yolov8训练时gpu占用很少

转载

mob64ca1407216b 2024-11-03 22:27:18

文章标签 yolov8训练时gpu占用很少 YOLO pycharm python linux 文章分类 游戏开发

环境配置

见（linux）yolov5/v3-pytorch目标检测1：环境配置gpu+anaconda+pycham+ RTX2080ti 笔记。环境配置完成后yolov3和yolov5都可以使用，数据集和yaml文件通用，训练步骤相同。

原始图像文件和xml

已经有jpg图像文件(JPEGImages)和对应的xml标注文件(Annotations)和数据集文件分布

转换为yolo格式代码如下

3.1新建ImageSets/Main文件夹，划分数据集，split_train_val.py代码如下

import os
import random
import argparse

parser = argparse.ArgumentParser()
# ***为该数据集的绝对路径
parser.add_argument('--xml_path', default='***/Annotations', type=str, help='input xml label path')
parser.add_argument('--txt_path', default='***/ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()

trainval_percent = 0.9  # 训练集和验证集所占比例。
train_percent = 0.7     # 训练集所占比例，可自己进行调整
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
    os.makedirs(txtsavepath)

num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)

file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')

for i in list_index:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        file_trainval.write(name)
        if i in train:
            file_train.write(name)
        else:
            file_val.write(name)
    else:
        file_test.write(name)

file_trainval.close()
file_train.close()
file_val.close()
file_test.close()

运行结果如下

yolov8训练时gpu占用很少_YOLO

3.2生成xml和txt文件的xml2txt代码

import xml.etree.ElementTree as ET
import os
sets = ['train', 'val', 'test']  # 如果你的Main文件夹没有test.txt，就删掉'test'
# classes = ["a", "b"]   # 改成自己的类别，VOC数据集有以下20类别
classes = ["A", "B", "C", "D"]  # class names
abs_path = '***' # ***该数据集的绝对路径

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(image_id):
    in_file = open(abs_path + '/Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open(abs_path + '/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
        # 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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


for image_set in sets:
    if not os.path.exists(abs_path + '/labels/'):
        os.makedirs(abs_path + '/labels/')

    image_ids = open(abs_path + '/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open(abs_path + '/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/JPEGImages/%s.jpg\n' % (image_id))  # 要么自己补全路径，只写一半可能会报错
        convert_annotation(image_id)
    list_file.close()

最后运行结果

yolov8训练时gpu占用很少_YOLO_02

yolo.yaml文件配置（该文件写好后放在yolov3或yolov3的data文件下）

# YOLOv5 yolov3
# 该文件存放在YOLOv5 3的/models中
# 文件夹的相对位置如下
# parent
# ├── yolo （yolov3 v5算法文件夹）
# └── datasets
#     └──DATA (数据集的名称)
# **为数据集绝对路径，注意冒号: 和路径之间必须有一个空格
train: **/train.txt
val: **/val.txt
test: **/test.txt

# Classes
nc: 5  # number of classes ##class数目
names: ['A',  'B',  'C',  'D',  'E']  # class names名称