tram-v2

aghoraguru/tram-v2

tram-v2 is a object detection model from aghoraguru. Use it when you need objects located in an image. It is set up for pytorch. The card lists the license as cc-by-4.0.

Reference checkpoint for TRAM-V2 from the paper TRAM: Transformer-Based Mask R-CNN Framework for Underwater Object Detection in Side-Scan Sonar Data (Makam, Sundaram, & Sundaram).

Downloads · 30 days

Access

Public

Updated May 10, 2026

Repo size

427 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pth427 MB · 100%

At a glance

Task: Object Detection
Library: pytorch
License: cc-by-4.0
Access: Public
Created: May 10, 2026
Updated: May 10, 2026
SHA: fc8f849d

Model card

From the Hugging Face model README

TRAM-V2

Reference checkpoint for TRAM-V2 from the paper TRAM: Transformer-Based Mask R-CNN Framework for Underwater Object Detection in Side-Scan Sonar Data (Makam, Sundaram, & Sundaram).

Architecture: MST (Swin-Base) + FPN + CBAM + Mask R-CNN
Input: 224×224 RGB
Training data: SSS_OD-5 (SeabedObjects-KLSG-derived, plane + ship)
Best epoch: 27 / 47
Random seed: not fixed

Validation metrics (this run)

Metric	This run	Paper
Det [email protected]	0.8356	0.8321
Det [email protected]:0.95	0.5496	0.5293
Seg [email protected]	0.7538	0.7352
Seg [email protected]:0.95	0.4244	0.4412

Usage

git clone -b final-tram-v123 https://github.com/CrypticCortex/iisc-sss-codes.git
cd iisc-sss-codes
pip install -r final/requirements.txt

python -m final.tram_v2.inference \
    --weights /path/to/tram_v2_best.pth \
    --data-root /path/to/SSS_OD-5/valid \
    --output-dir runs/tram-v2/inference \
    --evaluate-map

Files

tram_v2_best.pth — best checkpoint (highest val bbox [email protected]:0.95)
training.log — per-epoch training/validation log

Source

Code: https://github.com/CrypticCortex/iisc-sss-codes/tree/final-tram-v123/final
Other variants: tram-v1 · tram-v2 · tram-v3

Task: Object Detection
Library: pytorch
License: cc-by-4.0
Created: May 10, 2026
Updated: May 10, 2026