Downloads · 30 days
0
Medico2025_Task1_Submission
Suguneswari/Medico2025_Task1_Submission
Medico2025_Task1_Submission is a machine learning model from Suguneswari. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains the submission for MediaEval Medico 2025 - Task 1: VQA on GastroIntestinal Imaging.
Access
Public
Updated Oct 14, 2025
Repo size
83.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth83.9 MB · 91%
At a glance
- Access
- Public
- Created
- Sep 22, 2025
- Updated
- Oct 14, 2025
- SHA
- 0ac20464
Model card
From the Hugging Face model README
Medico 2025 Task 1 Submission
This repository contains the submission for MediaEval Medico 2025 - Task 1: VQA on GastroIntestinal Imaging.
Files
submission_task1.py: Inference script (used by evaluation server).train_task1.py: Training script (full pipeline, used offline).best_model.pth: Trained model weights (to be added after training).label_mapping.json: Mapping between label indices and answer strings.requirements.txt: Dependencies required to run the code.
How to Train
python train_task1.py
This will save the best model as best_model.pth.
How to Run Submission
The evaluation server will call:
python submission_task1.py
Make sure best_model.pth and label_mapping.json are present in the repo root.
- Created
- Sep 22, 2025
- Updated
- Oct 14, 2025