Yolov5——訓練目標檢測模型

專案的克隆

開啟yolov5官網（GitHub - ultralytics/yolov5 at v5.0），下載yolov5的專案：

環境的安裝（免額外安裝CUDA和cudnn）

開啟anaconda的終端，建立新的名為yolov5的環境（python選擇3.8版本）：

conda create -n yolov5 python=3.8

執行如下命令，啟用這個環境：

conda activate yolov5

開啟pytorch的官網，選擇自己顯示卡對應的pytorch版本（我的顯示卡為GTX1650，這裡選擇1.8.0pytorch版本）：

選擇CUDA版本（這裡我選擇10.2），複製命令到anaconda終端執行：

至此pytorch環境安裝完成，接下來驗證CUDA和cudnn版本，開啟Ptcharm，執行如下程式碼：

import torch
print(torch.cuda.is_available())
print(torch.backends.cudnn.is_available())
print(torch.cuda_version)
print(torch.backends.cudnn.version())

輸出如下結果表示安裝成功：

利用labelimg標註資料集：

labelimg的安裝：

開啟cmd命令控制檯，輸入如下的命令下載labelimg相關的依賴：

pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple

資料準備：

新建一個名為VOC2007的資料夾，在裡面建立一個名為JPEGImages的資料夾存放需要打標籤的圖片檔案；再建立一個名為Annotations的資料夾存放標註的標籤檔案；最後建立一個名為 predefined_classes.txt 的txt檔案來存放所要標註的類別名稱（這裡我的類別一共有6類，分別是fanbingbing，jiangwen，liangjiahui，liuyifei，zhangziyi，zhoujielun）：

進入到剛剛建立的VOC2007路徑，執行cmd命令：

輸入如下的命令開啟labelimg並初始化predefined_classes.txt裡面定義的類：

labelimg JPEGImages predefined_classes.txt

開啟view設定，勾選如下選項（建議勾選）：

標註資料：

按下快捷鍵W調出標註十字架，選擇需要標註的物件區域，並定義自己要標註的類別：

打完標籤後的圖片會在Annotations 資料夾下生成對應的xml檔案：

資料集格式轉化及訓練集和驗證集劃分

利用pycharm開啟從yolov5官網下載的yolov5專案，在該專案目錄下建立名為VOCdevkit的資料夾，並將剛才的VOC2007資料夾放入：

在VOCdevkit的同級目錄下建立新的python檔案，執行如下程式碼：

（注：classes裡面必須正確填寫xml裡面已經標註好的類這裡為classes = ["fanbingbing", "jiangwen", "liangjiahui", "liuyifei", "zhangziyi", "zhoujielun"]）

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile

classes = ["fanbingbing", "jiangwen", "liangjiahui", "liuyifei", "zhangziyi", "zhoujielun"]
# classes=["ball"]

TRAIN_RATIO = 80


def clear_hidden_files(path):
    dir_list = os.listdir(path)
    for i in dir_list:
        abspath = os.path.join(os.path.abspath(path), i)
        if os.path.isfile(abspath):
            if i.startswith("._"):
                os.remove(abspath)
        else:
            clear_hidden_files(abspath)


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("F:/Yolov5/yolov5_offical/yolov5-master/VOCdevkit/VOC2007/Annotations/%s.xml" % image_id)
    out_file = open('F:/Yolov5/yolov5_offical/yolov5-master/VOCdevkit/VOC2007/YOLOLabels/%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')
    in_file.close()
    out_file.close()


wd = os.getcwd()
wd = os.getcwd()
data_base_dir = os.path.join(wd, "F:/Yolov5/yolov5_offical/yolov5-master/VOCdevkit/")
if not os.path.isdir(data_base_dir):
    os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
    os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
    os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
    os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
    os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
    os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
    os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
    os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
    os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
    os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)

train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir)  # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
    path = os.path.join(image_dir, list_imgs[i])
    if os.path.isfile(path):
        image_path = image_dir + list_imgs[i]
        voc_path = list_imgs[i]
        (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
        (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
        annotation_name = nameWithoutExtention + '.xml'
        annotation_path = os.path.join(annotation_dir, annotation_name)
        label_name = nameWithoutExtention + '.txt'
        label_path = os.path.join(yolo_labels_dir, label_name)
    prob = random.randint(1, 100)
    print("Probability: %d" % prob)
    if (prob < TRAIN_RATIO):  # train dataset
        if os.path.exists(annotation_path):
            train_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_train_dir + voc_path)
            copyfile(label_path, yolov5_labels_train_dir + label_name)
    else:  # test dataset
        if os.path.exists(annotation_path):
            test_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_test_dir + voc_path)
            copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()