fragNN

A C++/CUDA neural network trained on fragrance data to predict gender and main accord from perfume notes and accords.

Dataset

Download the dataset from Kaggle and place it in a datasets/ directory at the project root:

Dataset: Fragrantica Fragrance Dataset

fragNN/
└── datasets/
    └── fra_cleaned.csv

Run the preprocessing script before building:

cd datasets/
python3 ../preprocess.py

This will generate train.csv, test.csv, note_vocab.txt, and accord_vocab.txt inside data/.

Project Structure

fragNN/
├── data/               # generated by preprocess.py — do not edit manually
├── datasets/           # place fra_cleaned.csv here
├── src/
│   ├── dataloader.h
│   ├── dataloader.cpp
│   ├── network.h
│   └── network.cpp
├── cuda/
│   └── kernels.cu
│   └── kernels.cuh
├── main.cpp
├── preprocess.py
├── CMakeLists.txt
└── README.md

Requirements

• CUDA-capable GPU (tested on RTX 2050)
• CUDA Toolkit
• CMake >= 3.24
• C++17

WIP

• When to use: 'morning', 'office', 'date', 'home'...
• Make a small web interface to the program: images, note pyramids...