darkent Yolo训练自己的数据集（学习记录）

1.下载darknet源码

git clone https://github.com/pjreddie/darknet
cd darknet

2.修改配置文件Makefile

GPU=1 #如果使用GPU设置为1，CPU设置为0
CUDNN=1  #如果使用CUDNN设置为1，否则为0
OPENCV=0 #如果调用摄像头，还需要设置OPENCV为1，否则为0
OPENMP=0  #如果使用OPENMP设置为1，否则为0
DEBUG=0  #如果使用DEBUG设置为1，否则为0

4.下载yolov3预训练模型

wget https://pjreddie.com/media/files/yolov3.weights

5.测试

./darknet detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights data/dog.jpg

在darknet目录下创建**mask**文件夹，目录结构如下，将之前标注好的图片和xml文件放到对应目录下

会在./mask目录下生成一个labels文件夹一个txt文件(mask_train.txt)(内容是: 类别的编码和目标的相对位置)。

..JPEGImages#存放图像
 
...Annotations#存放图像对应的xml文件
 
...ImageSets/Main 

在darknet目录下创建my_label.py 用来将voc2007格式数据转换成yolo训练的格式

# coding=UTF-8
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

# 源代码sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets = [('mask', 'train'),('mask', 'test')]  # 改成自己建立的myData

classes = ["have_mask", "no_mask"]  # 改成自己的类别

wd ='/home/wei/darknet'


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def convert_annotation(year, image_id):
    in_file = open('/home/wei/darknet/mask/Annotations/%s.xml' % (image_id))  # 源代码VOCdevkit/VOC%s/Annotations/%s.xml
    out_file = open('/home/wei/darknet/mask/labels/%s.txt' % (image_id), 'w')  # 源代码VOCdevkit/VOC%s/labels/%s.txt
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    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 = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')




for year, image_set in sets:
    if not os.path.exists('/home/wei/darknet/mask/labels/'):  # 改成自己建立的myData
        os.makedirs('/home/wei/darknet/mask/labels/')
    image_ids = open('/home/wei/darknet/mask/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('/home/wei/darknet/mask/%s_%s.txt' % (year, image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/mask/JPEGImages/%s.jpg\n' % (wd, image_id))
        convert_annotation(year, image_id)
    list_file.close()

4.修改darknet/cfg下的voc.data和yolov3-voc.cfg文件

为了保险起见，复制这两个文件，并分别重命名为mask.data和mask_yolov3.cfg

maks.data内容：

classes= 2
train  = /home/wei/darknet/mask/mask_train.txt
valid  = /home/wei/darknet/mask/mask_test.txt
names = /home/wei/darknet/mask/mask.names
backup = backup

mask_yolov3.cfg的内容：

/yolo, 总共会搜出3个含有yolo的地方。
每个地方都必须要改2处， filters：3*（5+len（classes））；
其中：classes: len(classes) = 3，这里以我的工程为例
filters = 24
classes = 3
可修改：random = 1：原来是1，显存小改为0。（是否要多尺度输出。）

6.在mask文件夹下新建mask.names文件

have_mask
no_mask

7.下载预训练权重

wget https://pjreddie.com/media/files/darknet53.conv.74

8.开始训练

./darknet detector train cfg/my_data.data cfg/my_yolov3.cfg darknet53.conv.74
或者指定gpu训练，默认使用gpu0

计算测试后的mAP
在darknet在创建voc_eval.py

# --------------------------------------------------------
# Fast/er R-CNN
# Licensed under The MIT License [see LICENSE for details]
# Written by Bharath Hariharan
# --------------------------------------------------------

import xml.etree.ElementTree as ET
import os
import cPickle
import numpy as np

def parse_rec(filename):
    """ Parse a PASCAL VOC xml file """
    tree = ET.parse(filename)
    objects = []
    for obj in tree.findall('object'):
        obj_struct = {}
        obj_struct['name'] = obj.find('name').text
        obj_struct['pose'] = obj.find('pose').text
        obj_struct['truncated'] = int(obj.find('truncated').text)
        obj_struct['difficult'] = int(obj.find('difficult').text)
        bbox = obj.find('bndbox')
        obj_struct['bbox'] = [int(bbox.find('xmin').text),
                              int(bbox.find('ymin').text),
                              int(bbox.find('xmax').text),
                              int(bbox.find('ymax').text)]
        objects.append(obj_struct)

    return objects

def voc_ap(rec, prec, use_07_metric=False):
    """ ap = voc_ap(rec, prec, [use_07_metric])
    Compute VOC AP given precision and recall.
    If use_07_metric is true, uses the
    VOC 07 11 point method (default:False).
    """
    if use_07_metric:
        # 11 point metric
        ap = 0.
        for t in np.arange(0., 1.1, 0.1):
            if np.sum(rec >= t) == 0:
                p = 0
            else:
                p = np.max(prec[rec >= t])
            ap = ap + p / 11.
    else:
        # correct AP calculation
        # first append sentinel values at the end
        mrec = np.concatenate(([0.], rec, [1.]))
        mpre = np.concatenate(([0.], prec, [0.]))

