YOLOV3

Introduction

This is my own YOLOV3 written in pytorch, and is also the first time i have reproduced a object detection model.The dataset used is PASCAL VOC(not use difficulty). The eval tool is the voc2010. Now the mAP gains the goal score.

Subsequently, i will continue to update the code to make it more concise , and add the new and efficient tricks.

Results

name	Train Dataset	Val Dataset	mAP(others)	mAP(mine)	notes
YOLOV3-448-544	2007trainval + 2012trainval	2007test	0.769	0.768	baseline(augument + step lr)
YOLOV3-*-544	2007trainval + 2012trainval	2007test	0.793	0.803	+multi-scale training

Note :

YOLOV3-448-544 means train image size is 448 and test image size is 544. "*" means the multi-scale.
In the test, the nms threshold is 0.5 and the conf_score is 0.01.
Now only support the single gpu to train and test.

Environment

Nvida GeForce RTX 2080 Ti
CUDA10.0
CUDNN7.0
ubuntu 16.04

# install packages
pip3 install -r requirements.txt --user

Brief

Prepared work

1、Git clone YOLOV3 repository

git clone https://github.com/Peterisfar/YOLOV3.git

2、Download dataset

Download Pascal VOC dataset : VOC 2012_trainval 、VOC 2007_trainval、VOC2007_test
Convert data format : Convert the pascal voc *.xml format to custom format (Image_path0 xmin0,ymin0,xmax0,ymax0,class0 xmin1,ymin1...)

cd YOLOV3 && mkdir data
cd utils
python3 voc.py # get train_annotation.txt and test_annotation.txt in data/

3、Download pre-weight

Darknet pre-trained weight : darknet53-448.weights
This repository test weight : best.pt

Make dir weight/ in the YOLOV3 and put the weight file in.

Train

Run the following command to start training and see the details in the params.py

CFG_PATH=cfg/yolov3-voc.cfg
WEIGHT_PATH=weight

CUDA_VISIBLE_DEVICES=0 nohup python3 -u train.py --cfg_path $CFG_PATH --weight_path $WEIGHT_PATH --gpu_id 0 > nohup.log 2>&1 &

Notes:

Training steps could run the "cat nohup.log" to print the log.
It supports to resume training adding --resume, it will load last.pt automaticly.

Test

You should define your weight file path WEIGHT_FILE and images file path IMAGE_FILE

CFG_PATH=cfg/yolov3-voc.cfg
WEIGHT_PATH=weight
DATA_TEST=./data/test # your own images

CUDA_VISIBLE_DEVICES=0 python3 test.py --cfg_path $CFG_PATH --weight_path $WEIGHT_PATH --gpu_id 0 --visiual $DATA_TEST --eval

The images can be seen in the data/

TODO

Mish
OctvConv
Mobilenet v1-v3

Reference

tensorflow : https://github.com/Stinky-Tofu/Stronger-yolo
pytorch : https://github.com/ultralytics/yolov3
keras : https://github.com/qqwweee/keras-yolo3

cafunechen/YOLOV3