今天寫代碼labelmetovoc，即將labelme標(biāo)注的轉(zhuǎn)化為voc標(biāo)準(zhǔn)格式參考的這篇文章時遇到了如下問題： ValueError: With n_samples=0, test_size=0.2 and train_size=None, the resulting train set will be empty. Adjust any of the aforementioned parameters. 在網(wǎng)上查了一下，大部分博客都認(rèn)為是scikit-learn版本較高時出現(xiàn)的問題,需要換到0.20.0以下版本，但是換的話numpy,scipy等庫均要重新下載兼容的版本，所以建議不要輕易嘗試，我請教了一下師兄，他說是因?yàn)閰?shù)上面參數(shù)設(shè)置出現(xiàn)了問題，train或test的數(shù)量必須為整數(shù)，改好的代碼如下所示：
# -*- coding: utf-8 -*-
"""
Created on Fri Apr 10 13:39:17 2020@author: nihao
"""
import os
import numpy as np
import codecs
import json
import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split# 1.標(biāo)簽路徑
labelme_path = "D:\\PinInspection\\jpgretanglelabel" # 原始labelme標(biāo)注數(shù)據(jù)路徑
saved_path = "D:\\PinInspection\\improveto300\\VOC2007" # 保存路徑# 2.創(chuàng)建要求文件夾
dst_annotation_dir = os.path.join(saved_path, 'Annotations')
if not os.path.exists(dst_annotation_dir):os.makedirs(dst_annotation_dir)
dst_image_dir = os.path.join(saved_path, "JPEGImages")
if not os.path.exists(dst_image_dir):os.makedirs(dst_image_dir)
dst_main_dir = os.path.join(saved_path, "ImageSets", "Main")
if not os.path.exists(dst_main_dir):os.makedirs(dst_main_dir)# 3.獲取待處理文件
org_json_files = sorted(glob.glob(os.path.join(labelme_path, '*.json')))
org_json_file_names = [i.split("\\")[-1].split(".json")[0] for i in org_json_files]
org_img_files = sorted(glob.glob(os.path.join(labelme_path, '*.jpg')))
org_img_file_names = [i.split("\\")[-1].split(".jpg")[0] for i in org_img_files]# 4.labelme file to voc dataset
for i, json_file_ in enumerate(org_json_files):json_file = json.load(open(json_file_, "r", encoding="utf-8"))image_path = os.path.join(labelme_path, org_json_file_names[i]+'.jpg')img = cv2.imread(image_path)height, width, channels = img.shapedst_image_path = os.path.join(dst_image_dir, "{:06d}.jpg".format(i))cv2.imwrite(dst_image_path, img)dst_annotation_path = os.path.join(dst_annotation_dir, '{:06d}.xml'.format(i))with codecs.open(dst_annotation_path, "w", "utf-8") as xml:xml.write('<annotation>\n')xml.write('\t<folder>' + 'Pin_detection' + '</folder>\n')xml.write('\t<filename>' + "{:06d}.jpg".format(i) + '</filename>\n')# xml.write('\t<source>\n')# xml.write('\t\t<database>The UAV autolanding</database>\n')# xml.write('\t\t<annotation>UAV AutoLanding</annotation>\n')# xml.write('\t\t<image>flickr</image>\n')# xml.write('\t\t<flickrid>NULL</flickrid>\n')# xml.write('\t</source>\n')# xml.write('\t<owner>\n')# xml.write('\t\t<flickrid>NULL</flickrid>\n')# xml.write('\t\t<name>ChaojieZhu</name>\n')# xml.write('\t</owner>\n')xml.write('\t<size>\n')xml.write('\t\t<width>' + str(width) + '</width>\n')xml.write('\t\t<height>' + str(height) + '</height>\n')xml.write('\t\t<depth>' + str(channels) + '</depth>\n')xml.write('\t</size>\n')xml.write('\t\t<segmented>0</segmented>\n')for multi in json_file["shapes"]:points = np.array(multi["points"])xmin = min(points[:, 0])xmax = max(points[:, 0])ymin = min(points[:, 1])ymax = max(points[:, 1])label = multi["label"]if xmax <= xmin:passelif ymax <= ymin:passelse:xml.write('\t<object>\n')xml.write('\t\t<name>' + label + '</name>\n')xml.write('\t\t<pose>Unspecified</pose>\n')xml.write('\t\t<truncated>1</truncated>\n')xml.write('\t\t<difficult>0</difficult>\n')xml.write('\t\t<bndbox>\n')xml.write('\t\t\t<xmin>' + str(xmin) + '</xmin>\n')xml.write('\t\t\t<ymin>' + str(ymin) + '</ymin>\n')xml.write('\t\t\t<xmax>' + str(xmax) + '</xmax>\n')xml.write('\t\t\t<ymax>' + str(ymax) + '</ymax>\n')xml.write('\t\t</bndbox>\n')xml.write('\t</object>\n')print(json_file_, xmin, ymin, xmax, ymax, label)xml.write('</annotation>')# 5.split files for txt
train_file = os.path.join(dst_main_dir, 'train.txt')
trainval_file = os.path.join(dst_main_dir, 'trainval.txt')
val_file = os.path.join(dst_main_dir, 'val.txt')
test_file = os.path.join(dst_main_dir, 'test.txt')ftrain = open(train_file, 'w')
ftrainval = open(trainval_file, 'w')
fval = open(val_file, 'w')
ftest = open(test_file, 'w')total_annotation_files = glob.glob(os.path.join(dst_annotation_dir, "*.xml"))
total_annotation_names = [i.split("\\")[-1].split(".xml")[0] for i in total_annotation_files]# test_filepath = ""
for file in total_annotation_names:ftrainval.writelines(file + '\n')
# test
# for file in os.listdir(test_filepath):
# ftest.write(file.split(".jpg")[0] + "\n")
# split
train_files, val_files = train_test_split(total_annotation_names, test_size=0.2)
# train
for file in train_files:ftrain.write(file + '\n')
# val
for file in val_files:fval.write(file + '\n')ftrainval.close()
ftrain.close()
fval.close()
# ftest.close()
