yolov5训练自己的数据集
一、声明
本文仅作为记录学习的过程，当作个人笔记，文中内容全部为摘抄借鉴，附参考链接
(2条消息) Yolov5训练自己的数据集（详细完整版）_缔宇diyu的博客-CSDN博客_yolov5训练自己的数据集
这位大佬清晰的介绍了yolov5的训练过程，借鉴此大佬的文章记录一下学习过程
二、数据集的准备
VOC格式数据集主要有两个文件夹，和一个文件，一个为存放图片的文件夹，另外一个为存放xml格式的标注文件夹，还有一个存放类别信息的txt文件，将官方GitHub下载到的yolov5源码使用pycharm打开，根目录下创建一个文件夹用来存放数据集，此处命名为VOCData，将图片文件和标注文件放入到该目录下，并将图片文件夹命名为images，标注文件夹命名为Annotation（注意：文件夹的名字一定不要有错，因为给出的代码中已经写好固定的文件夹名称，为了简便操作，文件夹的名称尽量与作者一致。），如图所示，创建几个py文件。
split_train_val.py（不需要修改）
# coding:utf-8
import os
import random
import argparse
parser = argparse.ArgumentParser()
#xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
#数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()
trainval_percent = 1.0 # 训练集和验证集所占比例。 这里没有划分测试集
train_percent = 0.9 # 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()
text_to_yolo.py
需要将第 7 行改成自己所标注的类别 以及 代码中各文件绝对路径
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["light", "post"] # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
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('D:/Yolov5/yolov5/VOCData/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('D:/Yolov5/yolov5/VOCData/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')
wd = getcwd()
for image_set in sets:
if not os.path.exists('D:/Yolov5/yolov5/VOCData/labels/'):
os.makedirs('D:/Yolov5/yolov5/VOCData/labels/')
image_ids = open('D:/Yolov5/yolov5/VOCData/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
if not os.path.exists('D:/Yolov5/yolov5/VOCData/dataSet_path/'):
os.makedirs('D:/Yolov5/yolov5/VOCData/dataSet_path/')
list_file = open('dataSet_path/%s.txt' % (image_set), 'w')
# 这行路径不需更改，这是相对路径
for image_id in image_ids:
list_file.write('D:/Yolov5/yolov5/VOCData/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
kmeans.py 程序如下：这不需要运行，也不需要更改
import numpy as np
def iou(box, clusters):
"""
Calculates the Intersection over Union (IoU) between a box and k clusters.
:param box: tuple or array, shifted to the origin (i. e. width and height)
:param clusters: numpy array of shape (k, 2) where k is the number of clusters
:return: numpy array of shape (k, 0) where k is the number of clusters
"""
x = np.minimum(clusters[:, 0], box[0])
y = np.minimum(clusters[:, 1], box[1])
if np.count_nonzero(x == 0) > 0 or np.count_nonzero(y == 0) > 0:
raise ValueError("Box has no area") # 如果报这个错，可以把这行改成pass即可
intersection = x * y
box_area = box[0] * box[1]
cluster_area = clusters[:, 0] * clusters[:, 1]
iou_ = intersection / (box_area + cluster_area - intersection)
return iou_
def avg_iou(boxes, clusters):
"""
Calculates the average Intersection over Union (IoU) between a numpy array of boxes and k clusters.
:param boxes: numpy array of shape (r, 2), where r is the number of rows
:param clusters: numpy array of shape (k, 2) where k is the number of clusters
:return: average IoU as a single float
"""
return np.mean([np.max(iou(boxes[i], clusters)) for i in range(boxes.shape[0])])
def translate_boxes(boxes):
"""
Translates all the boxes to the origin.
:param boxes: numpy array of shape (r, 4)
:return: numpy array of shape (r, 2)
"""
new_boxes = boxes.copy()
for row in range(new_boxes.shape[0]):
new_boxes[row][2] = np.abs(new_boxes[row][2] - new_boxes[row][0])
new_boxes[row][3] = np.abs(new_boxes[row][3] - new_boxes[row][1])
return np.delete(new_boxes, [0, 1], axis=1)
def kmeans(boxes, k, dist=np.median):
"""
Calculates k-means clustering with the Intersection over Union (IoU) metric.
