Dl4J Implementation of Tiny-Yolov2
- Project based on DL4J-example
(click for full video)
- Import project dependencies with Gradle
- download model from g-drive watch model.txt
- If you own an NVIDIA card with a CUDA support you can enable the usage in Gradle file
- If you wish to use your own data simply paste it into the /data folder, link for an example set is in data.txt
- The project is using a Keras Yolo data-format
If model.zip isn't available in project then root directory then the training will start.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.