Training Yolo v4 (and v3)

最新推荐文章于 2024-06-28 11:32:29 发布

原创最新推荐文章于 2024-06-28 11:32:29 发布 · 814 阅读

1 ·

CC 4.0 BY-SA版权

yolo系列专栏收录该内容

11 篇文章

订阅专栏

本文详细介绍了如何使用YOLOv4进行自定义对象检测，包括下载预训练权重文件、创建配置文件、调整参数如batch大小、max_batches等，以及如何准备训练数据集。还提供了不同模型的预训练权重下载链接。

How to train (to detect your custom objects):

下载 pre-trained weights-file (162 MB): yolov4.conv.137 (Google drive mirror yolov4.conv.137 )
Create file yolo-obj.cfg with the same content as in yolov4-custom.cfg
修改 batch=64 subdivisions=16
修改 max_batches（max_batches = classes*2000，但不小于training images数量且不小于6000）例如，如果您训练3个class，max_batches=6000）
change line steps to 80% and 90% of max_batches, f.e. steps=4800,5400
change [filters=255] to filters=(classes + 5)x3 in the 3 [convolutional] before each [yolo] layer, keep in mind that it only has to be the last [convolutional] before each of the [yolo] layers.
.txt file for each .jpg

Where:

<object-class> - integer object number from 0 to (classes-1) 类别0 to class-1
<x_center> <y_center> <width> <height> - float values relative to width and height of image, it can be equal from (0.0 to 1.0]
for example: <x> = <absolute_x> / <image_width> or <height> = <absolute_height> / <image_height>
atention: <x_center> <y_center> - are center of rectangle (are not top-left corner)

For example for img1.jpg you will be created img1.txt containing:

1 0.716797 0.395833 0.216406 0.147222
0 0.687109 0.379167 0.255469 0.158333
1 0.420312 0.395833 0.140625 0.166667

For training with mAP (mean average precisions) calculation for each 4 Epochs (set valid=valid.txt or train.txt in obj.data file) and run: darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -map

Download pre-trained weights for the convolutional layers and put to the directory build\darknet\x64

for yolov4.cfg, yolov4-custom.cfg (162 MB): yolov4.conv.137 (Google drive mirror yolov4.conv.137 )
for yolov4-tiny.cfg, yolov4-tiny-3l.cfg, yolov4-tiny-custom.cfg (19 MB): yolov4-tiny.conv.29
for csresnext50-panet-spp.cfg (133 MB): csresnext50-panet-spp.conv.112
for yolov3.cfg, yolov3-spp.cfg (154 MB): darknet53.conv.74
for yolov3-tiny-prn.cfg , yolov3-tiny.cfg (6 MB): yolov3-tiny.conv.11
for enet-coco.cfg (EfficientNetB0-Yolov3) (14 MB): enetb0-coco.conv.132

For training Yolo based on other models (DenseNet201-Yolo or ResNet50-Yolo), you can download and get pre-trained weights as showed in this file: https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/partial.cmd If you made you custom model that isn't based on other models, then you can train it without pre-trained weights, then will be used random initial weights.