记录：百度3天AI进阶实战营——车牌识别

Day0

**step1:**进入BML主页，点击立即使用

https://ai.baidu.com/bml/

**step2:**点击Notebook，创建“通用任务”

**step3:**填写任务信息

Day01

​第一步：配置Notebook​

1.找到昨天创建的Notebook任务，点击配置

• 开发语言：Python3.7
• AI框架：PaddlePaddle2.0.0
• 资源规格：GPU V100

**

**

2.打开Notebook

3.创建一个Notebook，选择Python3

​第二步：上传数据集至Notebook​

1.下载数据集至本地

https://aistudio.baidu.com/aistudio/datasetdetail/123686

2.上传数据集至Notebook并解压

!unzip -q /home/work/chepaishibie.zip

3.生成标签文档

• 本次使用的数据集为CCPD2019车牌数据集
• 该数据集在合肥市的停车场采集得来，采集时间早上7:30到晚上10:00。停车场采集人员手持Android POS机对停车场的车辆拍照并手工标注车牌位置。拍摄的车牌照片涉及多种复杂环境，包括模糊、倾斜、阴雨天、雪天等等。CCPD数据集一共包含将近30万张图片，每种图片大小720x1160x3。一共包含8项，具体如下：

• CCPD数据集没有专门的标注文件，每张图像的文件名就是对应的数据标注(label)

• 例如: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 由分隔符’-'分为几个部分:

1. 025为区域
2. 95_113 对应两个角度, 水平95°, 竖直113°
3. 154&383_386&473对应边界框坐标:左上(154, 383), 右下(386, 473)
4. 386&473_177&454_154&383_363&402对应四个角点坐标
5. 0_0_22_27_27_33_16为车牌号码 映射关系如下: 第一个为省份0 对应省份字典皖, 后面的为字母和文字, 查看ads字典.如0为A, 22为Y…

• 仅使用到数据集中正常车牌即ccpd_base的数据

import os, cv2
import random
words_list = [
    "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" ]

con_list = [
    "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",
    "西", "陕", "甘", "青", "宁",
    "新"]

count = 0
total = []
paths = os.listdir('/home/work/chepaishibie')#真实数据集路径
#for path in paths:
for item in os.listdir(os.path.join('/home/work/chepaishibie')):#真实数据集路径
    if item[-3:] =='jpg':
        new_path = os.path.join('/home/work/chepaishibie', item) #训练图片路径的路径
        _, _, bbox, points, label, _, _ = item.split('-')
        points = points.split('_')
        points = [_.split('&') for _ in points]
        tmp = points[-2:]+points[:2]
        points = []
        for point in tmp:
            points.append([int(_) for _ in point])
        label = label.split('_')
        con = con_list[int(label[0])]
        words = [words_list[int(_)] for _ in label[1:]]
        label = con+''.join(words)
        line = new_path+'\t'+'[{"transcription": "%s", "points": %s}]' % (' ', str(points))
        line = line[:]+'\n'
        total.append(line)

random.shuffle(total)

with open('/home/work/data/train.txt', 'w', encoding='UTF-8') as f:
    for line in total[:-200]:
        f.write(line)

with open('/home/work/data/dev.txt', 'w', encoding='UTF-8') as f:
    for line in total[-200:]:
        f.write(line)

检查data下的两个txt文件

​第三步：配置环境​

1.升级PaddlePaddle

!pip install paddlepaddle-gpu==2.2.1.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html

2.下载PaddleOCR

!git clone https://gitee.com/PaddlePaddle/PaddleOCR.git

3.下载预训练模型

cd /home/work/PaddleOCR

!wget -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db.tar!wget -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_attn.tar

cd pretrain_models

!tar -xf ch_det_mv3_db.tar && rm -rf ch_det_mv3_db.tar!tar -xf rec_mv3_tps_bilstm_attn.tar && rm -rf rec_mv3_tps_bilstm_attn.tar

​第四步：保存Notebook并关闭、停止运行​

Day02

​第一步：重新安装环境​

1.启动Notebook并打开

2.重新执行以下安装命令

​第二步：安装PaddleOCR相关依赖文件​

1.修改requirements文件

删除opencv-contrib-python==4.4.0.46

2.执行以下两个安装命令

cd /home/work/PaddleOCR

!pip install -r requirements.txt

!pip install opencv-contrib-python==4.2.0.32

​第三步：修改模型训练的yml文件​

进入路径PaddleOCR/configs/det/

打开det_mv3_db.yml

1.修改模型路径和保存路径

2.修改训练数据的路径

训练集：

验证集：

3.设置训练参数

epoch数：

batch_size：

​第四步：模型训练​

CUDA_VISIBLE_DEVICES=0!python3 tools/train.py -c configs/det/det_mv3_db.yml

​第五步：保存Notebook并关闭、停止运行​

Day03

​第一步：重新安装环境​

1.启动Notebook并打开

2.重新执行以下安装命令

升级PaddlePaddle

安装相关依赖

​第二步：导出文字检测模型​

!python3 /home/work/PaddleOCR/tools/export_model.py \        -c /home/work/PaddleOCR/configs/det/det_mv3_db.yml \        -o Global.checkpoints=/home/work/PaddleOCR/output/db_mv3/best_accuracy \        Global.save_inference_dir=/home/work/PaddleOCR/inference/

​第三步：下载安装文字识别模型​

!wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar!tar -xf ch_ppocr_server_v2.0_rec_infer.tar -C inference

​第四步：模型预测​

1.上传一张车牌图片作为预测图片

上传至home/work根目录，命名为test.jpg

2.执行预测命令

!python /home/work/PaddleOCR/tools/infer/predict_system.py \
--image_dir="/home/work/test.jpg" \    --det_model_dir="/home/work/PaddleOCR/inference/" \    --rec_model_dir="/home/work/PaddleOCR/inference/ch_ppocr_server_v2.0_rec_infer/" \    --use_gpu False