- This repo contains an implementation of siamese network using triplett loss for object identification.
- The backbone used for this network in VGG19 having pretrained imagenet weights.
- This model was build for research and experiment
- Accuracy, ROC curve to be implemented and integrated in the evaluation subroutine.
- To be trained with more data and mode classes.
- Add demo script
- Its a very small dataset with 83 classes
- Link - https://drive.google.com/file/d/1UMuw0aletrs0X6Kdbr2hOEbzHoykANEY/view?usp=sharing
Link - https://drive.google.com/file/d/1AYirOgPosRgOu8qehsDKj2FaziT3jVFc/view?usp=sharing
- Python 3.8+
- tensorflow > 2.10
- cv2
Change the parameters of run.sh and
source run.sh
Note - This repo is developed and maintained by Saket Mohanty