基于keras框架yolov3算法的MAP计算

此处默认可以完成keras模型的训练、map的含义及理论计算。
本项目是基于[https://github.com/Cartucho/mAP]实现的。

此项目需要用到input文件夹（可参考原作者github），其中包含如下三个子文件夹：
detection-results：存放模型预测得到的txt文件
ground-truth：待测试图片的xml文件
images-optional：存放待测试图片

接下来是这三个文件夹的制作：
1、images-optional
这个文件夹直接将待测试的图片拖入即可。

2、ground-truth
第一步先将待测试图片的xml标注文件放入其中
第二部需要将此文件夹中的xml文件转换为txt文件。
需要用到https://github.com/Cartucho/mAP/tree/master/scripts/extra中的convert_gt_xml.py文件。会自动帮你从xml生成txt。
代码如下：

import sys
import os
import glob
import xml.etree.ElementTree as ET

# make sure that the cwd() in the beginning is the location of the python script (so that every path makes sense)
os.chdir(os.path.dirname(os.path.abspath(__file__)))

# change directory to the one with the files to be changed
parent_path = os.path.abspath(os.path.join(os.getcwd(), os.pardir))
parent_path = os.path.abspath(os.path.join(parent_path, os.pardir))
GT_PATH = os.path.join(parent_path, 'input','ground-truth')
#print(GT_PATH)
os.chdir(GT_PATH)

# old files (xml format) will be moved to a "backup" folder
## create the backup dir if it doesn't exist already
if not os.path.exists("backup"):
  os.makedirs("backup")

# create VOC format files
xml_list = glob.glob('*.xml')
if len(xml_list) == 0:
  print("Error: no .xml files found in ground-truth")
  sys.exit()
for tmp_file in xml_list:
  #print(tmp_file)
  # 1. create new file (VOC format)
  with open(tmp_file.replace(".xml", ".txt"), "a") as new_f:
    root = ET.parse(tmp_file).getroot()
    for obj in root.findall('object'):
      obj_name = obj.find('name').text
      bndbox = obj.find('bndbox')
      left = bndbox.find('xmin').text
      top = bndbox.find('ymin').text
      right = bndbox.find('xmax').text
      bottom = bndbox.find('ymax').text
      new_f.write("%s %s %s %s %s\n" % (obj_name, left, top, right, bottom))
  # 2. move old file (xml format) to backup
  os.rename(tmp_file, os.path.join("backup", tmp_file))
print("Conversion completed!")

运行之后提示Conversion completed!则转换成功。这样这个文件夹的内容就完成了。

3、detection-results
这个文件夹也需要生成预测结果的txt格式的文件，在你训练好模型和准备好前两个文件夹之后可以做这一步。
代码如下：（参考了一位大佬的）：

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

import colorsys
import os
import sys
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

class YOLO(object):
    _defaults = {
        "model_path": 'logs/000/trained_weights_final.h5', ##训练好的模型的路径
        "anchors_path": 'model_data/yolo_anchors.txt',
        "classes_path": 'model_data/voc_classes.txt',
        "score" : 0.3,
        "iou" : 0.45,
        "model_image_size" : (416, 416),
        "gpu_num" : 0
    }

    @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

        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'))
            print(label, (left, top), (right, bottom))
            #new_f=open("/home/shan/xws/pro/keras-yolo3/detection-results/"+tmp_file.replace(".jpg", ".txt"), "a")
            new_f.write("%s %s %s %s %s\n" %  (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()

if __name__ == '__main__':
    yolo=YOLO()
    # path = '1.jpg'
    # try:
    #     image = Image.open(path)
    # except:
    #     print('Open Error! Try again!')
    # else:
    #     r_image = yolo.detect_image(image)
    #     r_image.show()
    # yolo.close_session()
    #strat1=timer()
    dirname="input\images-optional/" ##该目录为测试照片的存储路径，每次测试照片的数量可以自己设定
    #dirname = "input/images-optional"
    path=os.path.join(dirname)
    pic_list=os.listdir(path)
    count=0
    for filename in pic_list:
        tmp_file=pic_list[count]
        new_f=open("input\detection-results/"+tmp_file.replace(".jpg", ".txt"), "a")  #预测坐标生成txt文件保存的路径
        #new_f = open("input/detection-results" + tmp_file.replace(".jpg", ".txt"), "a")  # 预测坐标生成txt文件保存的路径
        abs_path=path+pic_list[count]
        image = Image.open(abs_path)
        r_image = yolo.detect_image(image)
        count=count+1
    # yolo = YOLO()
    #end1=timer()
    print(count)
    yolo.close_session()

以上都准备就绪之后就只欠东风了，运行https://github.com/Cartucho/mAP中main.py函数即可完成计算并返回一个results文件夹（包含各种预测结果的指标）。