yolov5-pytorch训练自己数据集

一、yolov5源码测试

1、源码下载（v4.0版本）

官方地址：https://github.com/ultralytics/yolov5

2、模型下载

官方链接：https://github.com/ultralytics/yolov5/releases
yolov5l.pt
yolov5s.pt
yolov5x.pt
yolov5m.pt
将权重文件放入yolov5-master/weights文件夹下

3、环境配置

pip3 install -r requirements.txt

4、测试

git clone https://github.com/ultralytics/yolov5/releases
cd yolov5-master
#1 利用自带摄像头检测
python3 detec.py --source 0
#2 else
python detect.py --source 0  # webcam
                            file.jpg  # image 
                            file.mp4  # video
# 3 批量检测输出
python3 detect.py --source data/images --weights yolov5s.pt --conf 0.25

二、训练自己数据集

1、数据集构建

在yolov5-master文件夹构建my_Data文件夹存放自己数据
数据集结构显示：

myData
  ......images           #存放图像
  ......Annotations          #存放图像对应的xml文件
  ......ImageSets/Main       #存放训练/存放train.txt/val.txt/test.txt/trainval.txt文件
  ......test.py              #生成train.txt/val.txt/test.txt/trainval.txt文件

2、在ImageSets/Main下生成.txt文件

建立my_test.py文件：

# 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
train_percent = 0.9
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()

运行代码后在Main文件夹生成四个txt文档：

3、将数据集格式转换为yolo_txt格式，同时生成label标签

创建my_label.py文件

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['train', 'val', 'test']
classes = ["person"]   # 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('/home/wyh/keti/mubiao/yolov5-master/my_Data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('/home/wyh/keti/mubiao/yolov5-master/my_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))
        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('/home/wyh/keti/mubiao/yolov5-master/my_Data/labels/'):
        os.makedirs('/home/wyh/keti/mubiao/yolov5-master/my_Data/labels/')
    image_ids = open('/home/wyh/keti/mubiao/yolov5-master/my_Data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('/home/wyh/keti/mubiao/yolov5-master/my_Data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/home/wyh/keti/mubiao/yolov5-master/my_Data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

运行后在my_Data文件夹下生成labels文件夹和三个txt文件，labels中为不同图像的标注文件，
labels文件格式

0 0.8095238095238095 0.53 0.3630952380952381 0.892
0 0.25297619047619047 0.604 0.41666666666666663 0.46
0 0.30952380952380953 0.301 0.4583333333333333 0.28200000000000003

4、配置文件

4.1 在my_Data文件夹下新建my_data.yaml文件

文件内容：

# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
# Train command: python train.py --data voc.yaml
# Default dataset location is next to /yolov5:
#   /parent_folder
#     /VOC
#     /yolov5


# download command/URL (optional)
download: bash data/scripts/get_coco.sh

# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: /home/wyh/keti/mubiao/yolov5-master/my_Data/images  # 16551 images
val: /home/wyh/keti/mubiao/yolov5-master/my_Data/images # 4952 images
#test: /home/wyh/keti/mubiao/yolov5-master/my_Data/test.txt
# number of classes
nc: 1

# class names
names: [ 'person' ]

注：将labels文件夹和images文件夹修改成如下格式

images
  ......train  #原始图片
  ......val
labels
  ......train #label文件
  ......val

5、修改模型配置文件

5.1 在my_Data文件夹新建my_yolov5s.yaml文件

# parameters
nc: 1  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple

# anchors
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32
......

修改nc 、根据情况修改anchors

5.2 kmeans聚类

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")

    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))

聚类生成新anchors的文件new_anchors.py

# -*- 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 = "/home/wyh/keti/mubiao/yolov5-master/my_Data/"     # 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 = "/home/wyh/keti/mubiao/yolov5-master/my_Data/anchors.txt"

CLUSTERS = 1
CLASS_NAMES = ['person']

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()

进行路径修改

三、训练

1、训练

 parser = argparse.ArgumentParser()
    parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
    parser.add_argument('--cfg', type=str, default='my_Data/my_yolov5s.yaml', help='model.yaml path')
    parser.add_argument('--data', type=str, default='my_Data/my_data.yaml', help='data.yaml path')
    parser.add_argument('--hyp', type=str, default='data/hyp.scratch.yaml', help='hyperparameters path')
    parser.add_argument('--epochs', type=int, default=300)
    parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')

参数修改cfg\data等
epochs：指的就是训练过程中整个数据集将被迭代多少次,显卡不行你就调小点。
batch-size：一次看完多少张图片才进行权重更新，梯度下降的mini-batch,显卡不行你就调小点。
cfg：存储模型结构的配置文件
data：存储训练、测试数据的文件
img-size：输入图片宽高,显卡不行你就调小点。
rect：进行矩形训练
resume：恢复最近保存的模型开始训练
nosave：仅保存最终checkpoint
notest：仅测试最后的epoch
evolve：进化超参数
bucket：gsutil bucket
cache-images：缓存图像以加快训练速度
weights：权重文件路径
name： 重命名results.txt to results_name.txt
device：cuda device, i.e. 0 or 0,1,2,3 or cpu
adam：使用adam优化
multi-scale：多尺度训练，img-size +/- 50%
single-cls：单类别的训练集
训练：

python3 train.py --img 640 --batch 8 --epoch 5 --data my_Data/my_data.yaml --cfg my_Data/my_yolov5s.yaml --weights weights/yolov5s.pt --device cpu    # 0号GPU  -device 0

2、可视化

训练后生成runs文件夹

tensorboard --logdir=runs

四、测试

参考链接：https://blog.csdn.net/qq_36756866/article/details/109111065