September 8, 2019

394 words 2 mins read

YunYang1994/tensorflow-yolov3

YunYang1994/tensorflow-yolov3

pure tensorflow Implement of YOLOv3 with support to train your own dataset

repo name YunYang1994/tensorflow-yolov3
repo link https://github.com/YunYang1994/tensorflow-yolov3
homepage
language Python
size (curr.) 64372 kB
stars (curr.) 2381
created 2018-11-23
license Other

🆕 Are you looking for a new YOLOv3 implemented by TF2.0 ?

If you hate the fucking tensorflow1.x very much, no worries! I have implemented a new YOLOv3 repo with TF2.0, and also made a chinese blog on how to implement YOLOv3 object detector from scratch. code | blog | issue

part 1. Quick start

  1. Clone this file
$ git clone https://github.com/YunYang1994/tensorflow-yolov3.git
  1. You are supposed to install some dependencies before getting out hands with these codes.
$ cd tensorflow-yolov3
$ pip install -r ./docs/requirements.txt
  1. Exporting loaded COCO weights as TF checkpoint(yolov3_coco.ckpt)【BaiduCloud
$ cd checkpoint
$ wget https://github.com/YunYang1994/tensorflow-yolov3/releases/download/v1.0/yolov3_coco.tar.gz
$ tar -xvf yolov3_coco.tar.gz
$ cd ..
$ python convert_weight.py
$ python freeze_graph.py
  1. Then you will get some .pb files in the root path., and run the demo script
$ python image_demo.py
$ python video_demo.py # if use camera, set video_path = 0

part 2. Train your own dataset

Two files are required as follows:

xxx/xxx.jpg 18.19,6.32,424.13,421.83,20 323.86,2.65,640.0,421.94,20 
xxx/xxx.jpg 48,240,195,371,11 8,12,352,498,14
# image_path x_min, y_min, x_max, y_max, class_id  x_min, y_min ,..., class_id 
# make sure that x_max < width and y_max < height
person
bicycle
car
...
toothbrush

2.1 Train on VOC dataset

Download VOC PASCAL trainval and test data

$ wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
$ wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
$ wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar

Extract all of these tars into one directory and rename them, which should have the following basic structure.


VOC           # path:  /home/yang/dataset/VOC
├── test
|    └──VOCdevkit
|        └──VOC2007 (from VOCtest_06-Nov-2007.tar)
└── train
     └──VOCdevkit
         └──VOC2007 (from VOCtrainval_06-Nov-2007.tar)
         └──VOC2012 (from VOCtrainval_11-May-2012.tar)
                     
$ python scripts/voc_annotation.py --data_path /home/yang/test/VOC

Then edit your ./core/config.py to make some necessary configurations

__C.YOLO.CLASSES                = "./data/classes/voc.names"
__C.TRAIN.ANNOT_PATH            = "./data/dataset/voc_train.txt"
__C.TEST.ANNOT_PATH             = "./data/dataset/voc_test.txt"

Here are two kinds of training method:

(1) train from scratch:
$ python train.py
$ tensorboard --logdir ./data
(2) train from COCO weights(recommend):
$ cd checkpoint
$ wget https://github.com/YunYang1994/tensorflow-yolov3/releases/download/v1.0/yolov3_coco.tar.gz
$ tar -xvf yolov3_coco.tar.gz
$ cd ..
$ python convert_weight.py --train_from_coco
$ python train.py

2.2 Evaluate on VOC dataset

$ python evaluate.py
$ cd mAP
$ python main.py -na

the mAP on the VOC2012 dataset:

part 3. Stargazers over time

Stargazers over time

part 4. Other Implementations

-YOLOv3目标检测有了TensorFlow实现,可用自己的数据来训练

-Stronger-yolo

- Implementing YOLO v3 in Tensorflow (TF-Slim)

- YOLOv3_TensorFlow

- Object Detection using YOLOv2 on Pascal VOC2012

-Understanding YOLO

comments powered by Disqus