YOLO 算法是十分驰名的指标检测算法。从其全称 You Only Look Once: Unified, Real-Time Object Detection ，能够看出它的个性：

  • Look Once: one-stage (one-shot object detectors) 算法，把指标检测的两个工作分类和定位一步实现。
  • Unified: 对立的架构，提供 end-to-end 的训练和预测。
  • Real-Time: 实时性，初代论文给出的指标 FPS 45 , mAP 63.4 。

YOLOv4: Optimal Speed and Accuracy of Object Detection ，于往年 4 月颁布，采纳了很多近些年 CNN 畛域优良的优化技巧。其均衡了精度与速度，目前在实时指标检测算法中精度是最高的。

论文地址：

  • YOLO: https://arxiv.org/abs/1506.02640
  • YOLO v4: https://arxiv.org/abs/2004.10934

源码地址：

  • YOLO: https://github.com/pjreddie/d...
  • YOLO v4: https://github.com/AlexeyAB/d...

本文将介绍 YOLOv4 官网 Darknet 实现，如何于 Docker 编译应用。以及从 MS COCO 2017 数据集中怎么选出局部物体，训练出模型。

次要内容有：

  • 筹备 Docker 镜像
  • 筹备 COCO 数据集
  • 用预训练模型进行推断
  • 筹备 COCO 数据子集
  • 训练本人的模型并推断
  • 参考内容

筹备 Docker 镜像

首先，筹备 Docker ，请见：Docker: Nvidia Driver, Nvidia Docker 举荐装置步骤 。

之后，开始筹备镜像，从下到上的层级为：

  • nvidia/cuda: https://hub.docker.com/r/nvid...
  • OpenCV: https://github.com/opencv/opencv
  • Darknet: https://github.com/AlexeyAB/d...

nvidia/cuda

筹备 Nvidia 根底 CUDA 镜像。这里咱们抉择 CUDA 10.2 ，不必最新 CUDA 11，因为当初 PyTorch 等都还都是 10.2 呢。

拉取镜像：

docker pull nvidia/cuda:10.2-cudnn7-devel-ubuntu18.04

测试镜像：

$ docker run --gpus all nvidia/cuda:10.2-cudnn7-devel-ubuntu18.04 nvidia-smiSun Aug 8 00:00:00 2020+-----------------------------------------------------------------------------+| NVIDIA-SMI 440.100 Driver Version: 440.100 CUDA Version: 10.2 ||-------------------------------+----------------------+----------------------+| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC || Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. ||===============================+======================+======================|| 0 GeForce RTX 208... Off | 00000000:07:00.0 On | N/A || 0% 48C P8 14W / 300W | 340MiB / 11016MiB | 2% Default |+-------------------------------+----------------------+----------------------+| 1 GeForce RTX 208... Off | 00000000:08:00.0 Off | N/A || 0% 45C P8 19W / 300W | 1MiB / 11019MiB | 0% Default |+-------------------------------+----------------------+----------------------++-----------------------------------------------------------------------------+| Processes: GPU Memory || GPU PID Type Process name Usage ||=============================================================================|+-----------------------------------------------------------------------------+

OpenCV

基于 nvidia/cuda 镜像，构建 OpenCV 的镜像：

cd docker/ubuntu18.04-cuda10.2/opencv4.4.0/docker build -t joinaero/ubuntu18.04-cuda10.2:opencv4.4.0 --build-arg opencv_ver=4.4.0 --build-arg opencv_url=https://gitee.com/cubone/opencv.git --build-arg opencv_contrib_url=https://gitee.com/cubone/opencv_contrib.git .

其 Dockerfile 可见这里： https://github.com/ikuokuo/st... 。

Darknet

基于 OpenCV 镜像，构建 Darknet 镜像：

cd docker/ubuntu18.04-cuda10.2/opencv4.4.0/darknet/docker build -t joinaero/ubuntu18.04-cuda10.2:opencv4.4.0-darknet .

其 Dockerfile 可见这里： https://github.com/ikuokuo/st... 。

上述镜像已上传 Docker Hub 。如果 Nvidia 驱动可能反对 CUDA 10.2 ，那能够间接拉取该镜像：

docker pull joinaero/ubuntu18.04-cuda10.2:opencv4.4.0-darknet

筹备 COCO 数据集

MS COCO 2017 下载地址: http://cocodataset.org/#download

图像，包含：

  • 2017 Train images [118K/18GB]

    • http://images.cocodataset.org...

