🔥本文 GitHub https://github.com/kzbkzb/Python-AI已收錄

大家好，我是K同學啊！

我們接著上一篇文章 深度學習100例 | 第51天-目標檢測演算法（YOLOv5）（入門篇） 配置完YOLOv5需要的環境后，今天我們試著用YOLOv5訓練自己的資料，（在開始本教程前，記得先跑一遍入門篇，確保其他環境是正常的）

有圖有真相，先看看我昨天的運行結果

【YOLOv5 原始碼地址】

🚀 我的環境：

• 語言環境：Python3.8
• 編譯器：PyCharm
• 深度學習環境：
  • torch==1.10.0+cu113
  • torchvision==0.11.1+cu113
• 顯卡：GeForce RTX 3080

一、準備好自己的資料

我的目錄結構是這樣子的

• 主目錄
  • paper_data（自己創建一個檔案夾，將資料放到這里）
    • Annotations（放置我們的.xml檔案）
    • images（放置圖片檔案）
    • ImageSets
      • Main（會在該檔案夾內自動生成 train.txt、val.txt、test.txt 和 trainval.txt 四個檔案，存放訓練集、驗證集、測驗集圖片的名字）

你將會看如下的目錄結構：

Annotations檔案夾為xml檔案，我的檔案如下：

我images檔案位.png格式，官方的為.jpg，不過問題不大后面改一下代碼即可（后面會講解）

二、運行 split_train_val.py 檔案

ImageSets檔案夾下面有個Main子檔案夾，其下面存放了 train.txt、val.txt、test.txt 和 trainval.txt 四個檔案，它們是通過 split_train_val.py 檔案來生成的，

split_train_val.py 檔案的位置如下：

split_train_val.py 的內容如下：

# coding:utf-8

import os
import random
import argparse

parser = argparse.ArgumentParser()
#xml檔案的地址，根據自己的資料進行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
#資料集的劃分，地址選擇自己資料下的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()

運行 split_train_val.py 檔案后你將得到 train.txt、val.txt、test.txt 和 trainval.txt 四個檔案，結果如下：

三、生成 train.txt、test.txt、val.txt 檔案

先看看我們要生成的檔案位置

開始辦事，現在我們需要的是 voc_label.py 檔案，其位置如下：

voc_label.py 檔案的內容如下：

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

sets = ['train', 'val', 'test']
classes = ["unripe citrus"]   # 改成自己的類別
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('./Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('./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
        # 標注越界修正
        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('./labels/'):
        os.makedirs('./labels/')
    image_ids = open('./ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('./%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/images/%s.png\n' % (image_id)) # 注意你的圖片格式，如果是.jpg記得修改
        convert_annotation(image_id)
    list_file.close()

運行 voc_label.py 檔案，你將會得到上面截圖中 train.txt、test.txt、val.txt三個檔案，檔案內容如下：

四、創建 ab.yaml 檔案

這個檔案名是我隨意取的，這個可以做出改變的哈

ab.yaml 檔案的位置如下：

我的 ab.yaml 檔案內容如下：

#path: ../datasets/coco  # dataset root dir
train: ./paper_data/train.txt  # train images (relative to 'path') 118287 images
val: ./paper_data/val.txt  # train images (relative to 'path') 5000 images
#test: test-dev2017.txt

nc: 1  # number of classes

names: ['unripe citrus'] # 改成自己的類別

五、聚類得出先驗框

首先，我們需要準備 kmeans.py 檔案，檔案位于主目錄下，其內容如下：

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")                 # 如果報這個錯，可以把這行改成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))

然后，需要再準備一個名為 clauculate_anchors.py 的檔案，該檔案同樣位于主目錄下，其內容如下：

# -*- coding: utf-8 -*-
# 根據標簽檔案求先驗框

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

FILE_ROOT = "./paper_data/"     # 根路徑
ANNOTATION_ROOT = "Annotations"  # 資料集標簽檔案夾路徑
ANNOTATION_PATH = FILE_ROOT + ANNOTATION_ROOT

print(ANNOTATION_PATH)

ANCHORS_TXT_PATH = "./data/anchors.txt"

CLUSTERS = 1  # 類別數注意修改
CLASS_NAMES = ['unripe citrus'] #修改為自己的類別

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，否則時間很長
        anchors_tmp = []
        print(train_boxes)
        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()

運行 clauculate_anchors.py 檔案，我們將會得到 anchors.txt 檔案

六、開始用自己的資料集訓練模型

輸入命令：

python train.py --img 900 --batch 2 --epoch 100 --data data/ab.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --device '0'

就可以直接訓練我們自己的資料集啦，我最后的運行結果如下：

如果你還有問題無法解決可以加我微信（mtyjkh_）或者直接在下面留言哈，看到后都會盡快回復你的，