A safe hat detection model using keras-retinanet
Author | LCorleone |
---|---|
[email protected] |
please see the original github keras-retinanet
- Sorry I can not provide the training dataset, so only the trained model is available.
- The safe hat seems to be relatively small, by now I didn't figure out how to modify the anchor settings correctly in keras-retinanet. Indeed I try but the performance is not satisfactory. If anyone know about this, feel free to contact me!
- The trained model is available here BAIDU PAN