The inverse_cooking's intro from nerdward

inverse_cooking's Introduction

FoodAI

Installation guide
Backend
Frontend

Installation

This code uses Python 3.6 and PyTorch 0.4.1 cuda version 9.0.

Packages setup

$ pip install --editable .

Creating virtual environment:

conda create -n inv_cooking

Activate the virtual environment

conda activate inv_cooking

Installing PyTorch:

$ conda install pytorch=0.4.1 cuda90 -c pytorch

Install dependencies

$ pip install -r requirements.txt

Pretrained model

To download the Ingredient, Instruction vocabularies and pretrained model weights. Run:

$ make artifacts

Backend Server

To start up the fast api and uvicorn server

$ cd app

$ uvicorn app.api:app \       # location of app (`app` directory >`api.py` script > `app` object)
    --host 0.0.0.0 \        # localhost
    --port 8000 \           # port 8000
    --reload \              # reload every time we update
    --reload-dir tagifai \  # only reload on updates to `tagifai` directory
    --reload-dir app        # and the `app` directory

Frontend

To start up the streamlit frontend server, run

$ cd frontend

$ streamlit run home.py

Go to localhost on browser, copy http://localhost:8501

Code supporting the paper:

Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto, Adriana Romero. Inverse Cooking: Recipe Generation from Food Images. CVPR 2019

@InProceedings{Salvador2019inversecooking,
author = {Salvador, Amaia and Drozdzal, Michal and Giro-i-Nieto, Xavier and Romero, Adriana},
title = {Inverse Cooking: Recipe Generation From Food Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}

Recommend Projects