# Img2Vec

A rough implementation of generating image embeddings through methodologies introduced in LLaVA

### Structure
We derived the image embeddings by using a CLIP encoder and mapping it with the pretrained LLaVA’s projection weight

### Prerequisites
1. install requirements.txt
2. Make sure you have downloaded [pytorch_model-00003-of-00003.bin](https://huggingface.co/liuhaotian/LLaVA-13b-delta-v1-1/blob/main/pytorch_model-00003-of-00003.bin")
3. For example image data, I use [2017 Val images 5K/1GB](http://images.cocodataset.org/zips/val2017.zip) and [2017 Train/Val annotations 241MB](http://images.cocodataset.org/annotations/annotations_trainval2017.zip)

### Usage

Replace **image-dir** and **llava-ckpt** to your **test image folder addr** and **pytorch_model-00003-of-00003.bin addr** and run:

`python starter.py --image-dir ./datasets/coco/val2017 --output-dir imgVecs --vision-model openai/clip-vit-large-patch14-336 --proj-dim 5120 --llava-ckpt ./datasets/pytorch_model-00003-of-00003.bin --batch-size 64`