【YOLOV5】使用YOLOV5训练自己的数据集并预测

一数据准备

使用的labelImg标注工具，对数据进行标注。标注工具具体使用方法，可以自己去查一下。

在yolov5-master/data文件下新建下列文件夹

images文件夹放置图像文件，Annotations文件夹放置标注好的xml文件，ImageSets文件夹放置生成的训练txt文件，labels放置生成的标签文件。

A 在yolov5-master文件夹下新建dataprocess_split.py文件并运行，代码如下：

import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = 'data/Annotations'
txtsavepath = 'data/ImageSets'
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open('data/ImageSets/trainval.txt', 'w')
ftest = open('data/ImageSets/test.txt', 'w')
ftrain = open('data/ImageSets/train.txt', 'w')
fval = open('data/ImageSets/val.txt', 'w')
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftest.write(name)
        else:
            fval.write(name)
    else:
        ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

B在yolov5-master文件夹下新建dataprocess_voc_label.py文件并运行，代码如下：


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 = ['face']
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))
    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/%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()

二配置文件

1 数据集的配置

数据准备后，训练之前，修改配置文件。在data文件夹下，找到coco.yaml文件。复制一份，重命名为me.yaml(自己随意命名)。修改文件内容如下：

2 模型的配置文件

聚类得出先验框（可选）（聚类重新生成anchors运行时间较长）
最新版的yolov5，它会自动kmeans算出anchors。

dataprocess_kmeans.py代码如下：

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

聚类生成新anchors的文件dataprocess_clauculate_anchors.py，代码中的路径请根据自己的路径进行修改，代码内容如下：

import os
import numpy as np
import xml.etree.cElementTree as et
from kmeans import kmeans, avg_iou

FILE_ROOT = "yolov5/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 = "yolov5/data/anchors.txt"

CLUSTERS = 9
CLASS_NAMES = ['face']

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dataprocess_clauculate_anchors.py生成一个anchors.txt文件，内容如下：

在yolov5目录下的model文件夹下是模型的配置文件，这边提供s、m、l、x版本，逐渐增大（随着架构的增大，训练时间也是逐渐增大）。

假设采用yolov5s.yaml，只用修改一个参数，把nc改成自己的类别数。根据anchors.txt 中的 Best Anchors 修改，需要取整（可选）。

此时需要下载yolov5的预权重文件，请自行下载。

下载后，将yolov5s.pt权重文件放到weights文件夹下即可。

3 训练文件

对train.py文件进行修改后，就可以开始训练。修改如下几处：

三开始训练

运行train.py

训练结束后，生成的模型路径为：yolov5\runs\train\exp5\weights

四预测

将模型best.pt复制到yolov5-master/下，并改名yolov5s.pt。

detect.py文件修改如下：

运行detect.py，结果图所存的路径为：yolov5\runs\detect