Library / Framework · Jupyter Notebook

socrate

OCR using Transformers

vlad andrei@ihatebaselines · Atlas 49.6 · #11 builder

What it is

The SocrateX library provides a modular framework for building OCR models that combine CNN feature extraction with transformer-based sequence modeling, including components for data handling, training, and inference.

Scored from the code at its last scan, 19 Oct 2026. How merit is scored

Where it counts

Machine Learning80%
Computer Vision70%
NLP & LLMs60%
Data Science30%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit

35VISTAArchitecture Modification / Research · Jupyter NotebookVISTA is a video object detection framework that augments standard detection architectures (DETR, YOLO, SSD) with optical flow-based motion features and a staticness branch to improve detection of moving and static objects. It provides training scripts for three variants and…50.4/100ImplementationSuceveanu Mircea Dan SanduMachine Learning
36chatbot-pipelineML Application · PythonThis repository implements an end-to-end intent-based chatbot system using TensorFlow/Keras for model training and Flask for serving. It includes a standard NLP pipeline (tokenization, lemmatization, bag-of-words) and provides instructions for both training from scratch and…50.2/100ImplementationPop AlexandruMachine Learning
37socrateLibrary / Framework · Jupyter Notebook49.2/100Implementationvlad andreiMachine Learning
38Signal-DetectionML Application · Jupyter NotebookThis repository provides an end-to-end face mask detection system using transfer learning with MobileNetV2. It includes data loading, model training, evaluation, and a real-time inference script that integrates OpenCV-based face detection.47.5/100ImplementationSuceveanu Mircea Dan SanduMachine Learning
39advanced-clusteringEducational Implementation · Jupyter NotebookThe repository provides a comparative study of K-Means, DBSCAN, hierarchical, and spectral clustering on synthetic datasets, accompanied by a Jupyter notebook and a script to regenerate all figures.46.5/100ImplementationPop AlexandruMachine Learning

What it is

Where it counts

Around it on the Machine Learning board

More from vlad andrei