π Vessel Detection Model
This folder contains the inference model for detection of vessels in range-compressed SAR data, including:
- An unrestricted YOLO26s-Pose model used as the main or teacher model
- A lightweight YOLO26n-Pose model for faster deployment
These models were trained based on the filtered, higher quality subset of opensar-insight/vessel-detection-dataset.
π§© Detailed List of Models
The main models available are:
- Unrestricted teacher model: yolo26s-pose_opensar_true_vessel_filtered_dataset_640px_unrestricted.pt
- Lightweight student model: yolo26n-pose_feature_kd_from_s_640_300ep_feat4_lightweight.pt
π» Codebase
The full codebase, which includes training and inference capabalities, as well as script for further dataset generation, will soon be made open-source.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support