AI-Atlas score
| Machine Learning | 65 |
|---|---|
| Computer Vision | 61 |
| Data Science | 50 |
| NLP & LLMs | 39 |
| AI Agents | 0 |
| MLOps | 34 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
23 public repositories → 16 with AI work, evaluated. The other 7 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
25% of Atlas Score
This repository provides an end-to-end machine learning application for customer churn prediction, including model training, a FastAPI inference server, and a Streamlit user interface. It uses standard libraries such as scikit-learn, XGBoost, and pandas for data processing and modeling.
14% of Atlas Score
This repository provides an end-to-end image classification system for the CIFAR-100 dataset using a pre-trained EfficientNet-B0 model with a Gradio web interface for inference and a training script for fine-tuning.
13% of Atlas Score
This repository provides an end-to-end machine learning application for predicting student math scores. It includes a training pipeline (data ingestion, transformation, model training) and a deployed inference system via FastAPI and Streamlit, containerized with Docker.
10% of Atlas Score
This repository provides an end-to-end skin cancer classification system, including a CNN model trained on the Melanoma Skin Cancer Dataset, a FastAPI service for inference, and Grad-CAM visualizations for model interpretability. The model achieves approximately 90% accuracy on the evaluation set.
8% of Atlas Score
This repository provides a FastAPI-based inference service for plant disease classification using a pre-trained ONNX model. It also includes a training notebook demonstrating the model creation process via transfer learning with PyTorch Lightning.
8% of Atlas Score
This repository provides an educational walkthrough of linear regression implemented from scratch using NumPy, with data loading and preprocessing handled by scikit-learn, and includes both a Python script and a Jupyter notebook that demonstrate training on the California Housing dataset.
