接上篇,讲到如何从mask转成YOLOv5训练需要的txt数据集格式,这篇就在此基础上进行模型训练预测和部署转换吧!
目录
1.环境准备
2.YOLO训练
2.1 数据集准备
2.2 data.yaml准备
2.3 yolov5.yaml准备
2.4 训练命令
3.YOLO预测
3.1OLOv5 PyTorch Hub 预测
3.2代码预测
4.torch2onnx模型部署转换
5.onnx模型推理预测
6.onnx模型运行验证
数据集制作快速通道:YOLO格式数据集制作
1.环境准备
环境版本要求:python>=3.7
pytorch>=1.7
其他需要的安装包可以直接用requirements.txt下载安装
git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt # install
2.YOLO训练
2.1 数据集准备
rootpath
--images
--1.png
--2.png
...
--labels
--1.txt
--2.txt
...
images就不用多说了,里面就是存放原始训练影像,格式必须为png或者jpg;
labels里可以有两种格式.
- 如果是目标检测任务,那毋庸置疑就是标准yolo目标检测格式label了,一共5列,第1列存放每个目标的类别,第2-5列分别存放中心点坐标和宽度高度(center_x,center_y,wid ,hig)
注意:坐标点位置要归一化到(0-1)之间,也就是像素坐标分别除以宽度和高度。即
#center_x_pixl,center_y_pixl,width_pixl,higth_pixl表示中心点像素坐标和bbox的宽度和高度
#center_x,center_y,wid,hig表示归一化后的坐标,即txt里写的内容
#width,higth表示原始影像的宽度和高度
center_x = center_x_pixl / width
wid = width_pixl / width
center_y = center_y_pixl / higth
hig = higth_pixl / higth
- 如果是语义分割任务,与目标检测相同的是第1列仍然存放每个目标的类别,不同的是后面所有列分别存放每个边界点的坐标(center_x1,center_y1, center_x2,center_y2, ......, center_xn,center_yn),表示这些点组成了一个多边形目标。注意此时的边界点坐标也是归一化后的,归一化方法与目标检测方法一致。
2.2 data.yaml准备
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco128 # dataset root dir
train: images/train2017 # train images (relative to 'path') 128 images
val: images/train2017 # val images (relative to 'path') 128 images
test: # test images (optional)
# Classes (80 COCO classes)
names:
0: person
1: bicycle
2: car
...
77: teddy bear
78: hair drier
79: toothbrush
path:数据地址
train:训练数据文件夹名称
val:验证数据文件夹名称
names:类别名称对应,得从0开始
2.3 yolov5.yaml准备
以yolov5s为例,其实要改的就是一个numclass
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
nc改为自己的类别总数就可以了,其他不用动 ,0也算一类哦,比如类别是0,1,那nc就是2。
2.4 训练命令
- 单GPU训练
python train.py --batch 64 --data coco.yaml --weights yolov5s.pt --device 0
- 多GPU训练
python -m torch.distributed.run --nproc_per_node 2 train.py --batch 64 --data coco.yaml --weights yolov5s.pt --device 0,1
训练结果在run/train/目录下生成exp文件夹,若参数不变,会保留多个exp,不会覆盖。
3.YOLO预测
推理过程可以用两种方式,一种是用pytorch hub工具预测,一种是代码行预测
3.1OLOv5 PyTorch Hub 预测
import torch
# Model
model = torch.hub.load("ultralytics/yolov5", "yolov5s") # or yolov5n - yolov5x6, custom
# Images
img = "https://ultralytics.com/images/zidane.jpg" # or file, Path, PIL, OpenCV, numpy, list
# Inference
results = model(img)
# Results
results.print() # or .show(), .save(), .crop(), .pandas(), etc.
3.2代码预测
python detect.py --weights yolov5s.pt --source 0 # webcam
img.jpg # image
vid.mp4 # video
screen # screenshot
path/ # directory
list.txt # list of images
list.streams # list of streams
'path/*.jpg' # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
结果自动保存在runs/detect目录下
4.torch2onnx模型部署转换
把自己训练好的模型导出成onnx格式,方便部署
python export.py --weights yolov5s.pt --include torchscript onnx
注意:可以增加参数--half ,以达到半精度带出的目的,这样导出的文件比较小。
5.onnx模型推理预测
python detect.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s_openvino_model # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (macOS only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
yolov5s_paddle_model # PaddlePaddle
6.onnx模型运行验证
python val.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s_openvino_model # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (macOS Only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
yolov5s_paddle_model # PaddlePaddle