = f.readlines()  # 读取文件
            test_list = [x.strip() for x in test_list if x.strip() != '']  # 去除/n
            # print(test_list)

        t1 = time.time()
        yolo = YOLO()

        for filename in test_list:
            image_path = 'dataset/JPEGImages/'+filename+'.jpg'
            portion = os.path.split(image_path)
            # file.write(portion[1]+' detect_result：\n')
            file.write(image_path + ' ')
            image = Image.open(image_path)
            image_mAP_save_path = dir_project + '/mAP/input/images-optional/'
            image.save(image_mAP_save_path + filename + '.jpg')
            r_image = yolo.detect_image(image)
            file.write('\n')
            #r_image.show() 显示检测结果
            image_save_path = './result/result_'+portion[1]
            print('detect result save to....:'+image_save_path)
            r_image.save(image_save_path)

        time_sum = time.time() - t1
        # file.write('time sum: '+str(time_sum)+'s')
        print('time sum:',time_sum)
        file.close()
        yolo.close_session()

    if False:
        img_path = 'dataset/JPEGImages_resize'
        result_path = 'dataset/image_result'
        for file in os.listdir(img_path):
            file_path = os.path.join(img_path, file)
            image = Image.open(file_path)
            r_image = yolo.detect_image(image)

            image_save_path = os.path.join(result_path, file)
            print('detect result save to: ' + image_save_path)
            r_image.save(image_save_path)

4.2 计算mAP

mAP计算：【目标检测】kera-yolo3模型计算mAP
mAP源码：https://github.com/Cartucho/mAP

修改mAP源码，针对keras-yolov3的检测结果计算mAP。