RadEyeVideo

Download the following MIMIC datasets

1. You will need to complete the credentialing process in order to gain access to the data. You can do this here: https://physionet.org/settings/credentialing/. Then, sign the data usage agreement for each one of the following PhysioNet datasets.
2. Download MIMIC-EYE
3. Download MIMIC-CXR Reports
4. Extract mimic-cxr-reports.zip
5. Download MIMIC-CXR CheXpert
6. Extract mimic-cxr-2.0.0-chexpert.csv.gz

Run radeyevideo-processing.ipynb for dataset processing

Example for running LLaVA-OneVision

git clone https://github.com/LLaVA-VL/LLaVA-NeXT
cd LLaVA-NeXT

conda create -n llava python=3.10 -y
conda activate llava
pip install --upgrade pip  # Enable PEP 660 support.
pip install -e ".[train]"

move python files

mv eval_vqa_video.py LLaVA-NeXT
mv eval_vqa.py LLaVA-NeXT
mv run_vqa.sh LLaVA-NeXT
mv run_vqa_video.sh LLaVA-NeXT

run bash

bash run_vqa_video.sh