8-9(CCPD车牌数据集)

数据集中文件命名：
025-95_113-154&383_386&473-386&473_177&454_154&383_363&402-0_0_22_27_27_33_16-37-15.jpg".
则：（以‘-’分界）

025 车牌占全图面积比
95_113 水平倾斜度和垂直倾斜度
154&383 、386&473 LP左上顶点和右下顶点的坐标
386&473、177&454、154&383、363&402 右下、左下、左上、右上坐标
0、0、22_27_27_33_16-37-15 字符索引，分别对应下面三个数组

provinces = [“皖”, “沪”, “津”, “渝”, “冀”, “晋”, “蒙”, “辽”, “吉”, “黑”, “苏”, “浙”, “京”, “闽”, “赣”, “鲁”, “豫”, “鄂”, “湘”, “粤”, “桂”, “琼”, “川”, “贵”, “云”, “藏”, “陕”, “甘”, “青”, “宁”, “新”, “警”, “学”, “O”]
alphabets = [‘A’, ‘B’, ‘C’, ‘D’, ‘E’, ‘F’, ‘G’, ‘H’, ‘J’, ‘K’, ‘L’, ‘M’, ‘N’, ‘P’, ‘Q’, ‘R’, ‘S’, ‘T’, ‘U’, ‘V’, ‘W’,
‘X’, ‘Y’, ‘Z’, ‘O’]
ads = [‘A’, ‘B’, ‘C’, ‘D’, ‘E’, ‘F’, ‘G’, ‘H’, ‘J’, ‘K’, ‘L’, ‘M’, ‘N’, ‘P’, ‘Q’, ‘R’, ‘S’, ‘T’, ‘U’, ‘V’, ‘W’, ‘X’,
‘Y’, ‘Z’, ‘0’, ‘1’, ‘2’, ‘3’, ‘4’, ‘5’, ‘6’, ‘7’, ‘8’, ‘9’, ‘O’]

## Dataset AnnotationsAnnotations are embedded in file name.A sample image name is "025-95_113-154&383_386&473-386&473_177&454_154&383_363&402-0_0_22_27_27_33_16-37-15.jpg". Each name can be splited into seven fields. Those fields are explained as follows.- **Area**: Area ratio of license plate area to the entire picture area.- **Tilt degree**: Horizontal tilt degree and vertical tilt degree.- **Bounding box coordinates**: The coordinates of the left-up and the right-bottom vertices.- **Four vertices locations**: The exact (x, y) coordinates of the four vertices of LP in the whole image. These coordinates start from the right-bottom vertex.- **License plate number**: Each image in CCPD has only one LP. Each LP number is comprised of a Chinese character, a letter, and five letters or numbers. A valid Chinese license plate consists of seven characters: province (1 character), alphabets (1 character), alphabets+digits (5 characters). "0_0_22_27_27_33_16" is the index of each character. These three arrays are defined as follows. The last character of each array is letter O rather than a digit 0. We use O as a sign of "no character" because there is no O in Chinese license plate characters.
- provinces = ["皖", "沪", "津", "渝", "冀", "晋", "蒙", "辽", "吉", "黑", "苏", "浙", "京", "闽", "赣", "鲁", "豫", "鄂", "湘", "粤", "桂", "琼", "川", "贵", "云", "藏", "陕", "甘", "青", "宁", "新", "警", "学", "O"]
alphabets = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W','X', 'Y', 'Z', 'O']
ads = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X','Y', 'Z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'O']- **Brightness**: The brightness of the license plate region.- **Blurriness**: The Blurriness of the license plate region.

cuda 版本

nvcc -V

cudnn 版本

cat /usr/local/cuda/include/cudnn.h | grep CUDNN_MAJOR -A 2

官网https://pytorch.org/get-started/previous-versions/

Installing with CUDA 9
pip install torch==1.0.1 -f https://download.pytorch.org/whl/cu90/stable # CUDA 9.0 build

https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/linux-64/清华源，找适合的pytorch

cuda9.0:

sudo pip install -i https://pypi.tuna.tsinghua.edu.cn/simple torchvision

查看所装pytorch对应的cuda版本：

import torch
print(torch.version.cuda)
torch.cuda.is_available()

