├── README.md ├── elen645_finalReport_team7.pdf ├── obj.names ├── obj6.data ├── test6.txt ├── train6.txt └── yolov3-tiny6.cfg /README.md: -------------------------------------------------------------------------------- 1 | # YOLOv3-tiny-custom-object-detection 2 | As I continued exploring YOLO object detection, I found that for starters to train their own custom object detection project, it is ideal to use a YOLOv3-tiny architecture since the network is relative shallow and suitable for small/middle size datasets 3 | 4 | 5 | # Environment: 6 | OS: Ubuntu 16.04\ 7 | CUDA 9.0\ 8 | cuDNN 7.0\ 9 | Tensorflow 1.8.0\ 10 | OpenCV 3.3.0 11 | 12 | GPU:Nvidia Geforce GTX 1080 13 | 14 | 15 | # Great sources: 16 | 17 | https://github.com/AlexeyAB/darknet 18 | 19 | https://github.com/AlexeyAB/Yolo_mark 20 | 21 | # Step 1: 22 | Go to YOLO website https://pjreddie.com/darknet/yolo/, follow the instructions and have your Darknet installed. 23 | 24 | # Step 2: 25 | Compiling with CUDA and OpenCV, here is the instruction: https://pjreddie.com/darknet/install/#cuda 26 | Make sure your can run those commands before training your own dataset 27 | 28 | ./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights 29 | 30 | ./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights