引言
1 Windows环境准备
1.1 VSCode
Visual Studio Code（简称 VSCode）是一款由微软开发的开源代码编辑器。它非常受开发者欢迎，因为它功能强大、扩展性好，并且支持多种编程语言。VSCode 尤其适合 Python 开发，特别是在结合 Anaconda 的虚拟环境时，可以极大地提升开发效率。
官网下载
- 配置Anaconda环境
第一步：在Vscode中安装Python插件
第二步：选择anconda中的环境
在Vscode中使用CTRL+Shift+P的按钮打开搜索
然后输入：> select interpreter
-
安装中文插件（汉化）
参考链接🔗：Visual Studio Code安装中文插件 -
python相对路径设置
参考链接🔗：VScode 相对路径不能使用, 怎么办?
1.2 Anaconda安装（虚拟环境）
1.3 安装CUDA+cudnn
信息查看指令
- 显卡信息
nvcc -V
2. 驱动信息
nvidia-smi
2 目标检测——yolov5
- 环境安装教程： 【YOLO】YOLOv5-6.0环境搭建（不定时更新）
- yolov5官网源码：https://github.com/ultralytics/yolov5
- pytorc安装官网：https://pytorch.org/get-started/locally/
2.1 虚拟环境创建
conda create -n name python=3.9
conda activate name
2.2 pytorch安装
CUDA 10.2
pip install torch==1.12.1+cu102 torchvision==0.13.1+cu102 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu102
CUDA 11.3
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
# 查看torch的版本
python -c 'import torch;print(torch.__version__)'
python -c 'import torch;print(torch.cuda.is_available())'
CUDA 10.2
conda install cudatoolkit=10.2.89 cudnn==7.6.5 -c http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
CUDA 11.3
conda install cudatoolkit=11.3.1 cudnn==8.2.1 -c http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
2.3 源码下载及配置
pip install ultralytics
git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple # install
2.4 模型训练和测试
- 目标检测训练 （COCO8 Dataset）
from ultralytics import YOLO
# Load a model
model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training)
# Train the model
results = model.train(data="coco8.yaml", epochs=10, imgsz=640)
- 语义分割训练（COCO8-Seg Dataset）
from ultralytics import YOLO
# Load a model
model = YOLO("yolov8n-seg.pt") # load a pretrained model (recommended for training)
# Train the model
results = model.train(data="coco8-seg.yaml", epochs=100, imgsz=640)
2.5 自定义数据集训练
数据标注工具安装
【labelme】数据标注工具：https://blog.youkuaiyun.com/qq_44703886/article/details/108463900
pip install pyqt5 -i https://pypi.douban.com/simple
# labelme
pip install labelme -i https://pypi.douban.com/simple
# labelimg
pip install labelimg -i https://pypi.douban.com/simple
2.5.1 目标检测模型训练
训练自己的数据集：https://docs.ultralytics.com/yolov5/tutorials/train_custom_data/
参考链接：【YOLO】训练自己的数据集
cd /data3/205b/Alian/yolov5
python train.py --data D:\Alian_py\yolov5\data\my_coco128.yaml --cfg D:\Alian_py\yolov5\models\yolov5s.yaml --weights models/yolov56.pt --batch-size 4 --epochs 100 --img-size 640
2.5.2 目标检测自定义模型测试
python detect.py --source test --weights logs/exp/weights/best.pt --project results
2.5.3 语义分割模型训练
参考链接：YOLOV8实例分割——详细记录环境配置、自定义数据处理到模型训练与部署
用labelme工具标注好的数据集结构如下：
images：原始图片
json_labels：标签文件
labels：数据转换后的文件
数据格式转换脚本json2txt.py：
# -*- coding: utf-8 -*-
import json
import os
import argparse
from tqdm import tqdm
import glob
import cv2
import numpy as np
def convert_label_json(json_dir, save_dir, classes):
json_paths = os.listdir(json_dir)
classes = classes.split(',')
for json_path in tqdm(json_paths):
# for json_path in json_paths:
path = os.path.join(json_dir, json_path)
# print(path)
with open(path, 'r') as load_f:
print(load_f)
json_dict = json.load(load_f, )
h, w = json_dict['imageHeight'], json_dict['imageWidth']
# save txt path
txt_path = os.path.join(save_dir, json_path.replace('json', 'txt'))
txt_file = open(txt_path, 'w')
for shape_dict in json_dict['shapes']:
label = shape_dict['label']
label_index = classes.index(label)
points = shape_dict['points']
points_nor_list = []
for point in points:
points_nor_list.append(point[0] / w)
points_nor_list.append(point[1] / h)
points_nor_list = list(map(lambda x: str(x), points_nor_list))
points_nor_str = ' '.join(points_nor_list)
label_str = str(label_index) + ' ' + points_nor_str + '\n'
txt_file.writelines(label_str)
def check_labels(txt_labels, images_dir):
txt_files = glob.glob(txt_labels + "/*.txt")