        # compute the precision envelope
        for i in range(mpre.size - 1, 0, -1):
            mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])

        # to calculate area under PR curve, look for points
        # where X axis (recall) changes value
        i = np.where(mrec[1:] != mrec[:-1])[0]

        # and sum (\Delta recall) * prec
        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
    return ap

def voc_eval(detpath,
             annopath,
             imagesetfile,
             classname,
             cachedir,
             ovthresh=0.5,
             use_07_metric=False):
    """rec, prec, ap = voc_eval(detpath,
                                annopath,
                                imagesetfile,
                                classname,
                                [ovthresh],
                                [use_07_metric])
    Top level function that does the PASCAL VOC evaluation.
    detpath: Path to detections
        detpath.format(classname) should produce the detection results file.
    annopath: Path to annotations
        annopath.format(imagename) should be the xml annotations file.
    imagesetfile: Text file containing the list of images, one image per line.
    classname: Category name (duh)
    cachedir: Directory for caching the annotations
    [ovthresh]: Overlap threshold (default = 0.5)
    [use_07_metric]: Whether to use VOC07's 11 point AP computation
        (default False)
    """
    # assumes detections are in detpath.format(classname)
    # assumes annotations are in annopath.format(imagename)
    # assumes imagesetfile is a text file with each line an image name
    # cachedir caches the annotations in a pickle file

    # first load gt
    if not os.path.isdir(cachedir):
        os.mkdir(cachedir)
    cachefile = os.path.join(cachedir, 'annots.pkl')
    # read list of images
    with open(imagesetfile, 'r') as f:
        lines = f.readlines()
    imagenames = [x.strip() for x in lines]

    if not os.path.isfile(cachefile):
        # load annots
        recs = {}
        for i, imagename in enumerate(imagenames):
            recs[imagename] = parse_rec(annopath.format(imagename))
            if i % 100 == 0:
                print 'Reading annotation for {:d}/{:d}'.format(
                    i + 1, len(imagenames))
        # save
        print 'Saving cached annotations to {:s}'.format(cachefile)
        with open(cachefile, 'w') as f:
            cPickle.dump(recs, f)
    else:
        # load
        with open(cachefile, 'r') as f:
            recs = cPickle.load(f)

    # extract gt objects for this class
    class_recs = {}
    npos = 0
    for imagename in imagenames:
        R = [obj for obj in recs[imagename] if obj['name'] == classname]
        bbox = np.array([x['bbox'] for x in R])
        difficult = np.array([x['difficult'] for x in R]).astype(np.bool)
        det = [False] * len(R)
        npos = npos + sum(~difficult)
        class_recs[imagename] = {'bbox': bbox,
                                 'difficult': difficult,
                                 'det': det}

    # read dets
    detfile = detpath.format(classname)
    with open(detfile, 'r') as f:
        lines = f.readlines()

    splitlines = [x.strip().split(' ') for x in lines]
    image_ids = [x[0] for x in splitlines]
    confidence = np.array([float(x[1]) for x in splitlines])
    BB = np.array([[float(z) for z in x[2:]] for x in splitlines])

    # sort by confidence
    sorted_ind = np.argsort(-confidence)
    sorted_scores = np.sort(-confidence)
    BB = BB[sorted_ind, :]
    image_ids = [image_ids[x] for x in sorted_ind]

    # go down dets and mark TPs and FPs
    nd = len(image_ids)
    tp = np.zeros(nd)
    fp = np.zeros(nd)
    for d in range(nd):
        R = class_recs[image_ids[d]]
        bb = BB[d, :].astype(float)
        ovmax = -np.inf
        BBGT = R['bbox'].astype(float)

        if BBGT.size > 0:
            # compute overlaps
            # intersection
            ixmin = np.maximum(BBGT[:, 0], bb[0])
            iymin = np.maximum(BBGT[:, 1], bb[1])
            ixmax = np.minimum(BBGT[:, 2], bb[2])
            iymax = np.minimum(BBGT[:, 3], bb[3])
            iw = np.maximum(ixmax - ixmin + 1., 0.)
            ih = np.maximum(iymax - iymin + 1., 0.)
            inters = iw * ih

            # union
            uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +
                   (BBGT[:, 2] - BBGT[:, 0] + 1.) *
                   (BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)

            overlaps = inters / uni
            ovmax = np.max(overlaps)
            jmax = np.argmax(overlaps)

        if ovmax > ovthresh:
            if not R['difficult'][jmax]:
                if not R['det'][jmax]:
                    tp[d] = 1.
                    R['det'][jmax] = 1
                else:
                    fp[d] = 1.
        else:
            fp[d] = 1.