  • 2017 Val images [5K/1GB]

    • http://images.cocodataset.org...

  • 2017 Test images [41K/6GB]

    • http://images.cocodataset.org...

  • 2017 Unlabeled images [123K/19GB]

    • http://images.cocodataset.org...

标注，包含：

  • 2017 Train/Val annotations [241MB]

    • http://images.cocodataset.org...

  • 2017 Stuff Train/Val annotations [1.1GB]

    • http://images.cocodataset.org...

  • 2017 Panoptic Train/Val annotations [821MB]

    • http://images.cocodataset.org...

  • 2017 Testing Image info [1MB]

    • http://images.cocodataset.org...

  • 2017 Unlabeled Image info [4MB]

    • http://images.cocodataset.org...

用预训练模型进行推断

预训练模型 yolov4.weights ，下载地址 https://github.com/AlexeyAB/d... 。

运行镜像：

xhost +local:dockerdocker run -it --gpus all -e DISPLAY -e QT_X11_NO_MITSHM=1 -v /tmp/.X11-unix:/tmp/.X11-unix -v $HOME/.Xauthority:/root/.Xauthority --name darknet --mount type=bind,source=$HOME/Codes/devel/datasets/coco2017,target=/home/coco2017 --mount type=bind,source=$HOME/Codes/devel/models/yolov4,target=/home/yolov4 joinaero/ubuntu18.04-cuda10.2:opencv4.4.0-darknet

进行推断：

./darknet detector test cfg/coco.data cfg/yolov4.cfg /home/yolov4/yolov4.weights -thresh 0.25 -ext_output -show -out /home/coco2017/result.json /home/coco2017/test2017/000000000001.jpg

推断后果：

筹备 COCO 数据子集

MS COCO 2017 数据集有 80 个物体标签。咱们从中选取本人关注的物体，重组个子数据集。

首先，获取样例代码：

git clone https://github.com/ikuokuo/start-yolov4.git
  • scripts/coco2yolo.py: COCO 数据集转 YOLO 数据集的脚本
  • scripts/coco/label.py: COCO 数据集的物体标签有哪些
  • cfg/coco/coco.names: 编辑咱们想要的那些物体标签

之后，筹备数据集：

cd start-yolov4/pip install -r scripts/requirements.txtexport COCO_DIR=$HOME/Codes/devel/datasets/coco2017# trainpython scripts/coco2yolo.py --coco_img_dir $COCO_DIR/train2017/ --coco_ann_file $COCO_DIR/annotations/instances_train2017.json --yolo_names_file ./cfg/coco/coco.names --output_dir ~/yolov4/coco2017/ --output_name train2017 --output_img_prefix /home/yolov4/coco2017/train2017/# validpython scripts/coco2yolo.py --coco_img_dir $COCO_DIR/val2017/ --coco_ann_file $COCO_DIR/annotations/instances_val2017.json --yolo_names_file ./cfg/coco/coco.names --output_dir ~/yolov4/coco2017/ --output_name val2017 --output_img_prefix /home/yolov4/coco2017/val2017/

数据集，内容如下：

~/yolov4/coco2017/├── train2017/│ ├── 000000000071.jpg│ ├── 000000000071.txt│ ├── ...│ ├── 000000581899.jpg│ └── 000000581899.txt├── train2017.txt├── val2017/│ ├── 000000001353.jpg│ ├── 000000001353.txt│ ├── ...│ ├── 000000579818.jpg│ └── 000000579818.txt└── val2017.txt

训练本人的模型并推断

筹备必要文件

  • cfg/coco/coco.names <cfg/coco/coco.names.bak has original 80 objects>

    • Edit: keep desired objects

  • cfg/coco/yolov4.cfg <cfg/coco/yolov4.cfg.bak is original file>

    • Download yolov4.cfg, then changed:
    • batch=64, subdivisions=32 <32 for 8-12 GB GPU-VRAM>
    • width=512, height=512 <any value multiple of 32>
    • classes=<your number of objects in each of 3 [yolo]-layers>
    • max_batches=<classes*2000, but not less than number of training images and not less than 6000>
    • steps=<max_batches0.8, max_batches0.9>
    • filters=<(classes+5)x3, in the 3 [convolutional] before each [yolo] layer>
    • <s>filters=<(classes+9)x3, in the 3 [convolutional] before each [Gaussian_yolo] layer></s>

