1. 批处理将labelme标记完的json文件转为png图片
使用b导语义分割库里的代码批量处理json文件
import base64
import json
import os
import os.path as osp
import numpy as np
import PIL.Image
from labelme import utils
'''
制作自己的语义分割数据集需要注意以下几点:
1、我使用的labelme版本是3.16.7,建议使用该版本的labelme,有些版本的labelme会发生错误,
具体错误为:Too many dimensions: 3 > 2
安装方式为命令行pip install labelme==3.16.7
2、此处生成的标签图是8位彩色图,与视频中看起来的数据集格式不太一样。
虽然看起来是彩图,但事实上只有8位,此时每个像素点的值就是这个像素点所属的种类。
所以其实和视频中VOC数据集的格式一样。因此这样制作出来的数据集是可以正常使用的。也是正常的。
'''
if __name__ == '__main__':
jpgs_path = "datasets/JPEGImages"
pngs_path = "datasets/SegmentationClass"
classes = ["_background_","aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
count = os.listdir("./datasets/before/")
for i in range(0, len(count)):
path = os.path.join("./datasets/before", 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)
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')
文件格式为:此代码与datasets文件同目录,before内放原图和json文件,运行代码后另外两个文件夹内会输出处理后的图片
2. 裁剪为512*512大小
用cv2.imwrite会保存为24位的,很坑
# 将图片裁剪为512大小
import numpy as np
import os
from PIL import Image
base_dir = './SegmentationClass_Origin/' # 要裁剪的图片所在的文件夹
pic_target = './SegmentationClass/' # 分割后的图片保存的文件夹
if not os.path.exists(pic_target): #判断是否存在文件夹如果不存在则创建为文件夹
os.makedirs(pic_target)
imgs = os.listdir(base_dir) # 获取当前文件目录下所有文件的名称列表
index = 0
for img in imgs:
# if(index > 1):
# break
pic_path = base_dir + img # 分割的图片的位置
(pic_name, pic_PNGorJPG) = os.path.splitext(pic_path)
(a, pic_name) = os.path.split(pic_name)
image = Image.open(pic_path)
#要分割后的尺寸
cut_width = 512
cut_length = 512
width, length = image.size
# 计算可以划分的横纵的个数
num_width = int(width / cut_width)
num_length = int(length / cut_length)
for i in range(0, num_width):
for j in range(0, num_length):
new_image = image.crop((i*cut_width, j*cut_length, (i+1)*cut_width, (j+1)*cut_length))
result_path = pic_target + '{}_{}{}'.format(pic_name,i *num_length+j+ 1, pic_PNGorJPG)
new_image.save(result_path)
index = index + 1
print("已裁剪{}张图片".format(index))