yolov3 训练自己数据的配置

1.下载代码

github

2.处理图片

a.图片文件夹设置

--custom                  # 自定义图片
    --Annotation       # xml文件
    --images            # 图片
    --imageSets       # 运行makeTxt
        --test.txt
        --train.txt
        --trainval.txt
        --val.txt
    --JPEGImages     #复制images
    --labels           

makeTxt.py

import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = 'data/custom/Annotations'
txtsavepath = 'data/custom/ImageSets'
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('data/custom/ImageSets/trainval.txt', 'w')
ftest = open('data/custom/ImageSets/test.txt', 'w')
ftrain = open('data/custom/ImageSets/train.txt', 'w')
fval = open('data/custom/ImageSets/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()

voc_label.py
注意修改sets，classes
运行后labels生成，并生成训练测试路径文件

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test','val']
classes = ["RBC"]
def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    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(image_id):
    in_file = open('data/custom/Annotations/%s.xml' % (image_id))
    out_file = open('data/custom/labels/%s.txt' % (image_id), 'w')
    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')
wd = getcwd()
print(wd)
for image_set in sets:
    if not os.path.exists('data/custom/labels/'):
        os.makedirs('data/custom/labels/')
    image_ids = open('data/custom/ImageSets/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/custom/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('data/custom/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

b.配置文件

三处需要修改
i.custom.data 空一格

classes= 1
train=data/custom/train.txt
valid=data/custom/val.txt
names=data/custom/classes.names

ii.classes.names

RBC

iii.yolov3-tiny.cfg 每一处yolo都要修改

3.weights

4.train.py

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--epochs", type=int, default=10, help="number of epochs")
    parser.add_argument("--batch_size", type=int, default=3, help="size of each image batch")
    parser.add_argument("--gradient_accumulations", type=int, default=2, help="number of gradient accums before step")
    parser.add_argument("--model_def", type=str, default="config/yolov3-tiny.cfg", help="path to model definition file")
    parser.add_argument("--data_config", type=str, default="config/custom.data", help="path to data config file")
    parser.add_argument("--pretrained_weights", type=str, help="if specified starts from checkpoint model")
    parser.add_argument("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
    parser.add_argument("--img_size", type=int, default=416, help="size of each image dimension")
    parser.add_argument("--checkpoint_interval", type=int, default=1, help="interval between saving model weights")
    parser.add_argument("--evaluation_interval", type=int, default=1, help="interval evaluations on validation set")
    parser.add_argument("--compute_map", default=False, help="if True computes mAP every tenth batch")
    parser.add_argument("--multiscale_training", default=True, help="allow for multi-scale training")
    opt = parser.parse_args()