YOLOX系列三

图片标签显示中文

---

---

前言

实际项目应用中，图片的标签还是以显示中文为主，本文主要内容就是对YOLOX进行修改来进行标签中文显示。

一、类别标签中文设置

首先将类别便签修改为中文。
文件名称为YOLOX-main\tools\yolox\data\datasets\coco_classes.py。
将其中的COCO_CLASSES的标签修改为对应的中文，如下所示。
（摊牌了，我懒了，没有全部修改…）

COCO_CLASSES = ("人","自行车","汽车","motorcycle","飞机","公共汽车","火车","货车","船","交通信号灯","fire hydrant","停止标志","parking meter","bench","鸟","猫","狗","马","羊","奶牛","大象","熊","zebra","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite","baseball bat","baseball glove","skateboard","surfboard","tennis racket","瓶子","wine glass","cup","fork","knife","spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","热狗","披萨","donut","cake","chair","couch","potted plant","bed","dining table","toilet","tv","laptop","mouse","remote","keyboard","cell phone","microwave","oven","toaster","sink","refrigerator","book","clock","vase","scissors","teddy bear","hair drier","toothbrush",
)

二、字体设置

首先进行汉字字体设置，将需要的汉字字体格式放到目录中，我放到了与tools目录下。

linux 字体*.TTC的存放路径一般是： /usr/share/fonts/opentype/noto/
查找指令locate *.ttc (应该是，好久没用Linux了)
windows 字体 *.TTF 存放路径： C:\Windows\Fonts
查找命令 win+R+fonts

三、代码修改

最后一步就是对项目代码进行修改。
首先安装pillow依赖包（有的话就算了）。pip install pillow
修改文件tools\yolox\utils\visualize.py。将vis()函数修改如下所示：

import cv2
import numpy
import numpy as np
from PIL import Image, ImageDraw, ImageFont__all__ = ["vis"]def vis(img, boxes, scores, cls_ids, conf=0.5, class_names=None):for i in range(len(boxes)):                                                          # 遍历检测结果box = boxes[i]cls_id = int(cls_ids[i])score = scores[i]if score < conf:continuex0 = int(box[0])y0 = int(box[1])x1 = int(box[2])y1 = int(box[3])color = (_COLORS[cls_id] * 255).astype(np.uint8).tolist()                            # 框颜色设置text = '{}:{:.1f}%'.format(class_names[cls_id], score * 100)                         # 文本格式txt_color = (0, 0, 0) if np.mean(_COLORS[cls_id]) > 0.5 else (255, 255, 255)         # 文本颜色设置font = cv2.FONT_HERSHEY_SIMPLEX                                                      # 字体格式txt_size = cv2.getTextSize(text, font, 0.4, 1)[0]cv2.rectangle(img, (x0, y0), (x1, y1), color, 2)                                     # 画框txt_bk_color = (_COLORS[cls_id] * 255 * 0.7).astype(np.uint8).tolist()cv2.rectangle(img,(x0, y0 + 1),(x0 + txt_size[0] + 1, y0 + int(1.5*txt_size[1])),txt_bk_color,-1)# 打印汉字img_pil = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))# 字体  linux 字体*.ttc的存放路径一般是： /usr/share/fonts/opentype/noto/ 查找指令locate *.ttc#      win    win+R+fonts  C:\Windows\Fontsfont = ImageFont.truetype('STFANGSO.TTF', 10, encoding="utf-8")draw = ImageDraw.Draw(img_pil)draw.text((x0, y0), text, txt_color, font=font)# 转换回OpenCV格式img = cv2.cvtColor(numpy.asarray(img_pil), cv2.COLOR_RGB2BGR)# cv2.putText(img, text, (x0, y0 + txt_size[1]), font, 0.4, txt_color, thickness=1)    # 图片上打印文字return img

接下来测试一下效果。

效果还不错。

---

总结

本文主要内容就是将YOLOX项目的图片标签进行中文显示。
若发现文章有误，欢迎指出。
各位老铁点点关注点点赞啊