:param boxes: numpy array of shape (r, 2), where r is the number of rows
:param k: number of clusters
:param dist: distance function
:return: numpy array of shape (k, 2)
"""
rows = boxes.shape[0]
distances = np.empty((rows, k))
last_clusters = np.zeros((rows,))
np.random.seed()
# the Forgy method will fail if the whole array contains the same rows
clusters = boxes[np.random.choice(rows, k, replace=False)]
while True:
for row in range(rows):
distances[row] = 1 - iou(boxes[row], clusters)
nearest_clusters = np.argmin(distances, axis=1)
if (last_clusters == nearest_clusters).all():
break
for cluster in range(k):
clusters[cluster] = dist(boxes[nearest_clusters == cluster], axis=0)
last_clusters = nearest_clusters
return clusters
if __name__ == '__main__':
a = np.array([[1, 2, 3, 4], [5, 7, 6, 8]])
print(translate_boxes(a))
clauculate_anchors.py
会调用 kmeans.py 聚类生成新anchors的文件
程序如下：
需要更改第 9 、13行文件路径 以及 第 16 行标注类别名称
# -*- coding: utf-8 -*-
# 根据标签文件求先验框
import os
import numpy as np
import xml.etree.cElementTree as et
from kmeans import kmeans, avg_iou
FILE_ROOT = "D:/Yolov5/yolov5/VOCData/" # 根路径
ANNOTATION_ROOT = "Annotations" # 数据集标签文件夹路径
ANNOTATION_PATH = FILE_ROOT + ANNOTATION_ROOT
ANCHORS_TXT_PATH = "D:/Yolov5/yolov5/VOCData/anchors.txt" #anchors文件保存位置
CLUSTERS = 9
CLASS_NAMES = ['light', 'post'] #类别名称
def load_data(anno_dir, class_names):
xml_names = os.listdir(anno_dir)
boxes = []
for xml_name in xml_names:
xml_pth = os.path.join(anno_dir, xml_name)
tree = et.parse(xml_pth)
width = float(tree.findtext("./size/width"))
height = float(tree.findtext("./size/height"))
for obj in tree.findall("./object"):
cls_name = obj.findtext("name")
if cls_name in class_names:
xmin = float(obj.findtext("bndbox/xmin")) / width
ymin = float(obj.findtext("bndbox/ymin")) / height
xmax = float(obj.findtext("bndbox/xmax")) / width
ymax = float(obj.findtext("bndbox/ymax")) / height
box = [xmax - xmin, ymax - ymin]
boxes.append(box)
else:
continue
return np.array(boxes)
if __name__ == '__main__':
anchors_txt = open(ANCHORS_TXT_PATH, "w")
train_boxes = load_data(ANNOTATION_PATH, CLASS_NAMES)
count = 1
best_accuracy = 0
best_anchors = []
best_ratios = []
for i in range(10): ##### 可以修改，不要太大，否则时间很长
anchors_tmp = []
clusters = kmeans(train_boxes, k=CLUSTERS)
idx = clusters[:, 0].argsort()
clusters = clusters[idx]
# print(clusters)
for j in range(CLUSTERS):
anchor = [round(clusters[j][0] * 640, 2), round(clusters[j][1] * 640, 2)]
anchors_tmp.append(anchor)
print(f"Anchors:{anchor}")
temp_accuracy = avg_iou(train_boxes, clusters) * 100
print("Train_Accuracy:{:.2f}%".format(temp_accuracy))
ratios = np.around(clusters[:, 0] / clusters[:, 1], decimals=2).tolist()
ratios.sort()
print("Ratios:{}".format(ratios))
print(20 * "*" + " {} ".format(count) + 20 * "*")
count += 1
if temp_accuracy > best_accuracy:
best_accuracy = temp_accuracy
best_anchors = anchors_tmp
best_ratios = ratios
anchors_txt.write("Best Accuracy = " + str(round(best_accuracy, 2)) + '%' + "\r\n")
anchors_txt.write("Best Anchors = " + str(best_anchors) + "\r\n")
anchors_txt.write("Best Ratios = " + str(best_ratios))
anchors_txt.close()
运行 split_train_val.py
运行完毕后 会生成 ImagesSets\Main 文件夹，且在其下生成 测试集、训练集、验证集，存放图片的名字（无后缀.jpg）
我们的类别文件往往为txt文件这种格式
当类别较多时，为了方便转换成列表，可以创建一个py函数
readtext.py
file=open('classes.txt',encoding='UTF-8')
dataMat=[]
for line in file.readlines():
curLine=line.replace('\n', '')
dataMat.append(curLine)
print('dataMat:',dataMat)
print(len(dataMat))
复制输出结果即可。
运行text_to_yolo.py
运行后会生成如下 labels 文件夹和 dataSet_path 文件夹。
其中 labels 中为不同图像的标注文件。每个图像对应一个txt文件，文件每一行为一个目标的信息，包括class, x_center, y_center, width, height格式，这种即为 yolo_txt格式
3.配置文件
在 yolov5 目录下的 data 文件夹下 新建一个 myvoc.yaml文件（可以自定义命名），用记事本打开。
内容是：训练集以及验证集（train.txt和val.txt）绝对路径（通过 text_to_yolo.py 生成），然后是目标的类别数目和类别名称。
运行 clauculate_anchors.py
会生成anchors文件。如果生成文件为空，重新运行即可。
第二行 Best Anchors 后面需要用到。
使用记事本打开 yolov5s.yaml。
修改两个参数。
把 nc 改成自己的标注类别数
修改anchors，根据 anchors.txt 中的 Best Anchors 修改，需要取整（四舍五入、向上、向下都可以）。
保持yaml中的anchors格式不变，按顺序一对一即可。
点击开始训练，参数改为自己的配置文件
