训练pytorch yolo5

结构

data
  +Annotations
  +images
  +ImageSets
    ++Main
  +labels

修改data下面的yaml文件

修改model下面的对应的模型文件

运行maketxt.py

import os  
import random  
  
val_percent = 0.1 #验证集(实际为 0.9*0.1)
train_percent = 0.9 #训练集 测试集为1-0.9
xmlfilepath = 'Annotations'  
txtsavepath = 'ImageSets\Main'  
total_xml = os.listdir(xmlfilepath)  
  
num=len(total_xml)  
list=range(num)  
tr=int(num*train_percent)  
tv=int(tr*val_percent)  
train= random.sample(list,tr)  
val=random.sample(train,tv)  
  
ftest = open('ImageSets/Main/test.txt', 'w')  
ftrain = open('ImageSets/Main/train.txt', 'w')  
fval = open('ImageSets/Main/val.txt', 'w')  
  
for i  in list:  
    name=total_xml[i][:-4]+'\n'  
    if i in train:  
        ftrain.write(name) 
        if i in val:   
            fval.write(name) 
    else:   
        ftest.write(name)  
  
ftrain.close()  
fval.close()  
ftest.close()

运行voc_label.py

# -*- coding: utf-8 -*-
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 = ["persion"]#我们只是检测人，因此只有一个类别
 
 
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/Annotations/%s.xml' % (image_id),"r", encoding='UTF-8')
    out_file = open('data/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/labels/'):
        os.makedirs('data/labels/')
    image_ids = open('data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

训练

python train.py --data data/persion.yaml --cfg models/yolov5x.yaml --batch-size 16 --epochs 300