Skip to content

A Keras implementation of YOLOv3 (Tensorflow backend)

License

Notifications You must be signed in to change notification settings

EnableTech/keras-yolo3

 
 

Repository files navigation

keras-yolo3

license

Introduction

A Keras implementation of YOLOv3 (Tensorflow backend) inspired by allanzelener/YAD2K.


Quick Start

  1. Download YOLOv3 weights from YOLO website.
  2. Convert the Darknet YOLO model to a Keras model.
  3. Run YOLO detection.
curl -OL https://pjreddie.com/media/files/yolov3.weights
python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5
python yolo.py   OR   python yolo_video.py

Training

  1. Generate your own annotation file and class names file.
    One row for one image;
    Row format: image_file_path box1 box2 ... boxN;
    Box format: x_min,y_min,x_max,y_max,class_id (no space).
    For VOC dataset, try python voc_annotation.py

  2. Make sure you have run python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5
    A file model_data/yolo_weights.h5 will be generated when you run train.py for the first time.
    The file is used to load pretrained weights.

  3. Modify train.py and start training.
    python train.py
    You will get the trained model model_data/my_yolo.h5.

About

A Keras implementation of YOLOv3 (Tensorflow backend)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%