Kohulan/DECIMER-Image_Transformer

# 🧪 DECIMER Image Transformer 🖼️ ### Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer

DECIMER Logo

[![License](https://img.shields.io/badge/License-MIT%202.0-blue.svg?style=for-the-badge)](https://opensource.org/licenses/MIT) [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/graphs/commit-activity) [![GitHub issues](https://img.shields.io/github/issues/Kohulan/DECIMER-Image_Transformer.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/issues/) [![GitHub contributors](https://img.shields.io/github/contributors/Kohulan/DECIMER-Image_Transformer.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/graphs/contributors/) [![tensorflow](https://img.shields.io/badge/TensorFlow-2.10.1-FF6F00.svg?style=for-the-badge&logo=tensorflow)](https://www.tensorflow.org) [![DOI](https://zenodo.org/badge/293572361.svg)](https://zenodo.org/badge/latestdoi/293572361) [![Documentation Status](https://readthedocs.org/projects/decimer-image-transformer/badge/?version=latest&style=for-the-badge)](https://decimer-image-transformer.readthedocs.io/en/latest/?badge=latest) [![GitHub release](https://img.shields.io/github/release/Kohulan/DECIMER-Image_Transformer.svg?style=for-the-badge)](https://GitHub.com/Kohulan/DECIMER-Image_Transformer/releases/) [![PyPI version fury.io](https://badge.fury.io/py/decimer.svg?style=for-the-badge)](https://pypi.python.org/pypi/decimer/)

🔬 Abstract

The DECIMER 2.2 project tackles the OCSR (Optical Chemical Structure Recognition) challenge using cutting-edge computational intelligence methods. Our goal? To provide an automated, open-source software solution for chemical image recognition. We've supercharged DECIMER with Google's TPU (Tensor Processing Unit) to handle datasets of over 1 million images with lightning speed!

🧠 Method and Model Changes

🖼️ Image Feature Extraction

Now utilizing EfficientNet-V2 for superior image analysis

🔮 SMILES Prediction

Employing a state-of-the-art transformer model

🚀 Training Enhancements

TFRecord Files: Lightning-fast data reading
Google Cloud Buckets: Efficient cloud storage solution
TensorFlow Data Pipeline: Optimized data loading
TPU Strategy: Harnessing the power of Google's TPUs

💻 Installation

# Create a conda wonderland
conda create --name DECIMER python=3.10.0 -y
conda activate DECIMER

# Equip yourself with DECIMER
pip install decimer

🎮 Usage

from DECIMER import predict_SMILES

# Unleash the power of DECIMER
image_path = "path/to/your/chemical/masterpiece.jpg"
SMILES = predict_SMILES(image_path)
print(f"🎉 Decoded SMILES: {SMILES}")

✍️ DECIMER - Hand-drawn Model

🌟 **New Feature Alert!** 🌟 Our latest model brings the magic of AI to hand-drawn chemical structures! [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10781330.svg)](https://doi.org/10.5281/zenodo.10781330)

📜 Citation

If DECIMER helps your research, please cite: 1. Rajan K, et al. "DECIMER.ai - An open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications." *Nat. Commun.* 14, 5045 (2023). 2. Rajan, K., et al. "DECIMER 1.0: deep learning for chemical image recognition using transformers." *J Cheminform* 13, 61 (2021). 3. Rajan, K., et al. "Advancements in hand-drawn chemical structure recognition through an enhanced DECIMER architecture," *J Cheminform* 16, 78 (2024).

🙏 Acknowledgements

A big thank you to Charles Tapley Hoyt for his invaluable contributions!
Powered by Google's TPU Research Cloud (TRC)

👨‍🔬 Author: Kohulan

🌐 Project Website

Experience DECIMER in action at decimer.ai, brilliantly implemented by Otto Brinkhaus!

🏫 Research Group

### 📊 Project Analytics ![Repobeats](https://repobeats.axiom.co/api/embed/bf532b7ac0d34137bdea8fbb82986828f86de065.svg "Repobeats analytics image")