Showing 36 of 937 projects
A deep convolutional neural network that predicts RNA-seq coverage at 32bp resolution from DNA sequence.
An end-to-end Python outlier detection system with database support, automated machine learning, and unified APIs for statistical, ML, and deep learning models.
FLAME dataset and deep learning models for fire detection in aerial imagery using UAVs, supporting classification and segmentation tasks.
Neural machine translation between Shakespearean and modern English using TensorFlow.
Ankh is a state-of-the-art protein language model for general-purpose protein modeling and engineering tasks.
A curated list of open-source software tools for medical imaging research, including segmentation, visualization, and deep learning libraries.
A transformer-based model for predicting drug-target interactions using substructural pattern mining and augmented transformer encoders.
A real-time object-level reconstruction system for 6D pose estimation using volumetric fusion and multi-object reasoning.
A ROS2 intelligent visual grasp solution for industrial robots, integrating OpenVINO grasp detection with MoveIt motion planning.
A PyTorch frontend for JAX that enables running PyTorch code on TPUs and provides seamless PyTorch-JAX interoperability.
Automated 3D cell detection and classification in large-scale volumetric brain images using deep learning.
A self-supervised deep learning model for extrinsic calibration between LiDAR and camera sensors using 3D spatial transformer networks.
A PyTorch-based Python package for deep and machine learning analysis of microscopy data, designed for domain scientists.
A Python-based CAPTCHA breaking solution using Keras and OpenCV, developed for a data science competition.
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 proof-of-concept neural network library in Rust with implementations for MNIST digit recognition and char-rnn LSTM models.
A foundation model for cell segmentation that achieves state-of-the-art performance across diverse cellular targets and imaging modalities.
A Python library for building lazy data processing and machine learning workflows that handle datasets larger than memory.
A TensorFlow CNN implementation for Chinese character recognition, achieving 92.5% top-1 accuracy with batch normalization.
A benchmark dataset and meta self-learning method for multi-source domain adaptation in scene text recognition.
A vision transformer architecture that aggregates nested local transformers on image blocks for better accuracy, data efficiency, and convergence.
A Scala and JVM machine learning toolbox for research, education, and industry with an interactive REPL and end-to-end pipelines.
A layer library for JAX-based machine learning projects, optimized for large-scale ML.
A simulation-based deep learning approach to enhance the resolution of 3D lidar point clouds for ground vehicles.
A pure Crystal machine learning library for building and training neural networks with CPU/GPU support and PyTorch compatibility.
A Python library for logging ML metrics, parameters, and models in simple file formats, compatible with DVC and Git.
A collection of optimization algorithms and logging utilities for Torch machine learning models.
A PyTorch-based segmentation toolbox for electron microscopy connectomics, enabling neural structure analysis in 3D volumes.
A lightweight multilayer perceptron neural network library for MicroPython, designed for embedded systems like ESP32 and Pycom modules.
A Torch7 package providing extended neural network modules, criterions, and utilities for deep learning research.
A simple, flexible, and extensible object-oriented template for PyTorch projects.
A Docker container for face detection using Faster R-CNN deep learning, processing videos and images with bounding box outputs.
Shallow and deep convolutional neural networks for predicting visual saliency in images using a data-driven approach.
Integrates Intel OpenVINO with ROS 2 for efficient deep learning inference in computer vision applications on Intel hardware.
A curated collection of tools, tutorials, models, and resources for mastering TensorFlow.js.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.