You only look once (YOLO) is a state-of-the-art, real-time object detection system. It is implemented based on the Darknet, an Open Source Neural Networks in C. In this project I improved the YOLO by adding several convenient functions for detecting objects for researches and the development community.
Figure. Example of Object Detection using Yolo based on the Darknet.
The added functions are implemented based on AlexeyAB version of Darknet. As it is updated frequently, hereby I publish a stable version of AlexeyAB Darknet with those convenient functions. This repo will also be updated regularly.
Github link: https://github.com/vincentgong7/VG_AlexeyAB_darknet
Figure. The process of batch detecting images in a folder using Yolo based on the Darknet.
The detector function in AlexeyAB Darknet only supports a single image at a time. Therefore I added the batch function into this forked repo, which support detecting images in a folder in one time. Hope you like it. Please also refer to the post for detail:
./darknet detector batch cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch exp/in_images/ exp/out_images/ > exp/results/results.txt
Parameter explain:
- The input images are: in_images/
- The output images are: out_images/
- The detection classes with percentage is saved in: exp/results/results.txt
-
Clone this project.
-
Download pre-trained weights file into foder ./weights/. Such as:
-
Make the project with command in darknet/ folder:
make
- Use the command described above to perform batch detecting images.
Any questions please let me know. vincent.gong7[at]gmail.com
<script type="text/javascript" src="//counter.websiteout.net/js/5/4/69/0"></script>