DAR

KO | EN

gitlite — search

#javascript #hacktoberfest #machine-learning #docker #nodejs #java #windows #awesome #awesome-list #pytorch #security #openai #ios #open-source

(★ 15)

Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective

DAR 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Enhancing Recipe Retrieval with Foundation Models

Official implementation of our ECCV2024 paper:

**[Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective ](https://arxiv.org/abs/2312.04763)**

This paper proposes a new perspective on data augmentation using the Foundation Model (i.e., llama2 and SAM) to better learn multimodal representations in the common embedding space for the task of cross-modal recipe retrieval.

![Project Banner](https://raw.githubusercontent.com/Noah888/DAR/main/figs.jpg)

---
## Installation

To install the required packages, please follow these steps:

```bash
# Clone the repository
git clone https://github.com/Noah888/DAR.git

# Create a virtual environment (Python 3.8 or above)
conda create --name your_env_name python=3.9

# Activate the conda environment
conda activate your_env_nam

# Install dependencies
pip install -r requirements.txt
cd src
```

## Dataset
To reproduce the results,  Download Recipe1M [dataset](http://wednesday.csail.mit.edu/temporal/release/) and Generate enhanced data ([traindata (add visual imagination data)](https://drive.google.com/file/d/1mceOq99iyBJ3dG55TQTl983SOscDAK6a/view?usp=drive_link) and [segment data](https://pan.baidu.com/s/1gugeBDXb1e2b4EjcEIkdAQ?pwd=beig)). Place the data in the ```DATASET_PATH``` directory with the following structure:
```bash
DATASET_PATH/
│── traindata/
├── train/
│   ├── ...
├── val/
│   ├── ...
└── test/
│   ├── ...
├── segment/
│    ├── train/...
│    ├── val/...
│    ├── test/...
└── layer1.json
└── layer2.json
```

## Training

- Launch training with:

```
python train.py --model_name model --root DATASET_PATH --save_dir /path/to/saved/model/checkpoints
```

Run ```python train.py --help``` for the full list of available arguments.

## Evaluation

- Extract features from the trained model for the test set samples of Recipe1M:

```
python test.py --model_name model --eval_split test --root DATASET_PATH --save_dir /path/to/saved/model/checkpoints
```

- Compute MedR and recall metrics for the extracted feature set:
   Evaluation with only image and recipe feats(DAR):
```
python eval.py --embeddings_file /path/to/saved/model/checkpoints/model/feats_test.pkl --medr_N 10000
```
   Evaluation with raw image-recipe features as well as augment segments description features (DAR++):
```
python eval_add_augment.py --embeddings_file /path/to/saved/model/checkpoints/model/feats_test.pkl --medr_N 10000
```

## Pretrained models

- We provide pretrained model weights [DAR_model](https://pan.baidu.com/s/1C7YaSdldTrZLjxM--Atb5g?pwd=p7id):

```
python test.py --model_name DAR_model --eval_split test --root DATASET_PATH --save_dir ../checkpoints
```

- A file with extracted features will be saved under ```../checkpoints/DAR_model```.

This code is based on the [image-to-recipe-transformers](https://github.com/amzn/image-to-recipe-transformers). We would like to express our gratitude.

DAR

DAR 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

DAR

DAR 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README