Showing 24 of 24 projects
A deep learning tool for upscaling and denoising anime-style images and photos using convolutional neural networks.
A free and open-source face recognition library using deep neural networks for research and applications.
Efficient image captioning code in Torch, using a CNN-RNN model to generate captions for images, optimized for GPU training.
An end-to-end framework for building custom AI applications and agents directly integrated with databases.
A web application for training deep learning models with a focus on computer vision tasks.
Original DeepMind DQN 3.0 implementation for Atari game reinforcement learning, with community tweaks.
A modular neural network package for Torch providing building blocks for creating and training deep learning models.
A modular framework for Torch providing abstractions for datasets, engines, meters, and logs to encourage code re-use.
A curated list of awesome Torch tutorials, projects, libraries, and communities for deep learning.
Autograd automatically differentiates native Torch code, enabling automatic gradient computation for machine learning models.
A Torch implementation of a VIS+LSTM model for answering questions about images using deep learning.
Convert Torch7 neural network models to Apple CoreML format for deployment on iOS/macOS devices.
An on-device AI teleprompter that listens to your conversations and suggests charismatic quotes in real-time.
A Torch package for creating and visualizing complex neural network architectures using graph-based computation.
A deep learning model that reads IRCTC captchas with 98% accuracy, demonstrating their vulnerability to automated booking.
CUDA backend implementation for Torch's neural network package, enabling GPU acceleration for deep learning models.
A collection of optimization algorithms and logging utilities for Torch machine learning models.
A Torch wrapper for the Cephes mathematical functions library, providing special mathematical functions for scientific computing.
A graphical computation package for Torch that enables graph-based operations and visualization.
A convolutional neural network solution for the GalaxyZoo galaxy classification challenge, achieving 9th place with a score of 0.08246.
A personal learning repository for implementing neural networks and machine learning models using Torch in Lua.
A neural network system that generates English Wikipedia-style biographies from Semantic Web triples using encoder-decoder models.
A Torch library for computing saliency maps and interest points using fast integral histograms based on Kadir 2004.
Implementation of kernel smoothers (KNN, kernel-weighted average, local linear regression) in Lua for statistical learning.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.