    # compute precision recall
    fp = np.cumsum(fp)
    tp = np.cumsum(tp)
    rec = tp / float(npos)
    # avoid divide by zero in case the first detection matches a difficult
    # ground truth
    prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
    ap = voc_ap(rec, prec, use_07_metric)

    return rec, prec, ap

创建computer_Single_ALL_mAP.py

from voc_eval import voc_eval

import os

current_path = os.getcwd()
results_path = current_path+"/results"
sub_files = os.listdir(results_path)

mAP = []
for i in range(len(sub_files)):
    class_name = sub_files[i].split(".txt")[0]
    rec, prec, ap = voc_eval('/home/wei/darknet/results/{}.txt',
               '/home/wei/darknet/mask/Annotations/{}.xml',
               '/home/wei/darknet/mask/ImageSets/Main/test.txt',
                class_name, '.')
    print("mAP for {} :\t {} ".format(class_name, ap))
    mAP.append(ap)

mAP = tuple(mAP)

print("--------------")
print("mAP for all:\t {}".format( float( sum(mAP)/len(mAP)) ))
print("--------------")

绘制loss曲线

 ./darknet detector train mask/mask.data mask/mask.cfg darknet53.conv.74 2>1 | tee visualization/train_yolov3.log 

在使用脚本绘制变化曲线之前，需要先使用extract_log.py脚本，格式化log,用生成的新的log文件供可视化工具绘图，格式化log的extract_log.py脚本如下（和生成的log文件同一目录）：

# coding=utf-8
# 该文件用来提取训练log，去除不可解析的log后使log文件格式化，生成新的log文件供可视化工具绘图
 
import inspect
import os
import random
import sys
def extract_log(log_file,new_log_file,key_word):
    with open(log_file, 'r') as f:
      with open(new_log_file, 'w') as train_log:
  #f = open(log_file)
    #train_log = open(new_log_file, 'w')
        for line in f:
    # 去除多gpu的同步log
          if 'Syncing' in line:
            continue
    # 去除除零错误的log
          if 'nan' in line:
            continue
          if key_word in line:
            train_log.write(line)
    f.close()
    train_log.close()
 
extract_log('train_yolov3.log','train_log_loss.txt','images')
extract_log('train_yolov3.log','train_log_iou.txt','IOU')

运行之后，会解析log文件的loss行和iou行得到两个txt文件

使用train_loss_visualization.py脚本可以绘制loss变化曲线
train_loss_visualization.py脚本如下（也是同一目录新建py文件）：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
#%matplotlib inline
 
lines =5124    #改为自己生成的train_log_loss.txt中的行数
result = pd.read_csv('train_log_loss.txt', skiprows=[x for x in range(lines) if ((x%10!=9) |(x<1000))] ,error_bad_lines=False, names=['loss', 'avg', 'rate', 'seconds', 'images'])
result.head()
 
result['loss']=result['loss'].str.split(' ').str.get(1)
result['avg']=result['avg'].str.split(' ').str.get(1)
result['rate']=result['rate'].str.split(' ').str.get(1)
result['seconds']=result['seconds'].str.split(' ').str.get(1)
result['images']=result['images'].str.split(' ').str.get(1)
result.head()
result.tail()
 
# print(result.head())
# print(result.tail())
# print(result.dtypes)
 
print(result['loss'])
print(result['avg'])
print(result['rate'])
print(result['seconds'])
print(result['images'])
 
result['loss']=pd.to_numeric(result['loss'])
result['avg']=pd.to_numeric(result['avg'])
result['rate']=pd.to_numeric(result['rate'])
result['seconds']=pd.to_numeric(result['seconds'])
result['images']=pd.to_numeric(result['images'])
result.dtypes
 
 
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.plot(result['avg'].values,label='avg_loss')
# ax.plot(result['loss'].values,label='loss')
ax.legend(loc='best')  #图列自适应位置
ax.set_title('The loss curves')
ax.set_xlabel('batches')
fig.savefig('avg_loss')
# fig.savefig('loss')