解决问题四部曲：挑战、任务、对象、方法

正框光学目标检测（任务）

使用Python-Yolov5（方法）

一、观察标注格式（对象）

示例

0.txt

2 0.513333 0.493333 0.240000 0.653333

二、对数据及其标注进行可视化，便于观察分析（对象）

可视化时，需要对不同类别的目标用不同的颜色的框描绘，因此先要知晓总共都有几类，各类的序号分别是几。

统计类别序号的代码：

see_clsnum.py

import os.path as osp
import osBASEDIR = osp.dirname(osp.abspath(__file__))LABELDIR = osp.join(BASEDIR, 'labels')clsnums = set()for name in os.listdir(LABELDIR):path_txt = osp.join(LABELDIR, name)with open(path_txt, 'r') as fp:lines = fp.readlines()for line in lines:clsnum = line.split()[0]if clsnum not in clsnums:clsnums.add(clsnum)print(clsnums)

输出示例：

{'5', '9', '0', '2', '3', '6', '4', '8', '1', '7'}

可视化的代码：

watch_gtboxes.py
下面这段脚本可以直接运行。注意先按需求调整好 类别号-颜色 对应字典，并指定好源图片文件夹、标注文件夹、可视化输出文件夹的路径，再运行。

import cv2
import numpy as np
import os
import os.path as ospcolor_dict = {0: (255, 000, 000),1: (255, 128, 000),2: (255, 255, 000),3: (000, 255, 000),4: (000, 255, 255),5: (000, 000, 255),6: (128, 000, 255),7: (255, 000, 255),8: (128, 000, 000),9: (000, 128, 000),
}def run_watch_txts(img_dir, txt_dir, out_dir, color):IMAGEDIR = osp.abspath(img_dir)LABELDIR = osp.abspath(txt_dir)OUTDIR = osp.abspath(out_dir)if not os.path.exists(OUTDIR):os.makedirs(OUTDIR)png_names = set([name[:-4]for name in os.listdir(IMAGEDIR) if name.endswith('.jpg')])txt_names = set([name[:-4]for name in os.listdir(LABELDIR) if name.endswith('.txt')])intersection_names = png_names & txt_nameserrorimgs = []for name in png_names:image = cv2.imread(osp.join(IMAGEDIR, name+".jpg"))if name not in intersection_names:cv2.imwrite(osp.join(OUTDIR, name+".jpg"), image)continueprint('processing:', name)try:IMG_H, IMG_W, IMG_C = image.shapeexcept:errorimgs.append(name)continuewith open(osp.join(LABELDIR, name+".txt"), 'r') as fp:lines = fp.readlines()boxes = []for line in lines:line = line.strip().split()# print(line)label = int(line[0])cx = IMG_W * float(line[1])cy = IMG_H * float(line[2])w = IMG_W * float(line[3])h = IMG_H * float(line[4])# angle = int(line[5])rect = ((cx, cy), (w, h), 0)box = np.int0(cv2.boxPoints(rect))boxes.append(box)cv2.drawContours(image, boxes, -1, color_dict[label][::-1], 2)cv2.imwrite(osp.join(OUTDIR, name+".jpg"), image)print(name + ", done.")print(f"There are {len(errorimgs)} images failed to visualize, they are:\n{errorimgs}")if __name__ == '__main__':BASEDIR = osp.dirname(osp.abspath(__file__))img_dir = osp.join(BASEDIR, 'images')txt_dir = osp.join(BASEDIR, 'labels')out_dir = osp.join(BASEDIR, 'watch_gtboxes')run_watch_txts(img_dir, txt_dir, out_dir, color=(250, 200, 250))

等待片刻，从输出文件夹中收割可视化结果。

可视化效果图示例：

三、数据集 train val 划分

为数据集划分train，val。注意在yolov5架构下，希望按照如下目录进行组织：

objdet_data
|——images
|——|——train
|——|——val
|——labels
|————train
|————val

划分train-val的代码：

import os
import os.path as osp
import shutil
import random
import cv2BASEDIR = osp.dirname(osp.abspath(__file__))train_ratio = 0.9
random.seed(0)IMGDIR = osp.join(BASEDIR, 'images')
LABDIR = osp.join(BASEDIR, 'labels')imgnames = [name for name in os.listdir(IMGDIR) if name.endswith('.jpg')]
labnames = [name for name in os.listdir(LABDIR) if name.endswith('.txt')]
print(len(imgnames))
print(len(labnames))# create output dir
def mkdir_if_missing(OUTDIR):if not osp.exists(OUTDIR):os.makedirs(OUTDIR)OUTDIR = osp.join(BASEDIR, 'trainval')
OUT_IMG_TRAIN = osp.join(OUTDIR, 'images', 'train')
OUT_IMG_VAL = osp.join(OUTDIR, 'images', 'val')
OUT_LAB_TRAIN = osp.join(OUTDIR, 'labels', 'train')
OUT_LAB_VAL = osp.join(OUTDIR, 'labels', 'val')
for DIR in [OUT_IMG_TRAIN, OUT_IMG_VAL, OUT_LAB_TRAIN, OUT_LAB_VAL]:mkdir_if_missing(DIR)# filter available images
available_imgnames = []
for imgname in imgnames:path_img = osp.join(IMGDIR, imgname)img = cv2.imread(path_img)if img is None:continueelse:available_imgnames.append(imgname)print(len(available_imgnames))random.shuffle(available_imgnames)available_txtnames = [name.split('.')[0] + '.txt' for name in available_imgnames
]# available_imgnames.sort(key=lambda x: int(x.split('.')[0]))
# available_txtnames.sort(key=lambda x: int(x.split('.')[0]))thresh = int(len(available_imgnames) * train_ratio)for i, (imgname,txtname) in enumerate(zip(available_imgnames, available_txtnames)):if imgname.split('.')[0] != txtname.split('.')[0]:print('mismatch! ', imgname, 'VS', txtname)continueelse:src_img_path = osp.join(IMGDIR, imgname)src_lab_path = osp.join(LABDIR, txtname)if i < thresh:  # for traindst_img_path = osp.join(OUT_IMG_TRAIN, imgname)dst_lab_path = osp.join(OUT_LAB_TRAIN, txtname)else:  # for valdst_img_path = osp.join(OUT_IMG_VAL, imgname)dst_lab_path = osp.join(OUT_LAB_VAL, txtname)shutil.copy(src_img_path, dst_img_path)shutil.copy(src_lab_path, dst_lab_path)print(i, '/', thresh)

OK。。。

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！