作为刚入门的小白，能实践成功有点小激动。在次记录过程。

预测效果

实现

1、进入https://aistudio.baidu.com/创建自己的项目，并选择安全帽数据集

2、开发步骤

# 解压数据
!unzip data/data50329/HelmetDetection.zip

#  重命名images文件夹名称 并移动到新目录
!mv images mydata/mydata/JPEGImages

#  重命名annotations文件夹名称 并移动到新目录
!mv annotations mydata/mydata/Annotations

# 下载PaddleDetection代码
!git clone https://gitee.com/paddlepaddle/PaddleDetection

Cloning into 'PaddleDetection'...
remote: Enumerating objects: 21396, done.[K
remote: Counting objects: 100% (1866/1866), done.[K
remote: Compressing objects: 100% (934/934), done.[K
remote: Total 21396 (delta 1314), reused 1300 (delta 929), pack-reused 19530[K
Receiving objects: 100% (21396/21396), 202.22 MiB | 6.68 MiB/s, done.
Resolving deltas: 100% (15863/15863), done.
Checking connectivity... done.

# 下载依赖
!pip install -r PaddleDetection/requirements.txt

# 更换当前路径
cd PaddleDetection

/home/aistudio/PaddleDetection

# 编译安装paddledet
!python setup.py install

#  安装paddlex:为了方便切分数据集
!pip install paddlex

#  返回主目录
cd

# 切分数据集
!paddlex --split_dataset --format VOC --dataset_dir data/mydata --val_value 0.2 --test_value 0.1

#  查看gpu版本号
!cat /usr/local/cuda/version.txt

#  下载对应的版本
!python -m pip install paddlepaddle-gpu==2.2.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Looking in links: https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html
Requirement already satisfied: paddlepaddle-gpu==2.2.2.post101 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (2.2.2.post101)
Requirement already satisfied: Pillow in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (8.2.0)
Requirement already satisfied: numpy>=1.13 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (1.19.5)
Requirement already satisfied: six in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (1.16.0)
Requirement already satisfied: requests>=2.20.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (2.24.0)
Requirement already satisfied: protobuf>=3.1.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (3.14.0)
Requirement already satisfied: astor in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (0.8.1)
Requirement already satisfied: decorator in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlepaddle-gpu==2.2.2.post101) (4.4.2)
Requirement already satisfied: idna<3,>=2.5 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20.0->paddlepaddle-gpu==2.2.2.post101) (2.8)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20.0->paddlepaddle-gpu==2.2.2.post101) (2019.9.11)
Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20.0->paddlepaddle-gpu==2.2.2.post101) (3.0.4)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests>=2.20.0->paddlepaddle-gpu==2.2.2.post101) (1.25.6)
[33mWARNING: You are using pip version 21.3.1; however, version 22.0.3 is available.
You should consider upgrading via the '/opt/conda/envs/python35-paddle120-env/bin/python -m pip install --upgrade pip' command.[0m

更新 PaddleDetection/configs/datasets/voc.yml 文件

#  训练数据
!export CUDA_VISIBLE_DEVICES=0,1,2,3
!python  PaddleDetection/tools/train.py -c PaddleDetection/configs/yolov3/yolov3_darknet53_270e_voc.yml

#  模型导出
!python PaddleDetection/tools/export_model.py -c PaddleDetection/configs/yolov3/yolov3_darknet53_270e_voc.yml --output_dir=./inference_model -o weights=output/yolov3_darknet53_270e_voc/164.pdparams

#  图片预测
!python PaddleDetection/deploy/python/infer.py --model_dir=inference_model/yolov3_darknet53_270e_voc --image_file=mydata/VID_20200310_174419_15.jpg --device=GPU

