This project developed a U-Net model for image segmentation, specifically for identifying lunar craters in images. The model was trained on a dataset of lunar images and corresponding masks, with data augmentation techniques used to improve model robustness. The model was compiled with the Adam optimizer and a dice coefficient loss function, and evaluated using metrics such as IOU and dice coefficient. The trained model was then tested on a separate dataset of lunar images, and also applied to images of lunar boulders to assess its generalization capability.
Kindly, Assign me Under :
- Gssoc-ext
- hacktoberfest-accepted
- Level-3
This project developed a U-Net model for image segmentation, specifically for identifying lunar craters in images. The model was trained on a dataset of lunar images and corresponding masks, with data augmentation techniques used to improve model robustness. The model was compiled with the Adam optimizer and a dice coefficient loss function, and evaluated using metrics such as IOU and dice coefficient. The trained model was then tested on a separate dataset of lunar images, and also applied to images of lunar boulders to assess its generalization capability.
Kindly, Assign me Under :