目录
本片梳理博主在制备数据集所遇问题
1.labelme打开图片闪退问题
原因：数据位深不正确，所有位深为32，打开之后labelme直接闪退
解决：修改为24位深
from PIL import Image
import os
path = "D:\Desktop\实验\图片" # 原始位像素图像文件路径
save_path = "D:\Desktop\实验\图片24" # 转后保存的路径
files = os.listdir(path)
for pic in files:
img = Image.open(os.path.join(path, pic)).convert('RGB')
print(img.getbands()) # ('P',) 这种是有彩色的，而L是没有彩色的
pic_new = os.path.join(save_path, pic)
img.save(pic_new)
2.数据格式问题
jpg格式转化
创建txt文件，并将添加内容，并将后缀名改为.bat
@Echo Off&SetLocal ENABLEDELAYEDEXPANSION
FOR %%a in (*) do (
set "name=%%a"
set "name=!name: (=!"
set "name=!name:)=!"
ren "%%a" "!name!"
)
exit
3.数据量少问题
kears数据增广
首先是kears环境问题：【快速解决】vscode安装Keras，tensorflow；解决from tensorflow.keras.models import Sequential环境配置不上怎么办？_无法解析导入“keras.models”-CSDN博客
import os
from numpy import expand_dims
from keras.preprocessing.image import load_img, img_to_array
from keras.preprocessing.image import ImageDataGenerator
from matplotlib import pyplot as plt
import numpy as np
from PIL import Image
import shutil
# 设置源文件夹路径
source_folder = r''
# 遍历源文件夹中的所有图片
for filename in os.listdir(source_folder):
if filename.endswith('.jpg') or filename.endswith('.png'): # 根据需要添加其他图片格式
# 构建完整的文件路径
filepath = os.path.join(source_folder, filename)
# 加载图片
img = load_img(filepath)
# 转换为numpy数组
data = img_to_array(img)
# 扩展维度以适应模型输入
samples = expand_dims(data, 0)
# 创建图像数据增强生成器
data_gen = ImageDataGenerator(
width_shift_range=0.2, # TODO：随机水平方向平移图像(fraction of total width)
height_shift_range=0.2, # TODO：随机纵向平移图像(fraction of total height)
horizontal_flip=True,
rotation_range=180,
zoom_range=[0.9, 1.0],
#参数有很多
)
# 准备迭代器
it = data_gen.flow(samples, batch_size=1)
# 为增强后的图像创建一个新文件夹（如果需要）
augmented_folder = os.path.join(source_folder, 'augmented')
if not os.path.exists(augmented_folder):
os.makedirs(augmented_folder)
# 生成增强后的样本并保存
for i in range(9): # 假设我们想要为每个原始图像生成5个增强版本
# 生成一批图像
batch = it.next()
# 转换为无符号整数以便查看和保存
augmented_image = batch[0].astype('uint8')
# 创建保存路径
augmented_filepath = os.path.join(augmented_folder, f'{i}_{filename}')
# 将增强后的图像保存为文件
Image.fromarray(augmented_image).save(augmented_filepath)
# 注意：在实际应用中，您可能想要删除上面的可选显示部分，以避免在处理大量图像时产生不必要的延迟。4.数据转化问题
json to txt：
import json
import os
name2id = {'blood': 0} # 标签名称
def convert(img_size, box):
dw = 1. / (img_size[0])
dh = 1. / (img_size[1])
x = (box[0] + box[2]) / 2.0 - 1
y = (box[1] + box[3]) / 2.0 - 1
w = box[2] - box[0]
h = box[3] - box[1]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
def decode_json(json_floder_path, json_name):
txt_name = r'D:\TestMain\yolov10\datasets\bfish\lables/' + json_name[0:-5] + '.txt'
# 存放txt的绝对路径
txt_file = open(txt_name, 'w')
json_path = os.path.join(json_floder_path, json_name)
data = json.load(open(json_path, 'r', encoding='gb2312', errors='ignore'))
img_w = data['imageWidth']
img_h = data['imageHeight']
for i in data['shapes']:
label_name = i['label']
if (i['shape_type'] == 'rectangle'):
x1 = int(i['points'][0][0])
y1 = int(i['points'][0][1])
x2 = int(i['points'][1][0])
y2 = int(i['points'][1][1])
bb = (x1, y1, x2, y2)
bbox = convert((img_w, img_h), bb)
txt_file.write(str(name2id[label_name]) + " " + " ".join([str(a) for a in bbox]) + '\n')
if __name__ == "__main__":
json_floder_path = r'D:\TestMain\yolov10\datasets\bfish\json'
# 存放json的文件夹的绝对路径
json_names = os.listdir(json_floder_path)
for json_name in json_names:
decode_json(json_floder_path, json_name)xml to txt：
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
def convert(size, box):
# size=(width, height) b=(xmin, xmax, ymin, ymax)
# x_center = (xmax+xmin)/2 y_center = (ymax+ymin)/2
# x = x_center / width y = y_center / height
# w = (xmax-xmin) / width h = (ymax-ymin) / height
x_center = (box[0] + box[1]) / 2.0
y_center = (box[2] + box[3]) / 2.0
x = x_center / size[0]
