labelImg
首先安装labelImg
在Ancconda环境中pip install labelImg即可
然后直接在conda环境中运行labelImg即可打开软件、
软件非常好操作，选择你要打开的文件夹（未标记数据放在这里）
然后选择你要保存的路径
下面创建一个标注框。
创建一个标注框
自己起一个类名，后面就会自动显示
标好了点击save保存
如果需要大量标注数据，那用快捷键很方便。
按W就可以创建一个新的框，A是往前一张图，D是往后一张图。Ctrl+s是保存。
yolov5
以yolov为例（这里我用的是yolov5），为其标注VOC格式的数据集。
使用labelimg 标记数据集
labelimg
标注好了之后，放入两个文件夹下：
文件结构如下：
--VOCdevkit
----VOC2007
------Annotations # 这里面放标注的xml文件
------JPEGImages # 这里面放原图片
准备好test.py
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 = ["person"]
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('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id)
out_file = open('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, "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()
将test.py和VOCdevkit放在统计文件夹下
运行test.py
结果如下：
在VOCdevkit目录下生成images和labels文件夹，文件夹下分别生成了train文件夹和val文件夹，里面分别保存着训练集的照片和txt格式的标签，还有验证集的照片和txt格式的标签。images文件夹和labels文件夹就是训练yolov5模型所需的训练集和验证集。在VOCdevkit/VOC2007目录下还生成了一个YOLOLabels文件夹，里面存放着所有的txt格式的标签文件。
到此，xml格式的标签文件转换为txt格式的标签文件并划分为训练集和测试集就做完了。
准备训练
然后，在yolo源码下面data文件夹下，有一个VOC.yaml，把这个文件复制到VOCdevkit下
修改这个文件中的路径和类别
path: ./VOCdevkit #从根目录开始写
train:
- images/train/ # train images (relative to 'path')
val:
- images/val/ # val images (relative to 'path')
nc:1 # number of classes
names:['person'] # class name
然后找到yolo的train.py文件，找到main，注意下面这几行
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='models/yolov5s.yaml', help='model.ya ml path')
parser.add_argument('--data', type=str, default='VoCdevkit/VOC.yaml', help='data.yaml path')
如果你用的是yolov5s.yaml，那么你要去models文件夹下，找到yolov5s.yaml文件，把里面的nc: 5改成你的类别数
开始训练
然后运行train.py开始训练
labelme
这个用来标注语义分割的数据集。
安装方法一样
在Ancconda环境中pip install labelme即可
然后直接在conda环境中运行labelme即可打开软件
使用方法很简单，一目了然
打开文件，标注，保存save
标注的时候必须首尾相连
圈出来之后给他起个类名，不同的类会有不同的颜色
在右边会显示，这是红色
标注好了之后保存下来的是json文件
这个文件有多种打开方式。下面以PFNet训练为例
PFNet训练
标注好的jpg文件和json文件
还需要用一个程序json_to_dataset.py
代码如下：也很好看懂，改一下路径即可
import base64
import json
import os
import os.path as osp
import numpy as np
import PIL.Image
from labelme import utils
if __name__ == '__main__':
jpgs_path = r"E:\video\pic\test_jpg" # 标注的图像路径
pngs_path = r"E:\video\pic\test_json" # json文件存放路径
classes = ["_background_", "vibrating tube"] # 标注的类别 第一个是背景不用改
# classes = ["_background_", "per"]
# classes = ["_background_","cat","dog"]
count = os.listdir(pngs_path)
for i in range(0, len(count)):
path = os.path.join(pngs_path, count[i])
if os.path.isfile(path) and path.endswith('json'):
data = json.load(open(path))
if data['imageData']:
imageData = data['imageData']
else:
imagePath = os.path.join(os.path.dirname(path), data['imagePath'])
with open(imagePath, 'rb') as f:
imageData = f.read()
imageData = base64.b64encode(imageData).decode('utf-8')
img = utils.img_b64_to_arr(imageData)
label_name_to_value = {'_background_': 0}
for shape in data['shapes']:
label_name = shape['label']
if label_name in label_name_to_value:
label_value = label_name_to_value[label_name]
else:
label_value = len(label_name_to_value)
label_name_to_value[label_name] = label_value
# label_values must be dense
label_values, label_names = [], []
for ln, lv in sorted(label_name_to_value.items(), key=lambda x: x[1]):
label_values.append(lv)
label_names.append(ln)
assert label_values == list(range(len(label_values)))
lbl = utils.shapes_to_label(img.shape, data['shapes'], label_name_to_value)[0]
# PIL.Image.fromarray(img).save(osp.join(jpgs_path, count[i].split(".")[0]+'.jpg'))
new = np.zeros([np.shape(img)[0],np.shape(img)[1]])
for name in label_names:
index_json = label_names.index(name)
index_all = classes.index(name)
new = new + index_all*(np.array(lbl) == index_json)
# utils.lblsave(osp.join(pngs_path, count[i].split(".")[0]+'.png'), new)
# print('Saved ' + count[i].split(".")[0] + '.jpg and ' + count[i].split(".")[0] + '.png')
utils.lblsave(osp.join(pngs_path, count[i] + '.png'), new)
print('Saved ' + count[i] + '.jpg and ' + count[i] + '.png')
用这个程序处理json文件，处理完了之后会在json的文件夹下生成这样的图像
这就是标注的物体
把原图和最后生成的这个.json.png图像名字对应好
就可以拿去训练了
3300
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
