使用RKNN官方指定的yolov5训练模型:
环境配置:
先把官方指定的yolov5版本贴出来官方yolov5
这里建议大家用官方的yolov5去训练,这样最后在香橙派5上展现出来的效果最好。
大家先到GitHub上把yolov5给下载下来,这时候我们得给电脑安装一个anaconda,用来创建虚拟环境,这样我们再把yolov5需要的环境给下载到这个虚拟环境中,这样环境与环境中就不会相互干扰和污染。
进入虚拟环境后,我们根据需求来安装一下依赖包。
pip install -r requirements.txt
这里要注意一点,因为每台电脑装载的显卡版本不同,在安装完之后,大家可以运行一下一下代码来判断一下自己的torch版本是否匹配。如果出现“successful installation!”那就是安装成功了,反之就是每成功。
import torch
print(“successful installation!”) if torch.cuda.is_available() else print(“fail installation”)
如果不匹配的话,大家可以到torch官网下载一下,这里我也给大家把地址贴一下,省的大家再去找https://download.pytorch.org/whl/torch_stable.html在这个界面下,torch的版本是非常全的
yolov5模型训练:
根据一篇大佬的文章大佬的文章,这里也简单记录一下吧,毕竟还是有些不同的
首先在yolov5文件夹下新建一个文件夹,这里取名为VOCData,并在这个文件夹下面新建两个文件夹,一个是Annotations,另一个是images。其中Annotations下面放的是我们标注好的.xml文件,另一个images下面放的是我们拍摄的图片。
划分数据集
接下来,我们要在VOCData下面新建文件 split_train_val.py用来划分我们的数据集(这里不需要修改,直接运行就可以)
# 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()
运行完后会在VOCData\ImagesSets\Main下生成 测试集、训练集、训练验证集和验证集,如下图所示:
将.xml文件转为.txt文件
在VOCData目录下创建程序 text_to_yolo.py 并运行,开头classes部分改成自己的类别。
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["0","1","2","3","4","5","6","7","8","9"] # 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('E:/SQY/new/yolov5-master/VOCData/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('E:/SQY/new/yolov5-master/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('E:/SQY/new/yolov5-master/VOCData/labels/'):
os.makedirs('E:/SQY/new/yolov5-master/VOCData/labels/')
image_ids = open('E:/SQY/new/yolov5-master/VOCData/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
if not os.path.exists('E:/SQY/new/yolov5-master/VOCData/dataSet_path/'):
os.makedirs('E:/SQY/new/yolov5-master/VOCData/dataSet_path/')
list_file = open('dataSet_path/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write('E:/SQY/new/yolov5-master/VOCData/images/%s.JPG\n' % (image_id))
convert_annotation(image_id)
list_file.close()
运行完后会生成如下 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。dataSet_path文件夹包含三个数据集的txt文件,train.txt等txt文件为划分后图像所在位置的绝对路径,如train.txt就含有所有训练集图像的绝对路径。
配置voc.yaml文件
在 yolov5 目录下的 data 文件夹下 新建一个 voc.yaml文件
train: E:\SQY\new\yolov5-master\VOCData\dataSet_path\train.txt
val: E:\SQY\new\yolov5-master\VOCData\dataSet_path\val.txt
# number of classes
nc: 10
# class names
names: ["0","1","2","3","4","5","6","7","8","9"]
上面部分根据自己的数据集修改即可
参考文章:
聚类先验框
生成anchors文件,VOCData目录下创建程序两个程序 kmeans.py 以及 clauculate_anchors.py不需要运行 kmeans.py,运行 clauculate_anchors.py 即可。
kmeans.py 程序如下:这不需要运行,也不需要更改,报错则查看第十三行内容。
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((</