for txt_file in txt_files:
filename = os.path.splitext(os.path.basename(txt_file))[0]
pic_path = os.path.join(images_dir, filename + ".jpg")
img = cv2.imread(pic_path)
height, width, _ = img.shape
file_handle = open(txt_file)
cnt_info = file_handle.readlines()
new_cnt_info = [line_str.replace("\n", "").split(" ") for line_str in cnt_info]
color_map = {"0": (0, 255, 255)}
for new_info in new_cnt_info:
print(new_info)
s = []
for i in range(1, len(new_info), 2):
b = [float(tmp) for tmp in new_info[i:i + 2]]
s.append([int(b[0] * width), int(b[1] * height)])
cv2.polylines(img, [np.array(s, np.int32)], True, color_map.get(new_info[0]))
cv2.namedWindow('img2', 0)
cv2.imshow('img2', img)
cv2.waitKey()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='json convert to txt params')
parser.add_argument('--json-dir', type=str, default='dataset/json_labels', help='json path dir')
parser.add_argument('--save-dir', type=str, default=r'D:\Alian_py\yolov5\datasets\coco8-seg-test\labels', help='txt save dir')
parser.add_argument('--classes', type=str, default='surface', help='classes')
parser.add_argument('--images-dir', type=str, default=r'D:\Alian_py\yolov5\datasets\coco8-seg-test\images', help='iamges path dir')
args = parser.parse_args()
json_dir = args.json_dir
save_dir = args.save_dir
classes = args.classes
images_dir = args.images_dir
# convert_label_json(json_dir, save_dir, classes)
# 检查转换的标签是否正确
# check_labels(save_dir, images_dir)
数据分割脚本seg_spilit.py
# -*- coding:utf-8 -*
import os
import random
import os
import shutil
def data_split(full_list, ratio):
n_total = len(full_list)
offset = int(n_total * ratio)
if n_total == 0 or offset < 1:
return [], full_list
random.shuffle(full_list)
sublist_1 = full_list[:offset]
sublist_2 = full_list[offset:]
return sublist_1, sublist_2
#数据集路径
images_dir=r"D:\Alian_py\yolov5\datasets\coco8-seg-test\images"
labels_dir=r"D:\Alian_py\yolov5\datasets\coco8-seg-test\labels"
#划分数据集，设置数据集数量占比
proportion_ = 0.9 #训练集占比
train_p=os.path.join(os.path.dirname(images_dir),"train")
val_p=os.path.join(os.path.dirname(images_dir),"val")
imgs_p="images"
labels_p="labels"
#创建训练集
if not os.path.exists(train_p):#指定要创建的目录
os.mkdir(train_p)
tp1=os.path.join(train_p,imgs_p)
tp2=os.path.join(train_p,labels_p)
print(tp1,tp2)
if not os.path.exists(tp1):#指定要创建的目录
os.mkdir(tp1)
if not os.path.exists(tp2): # 指定要创建的目录
os.mkdir(tp2)
#创建测试集文件夹
if not os.path.exists(val_p):#指定要创建的目录
os.mkdir(val_p)
vp1=os.path.join(val_p,imgs_p)
vp2=os.path.join(val_p,labels_p)
print(vp1,vp2)
if not os.path.exists(vp1):#指定要创建的目录
os.mkdir(vp1)
if not os.path.exists(vp2): # 指定要创建的目录
os.mkdir(vp2)
total_file = os.listdir(images_dir)
num = len(total_file) # 统计所有的标注文件
list_=[]
for i in range(0,num):
list_.append(i)
list1,list2=data_split(list_,proportion_)
for i in range(0,num):
file=total_file[i]
print(i,' - ',total_file[i])
name=file.split('.')[0]
if i in list1:
jpg_1 = os.path.join(images_dir, file)
jpg_2 = os.path.join(train_p, imgs_p, file)
txt_1 = os.path.join(labels_dir, name + '.txt')
txt_2 = os.path.join(train_p, labels_p, name + '.txt')
if os.path.exists(txt_1) and os.path.exists(jpg_1):
shutil.copyfile(jpg_1, jpg_2)
shutil.copyfile(txt_1, txt_2)
elif os.path.exists(txt_1):
print(txt_1)
else:
print(jpg_1)
elif i in list2:
jpg_1 = os.path.join(images_dir, file)
jpg_2 = os.path.join(val_p, imgs_p, file)
txt_1 = os.path.join(labels_dir, name + '.txt')
txt_2 = os.path.join(val_p, labels_p, name + '.txt')
shutil.copyfile(jpg_1, jpg_2)
shutil.copyfile(txt_1, txt_2)
print("数据集划分完成： 总数量：",num," 训练集数量：",len(list1)," 验证集数量：",len(list2))
3 语义分割
官网源码：https://github.com/open-mmlab/mmsegmentation
中文教程：https://github.com/open-mmlab/mmsegmentation/blob/main/README_zh-CN.md
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