  • cfg/coco/coco.data

    • Edit: train, valid to YOLO datas

  • csdarknet53-omega.conv.105

    • Download csdarknet53-omega_final.weights, then run:
docker run -it --rm --gpus all --mount type=bind,source=$HOME/Codes/devel/models/yolov4,target=/home/yolov4 joinaero/ubuntu18.04-cuda10.2:opencv4.4.0-darknet./darknet partial cfg/csdarknet53-omega.cfg /home/yolov4/csdarknet53-omega_final.weights /home/yolov4/csdarknet53-omega.conv.105 105

训练本人的模型

运行镜像：

cd start-yolov4/xhost +local:dockerdocker run -it --gpus all -e DISPLAY -e QT_X11_NO_MITSHM=1 -v /tmp/.X11-unix:/tmp/.X11-unix -v $HOME/.Xauthority:/root/.Xauthority --name darknet --mount type=bind,source=$HOME/Codes/devel/models/yolov4,target=/home/yolov4 --mount type=bind,source=$HOME/yolov4/coco2017,target=/home/yolov4/coco2017 --mount type=bind,source=$PWD/cfg/coco,target=/home/cfg joinaero/ubuntu18.04-cuda10.2:opencv4.4.0-darknet

进行训练：

mkdir -p /home/yolov4/coco2017/backup# Training command./darknet detector train /home/cfg/coco.data /home/cfg/yolov4.cfg /home/yolov4/csdarknet53-omega.conv.105 -map

中途能够中断训练，而后这样持续：

# Continue training./darknet detector train /home/cfg/coco.data /home/cfg/yolov4.cfg /home/yolov4/coco2017/backup/yolov4_last.weights -map

yolov4_last.weights 每迭代 100 次，会被记录。

如果多 GPU 训练，能够在 1000 次迭代后，加参数 -gpus 0,1 ，再持续：

# How to train with multi-GPU# 1. Train it first on 1 GPU for like 1000 iterations# 2. Then stop and by using partially-trained model `/backup/yolov4_1000.weights` run training with multigpu./darknet detector train /home/cfg/coco.data /home/cfg/yolov4.cfg /home/yolov4/coco2017/backup/yolov4_1000.weights -gpus 0,1 -map

训练过程，记录如下：

加参数 -map 后，上图会显示有红线 mAP。

查看模型 mAP@IoU=50 精度：

$ ./darknet detector map /home/cfg/coco.data /home/cfg/yolov4.cfg /home/yolov4/coco2017/backup/yolov4_final.weights...Loading weights from /home/yolov4/coco2017/backup/yolov4_final.weights...seen 64, trained: 384 K-images (6 Kilo-batches_64)Done! Loaded 162 layers from weights-file  calculation mAP (mean average precision)...Detection layer: 139 - type = 27Detection layer: 150 - type = 27Detection layer: 161 - type = 27160detections_count = 745, unique_truth_count = 190class_id = 0, name = train, ap = 80.61% (TP = 142, FP = 18)for conf_thresh = 0.25, precision = 0.89, recall = 0.75, F1-score = 0.81for conf_thresh = 0.25, TP = 142, FP = 18, FN = 48, average IoU = 75.31 %IoU threshold = 50 %, used Area-Under-Curve for each unique Recallmean average precision (mAP@0.50) = 0.806070, or 80.61 %Total Detection Time: 4 Seconds

进行推断：

./darknet detector test /home/cfg/coco.data /home/cfg/yolov4.cfg /home/yolov4/coco2017/backup/yolov4_final.weights -ext_output -show /home/yolov4/coco2017/val2017/000000006040.jpg

推断后果：

参考内容

  • Train Detector on MS COCO (trainvalno5k 2014) dataset-dataset)
  • How to evaluate accuracy and speed of YOLOv4
  • How to train (to detect your custom objects)

结语

为什么用 Docker ？ Docker 导出镜像，可简化环境部署。如 PyTorch 也都有镜像，能够间接上手应用。

对于 Darknet 还有什么？ 下回介绍 Darknet 于 Ubuntu 编译，及应用 Python 接口 。

Let's go coding ~