y = y_center / size[1]
w = (box[1] - box[0]) / size[0]
h = (box[3] - box[2]) / size[1]
# print(x, y, w, h)
return (x, y, w, h)
def convert_annotation(xml_files_path, save_txt_files_path, classes):
xml_files = os.listdir(xml_files_path)
# print(xml_files)
for xml_name in xml_files:
# print(xml_name)
xml_file = os.path.join(xml_files_path, xml_name)
out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
out_txt_f = open(out_txt_path, 'w')
tree = ET.parse(xml_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))
# b=(xmin, xmax, ymin, ymax)
# print(w, h, b)
bb = convert((w, h), b)
out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
if __name__ == "__main__":
# 把forklift_pallet的voc的xml标签文件转化为yolo的txt标签文件
# 1、需要转化的类别
classes = ['fish']
# 2、voc格式的xml标签文件路径
xml_files1 = r'D:\TestMain\yolov9-main\datasets\fish1\Annotations'
# 3、转化为yolo格式的txt标签文件存储路径
save_txt_files1 = r'D:\TestMain\yolov9-main\datasets\fish1\lables'
convert_annotation(xml_files1, save_txt_files1, classes)
5.数据划分问题
import os, shutil, random
from tqdm import tqdm
"""
标注文件是yolo格式（txt文件）
训练集：验证集：测试集 （7：2：1）
"""
def split_img(img_path, label_path, split_list):
try:
Data = 'D:/TestMain/yolov9-main/datasets/fish1/ImageSets'
# Data是你要将要创建的文件夹路径（路径一定是相对于你当前的这个脚本而言的）
# os.mkdir(Data)
train_img_dir = Data + '/images/train'
val_img_dir = Data + '/images/val'
test_img_dir = Data + '/images/test'
train_label_dir = Data + '/labels/train'
val_label_dir = Data + '/labels/val'
test_label_dir = Data + '/labels/test'
# 创建文件夹
os.makedirs(train_img_dir)
os.makedirs(train_label_dir)
os.makedirs(val_img_dir)
os.makedirs(val_label_dir)
os.makedirs(test_img_dir)
os.makedirs(test_label_dir)
except:
print('文件目录已存在')
train, val, test = split_list
all_img = os.listdir(img_path)
all_img_path = [os.path.join(img_path, img) for img in all_img]
# all_label = os.listdir(label_path)
# all_label_path = [os.path.join(label_path, label) for label in all_label]
train_img = random.sample(all_img_path, int(train * len(all_img_path)))
train_img_copy = [os.path.join(train_img_dir, img.split('\\')[-1]) for img in train_img]
train_label = [toLabelPath(img, label_path) for img in train_img]
train_label_copy = [os.path.join(train_label_dir, label.split('\\')[-1]) for label in train_label]
for i in tqdm(range(len(train_img)), desc='train ', ncols=80, unit='img'):
_copy(train_img[i], train_img_dir)
_copy(train_label[i], train_label_dir)
all_img_path.remove(train_img[i])
val_img = random.sample(all_img_path, int(val / (val + test) * len(all_img_path)))
val_label = [toLabelPath(img, label_path) for img in val_img]
for i in tqdm(range(len(val_img)), desc='val ', ncols=80, unit='img'):
_copy(val_img[i], val_img_dir)
_copy(val_label[i], val_label_dir)
all_img_path.remove(val_img[i])
test_img = all_img_path
test_label = [toLabelPath(img, label_path) for img in test_img]
for i in tqdm(range(len(test_img)), desc='test ', ncols=80, unit='img'):
_copy(test_img[i], test_img_dir)
_copy(test_label[i], test_label_dir)
def _copy(from_path, to_path):
shutil.copy(from_path, to_path)
def toLabelPath(img_path, label_path):
img = img_path.split('\\')[-1]
label = img.split('.jpg')[0] + '.txt'
return os.path.join(label_path, label)
if __name__ == '__main__':
img_path = 'D:\TestMain\yolov9-main\datasets\\fish1\images' # 你的图片存放的路径（路径一定是相对于你当前的这个脚本文件而言的）
label_path = 'D:\TestMain\yolov9-main\datasets\\fish1\lables' # 你的txt文件存放的路径（路径一定是相对于你当前的这个脚本文件而言的）
split_list = [0.7, 0.2, 0.1] # 数据集划分比例[train:val:test]
split_img(img_path, label_path, split_list)
6.数据自动标注问题
yolo辅助标注
设置save_txt为False表示不会将结果保存为.txt文件。这是一个布尔值。
存放位置在runs/detect/predict文件夹中
7.labelme和labelimg
labelimg结果为txt文件，且打开步骤为先打开输出文件，再打开图片
labelme结果为json文件，要进一步转为txt文件
1447
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