-----------  Running Arguments -----------
batch_size: 1
camera_id: -1
cpu_threads: 1
device: GPU
enable_mkldnn: False
image_dir: None
image_file: mydata/VID_20200310_174419_15.jpg
model_dir: inference_model/yolov3_darknet53_270e_voc
output_dir: output
reid_batch_size: 50
reid_model_dir: None
run_benchmark: False
run_mode: paddle
save_images: False
save_mot_txt_per_img: False
save_mot_txts: False
scaled: False
threshold: 0.5
trt_calib_mode: False
trt_max_shape: 1280
trt_min_shape: 1
trt_opt_shape: 640
use_dark: True
use_gpu: False
video_file: None
------------------------------------------
-----------  Model Configuration -----------
Model Arch: YOLO
Transform Order:
--transform op: Resize
--transform op: NormalizeImage
--transform op: Permute
--------------------------------------------
class_id:1, confidence:0.9309, left_top:[750.12,270.37],right_bottom:[799.00,342.68]
class_id:1, confidence:0.8036, left_top:[736.21,337.55],right_bottom:[794.07,406.86]
save result to: output/VID_20200310_174419_15.jpg
------------------ Inference Time Info ----------------------
total_time(ms): 2824.7, img_num: 1
average latency time(ms): 2824.70, QPS: 0.354020
preprocess_time(ms): 2805.50, inference_time(ms): 19.20, postprocess_time(ms): 0.00

#  视频预测
!python PaddleDetection/deploy/python/infer.py --model_dir=inference_model/yolov3_darknet53_270e_voc --video_file=mydata/test.avi --device=GPU

部署模型

最后出来的成果
https://download.csdn.net/download/u010568976/81300268

项目路径

补充：
pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox
pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

PaddleDetection安全帽检测相关推荐

基于YOLOv5的智慧工地安全帽检测（1）
基于YOLOv5的智慧工地安全帽检测数据集+代码下载地址:下载地址
基于YOLOv5的智慧工地实现---安全帽检测（2）
基于YOLOv5的智慧工地安全帽检测代码下载地址:下载地址 Smart_Construction 该项目是使用 YOLOv5 v2.x 的程序来训练在智能工地安全领域中头盔目标检测的应用指标 yo ...
智慧工地-基于深度学习yolov3的安全帽检测以及安全帽检测数据集（1）
基于深度学习yolov3的安全帽检测以及安全帽检测数据集数据集和代码下载地址:下载地址数据可视化: 根目录下运行命令: show_yolo_anno.py (注意脚本内相关参数配置 ) 模型训练 ...
微调Faster-R-CNN-InceptionV2完成高准确率安全帽检测任务
个人简介:李响Superb,CSDN百万访问量博主,普普通通男大学生,深度学习算法.医学图像处理专攻,偶尔也搞全栈开发,没事就写文章. 博客地址:lixiang.blog.csdn.net 本文版权归 ...
飞桨PaddlePaddle升级解读 | PaddleDetection物体检测统一框架
目标检测是机器视觉领域的核心问题之一.7 月 3 日百度 AI 开发者大会,飞桨核心框架 Paddle Fluid v1.5 宣布开源了 PaddleDetection 物体检测统一框架,用户可以非常 ...
调用远程摄像头进行人脸识别_工地安全：AI如何实现安全帽检测与人脸识别？...
安全生产一直是施工生产中很重要的一部分,只有保障了员工的安全,才能保证企业的利益.安全帽作为保护.防护的重要防范手段,一直是各大企业要求员工佩戴的,可还是发生了各种由于未佩戴安全帽导致的安全事故. 通 ...
texstudio自动拼写检测_飞桨PaddleDetection物体检测统一框架详解
目标检测是机器视觉领域的核心问题之一.7 月 3 日百度 AI 开发者大会,飞桨核心框架 Paddle Fluid v1.5 宣布开源了 PaddleDetection 物体检测统一框架,用户可以非常 ...
基于YOLOV3的安全帽检测
" 作为目标检测的鸿篇巨制YOLOV3,用来做安全帽检测非常合适" 01 - Yolov3简介 Yolo_v3使用了darknet-53的前面的52层(没有全连接层),yolo_v ...
【深度学习】搭建人工智能服务网站（安全帽检测）
电力图像分类最典型的场景就是安全帽佩戴识别. 针对电网作业现场人员行为的图像数据,采用目标检测.图像识别等人工智能技术,对电网作业现场人员是否规范佩戴安全帽进行检测识别.通过计算平均精确率.漏检率.误 ...

PaddleDetection安全帽检测

预测效果

实现

1、进入https://aistudio.baidu.com/创建自己的项目，并选择安全帽数据集

2、开发步骤

部署模型

PaddleDetection安全帽检测相关推荐

最新文章

热门文章