对于图片文件的信息提取：

provinces = ['皖', '沪', '津', '渝', '冀', '晋', '蒙', '辽', '吉', '黑', '苏', '浙', '京', '闽', '赣', '鲁', '豫', '鄂',
'湘', '粤', '桂', '琼', '川', '贵', '云', '藏', '陕', '甘', '青', '宁', '新', '警', '学', 'O']alphabets = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W',
'X', 'Y', 'Z', 'O']ads = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',
'Y', 'Z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'O']def STRcoordinates_deal(STRcoordinates,i):# STRcoordinates = STRcoordinates.split('_')result = STRcoordinates[i]x,y = int(result.split('&')[0]),int(result.split('&')[1])result = x,yreturn resultdef analyse_file(filename):STRinformation = filename.split('-')STRarea_ratio = STRinformation[0]STRangle = STRinformation[1]STRcoordinates = STRinformation[3]  #386&473_177&454_154&383_363&402 右下、左下、左上、右下STRchars = STRinformation[4]#坐标处理coordinates = []STRcoordinates = STRcoordinates.split('_')right_bottom = STRcoordinates_deal(STRcoordinates,0)left_top = STRcoordinates_deal(STRcoordinates,1)left_bottom = STRcoordinates_deal(STRcoordinates,2)right_top = STRcoordinates_deal(STRcoordinates,3)coordinates = [right_bottom,left_top,left_bottom,right_top]#车牌字符处理LPchars = []STRchars = STRchars.split('_')LPchars.append(provinces[int(STRchars[0])])LPchars.append(alphabets[int(STRchars[1])])for i in range(2,7):LPchars.append(ads[int(STRchars[i])])return coordinates,LPchars

8-9(CCPD车牌数据集)相关推荐

智能驾驶车牌检测和识别（一）《CCPD车牌数据集》
智能驾驶车牌检测和识别(一)<CCPD车牌数据集> 目录智能驾驶车牌检测和识别(一)<CCPD车牌数据集> 1. 前言 2.车牌号码说明 3.车牌数据集CCPD (1)车 ...
【项目三、车牌检测+识别项目】一、CCPD车牌数据集转为YOLOv5格式和LPRNet格式
目录前言一.CCPD数据集介绍二.CCPD数据集下载三.划分训练集.验证集和测试集四.车牌检测数据集制作五.车牌识别数据集制作六.我的车牌检测+识别数据集 Reference 前言马上 ...
[深度学习] CCPD车牌数据集介绍
CCPD是一个大型的.多样化的.经过仔细标注的中国城市车牌开源数据集.CCPD数据集主要分为CCPD2019数据集和CCPD2020(CCPD-Green)数据集.CCPD2019数据集车牌类型仅有普 ...
大型开源车牌数据集CCPD及私有车牌数据集介绍
转自:https://zhuanlan.zhihu.com/p/213780276?utm_source=wechat_session 一般常见的车牌数据集都是收集于交通监控系统.高速公路收费站和停车 ...
基于yolov3的目标检测与LPRnet字符识别的车牌识别（CCPD2020新能源车牌数据集）
文章目录前言一.程序思路二.使用步骤 1.配置环境 2.文件结构 3.准备数据集 4.训练有问题欢迎指正前言项目放这:车牌识别基于python和pytorch平台,使用CCPD2020新 ...
TensorFlow车牌识别完整版（含车牌数据集）
https://blog.csdn.net/ShadowN1ght/article/details/78571187 在之前发布的一篇博文<MNIST数据集实现车牌识别--初步演示版>中, ...
中科大开源车牌数据集CCPD 2019详细介绍
数据集能够应用到车牌检测以及识别任务中,总的图片数量能够达到300K张图片,可以从CCPD: Chinese City Parking Dataset下载. 数据集内部包含的文件夹以及内容如下表所示, ...
中文车牌数据集ccpd，标签处理
数据集介绍 CCPD数据集主要分为CCPD2019数据集和CCPD2020(CCPD-Green)数据集.CCPD2019数据集车牌类型仅有普通车牌(蓝色车牌),CCPD2020数据集车牌类型仅有新能 ...
CCPD数据集不限速夸克云盘下载车牌数据集 40G
原始公开数据中提供了谷歌云与百度网盘的链接,在此补充夸克云盘下载链接(不限速下载) 我用夸克网盘分享了「CCPD2019.tar」,点击链接即可保存.打开「夸克APP」链接:https://pan. ...

8-9(CCPD车牌数据集)

8-9(CCPD车牌数据集)相关推荐

最新文章

热门文章