训练yolov7源码

第一步下载源码：

GitCode - 开发者的代码家园

点击下载zip

第二步，在pycharm上配置相关的环境

请看这位博客的操作流程

利用yolov7训练自己的数据集； yolov7的安装与使用 ； yolov7源码解读_yolov7.pt-CSDN博客

第三步：划分数据集

可以运行下面的代码

import os
import random
trainval_percent = 0.9
train_percent = 0.8
xmlfilepath = 'mydatas/Annotations'
txtsavepath = 'mydatas/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('mydatas/ImageSets/trainval.txt', 'w')
ftest = open('mydatas/ImageSets/test.txt', 'w')
ftrain = open('mydatas/ImageSets/train.txt', 'w')
fval = open('mydatas/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:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

效果如下：

 

接下来是准备label

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 =  ['craze','white mark','joint line', 'bump', 'off-centered']
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('/home/gzz/yangshuai/yolov7-main/mydatas/Annotations/%s.xml' % (image_id),encoding='utf-8')
    out_file = open('/home/gzz/yangshuai/yolov7-main/mydatas/labels/%s.txt' % (image_id), 'w',encoding='utf-8')
    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('mydatas/labels/'):
        os.makedirs('mydatas/labels/')
    image_ids = open('mydatas/ImageSets/%s.txt' % (image_set)).read().strip().split()
    list_file = open('mydatas/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('mydatas/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

然后还需要准备一个配置文件

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# COCO 2017 dataset http://cocodataset.org by Microsoft
# Example usage: python train.py --data coco.yaml
# parent
# ├── yolov5
# └── datasets
#     └── coco  ← downloads here (20.1 GB)


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
#path: ../mydatas/  # dataset root dir
train: mydatas/train.txt  # train images (relative to 'path') 118287 images
val: mydatas/val.txt  # val images (relative to 'path') 5000 images
test: mydatas/test.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794

# Classes
nc: 5 # number of classes
names:  ['craze','white mark','joint line', 'bump', 'off-centered']  # class names


# Download script/URL (optional)
download: |
  from utils.general import download, Path


  # Download labels
  segments = False  # segment or box labels
  dir = Path(yaml['path'])  # dataset root dir
  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
  urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')]  # labels
  download(urls, dir=dir.parent)

  # Download data
  urls = ['http://images.cocodataset.org/zips/train2017.zip',  # 19G, 118k images
          'http://images.cocodataset.org/zips/val2017.zip',  # 1G, 5k images
          'http://images.cocodataset.org/zips/test2017.zip']  # 7G, 41k images (optional)
  download(urls, dir=dir / 'images', threads=3)

这部分需要修改成自己的数据集信息。

第四步：找到train文件。在yolov7的同根目录下。

修改上面的参数。第一个weights是模型的权重（相对位置即可），datas是数据集的信息，就是上面创建的配置文件。cfg是你想训练的模型，epochs就是训练的总轮数

然后点击运行就可以拉！