Showing 36 of 350 projects
A curated archive of pre-trained computer vision models for object detection, face recognition, fire detection, and more.
A TensorFlow-based model that generates descriptive captions for images using an Inception-v3 encoder and LSTM decoder.
A TensorFlow implementation of Attend, Infer, Repeat (AIR), a generative model for fast scene understanding by reconstructing objects sequentially.
A Docker-based speech recognition model that converts short English WAV audio files into text using Mozilla's DeepSpeech.
A neural network model that integrates neighbor information from heterogeneous networks to discover new drug-target interactions.
An implementation of unsupervised image-to-image translation using Generative Adversarial Networks (GANs).
A TensorFlow/Keras LSTM model for hourly weather forecasting, offering univariate, multivariate, and multistep prediction modes.
A simple implementation of the DAGGER imitation learning algorithm for autonomous steering control in the Torcs racing simulator.
A TensorFlow-based convolutional neural network for recognizing four-digit CAPTCHA images.
Code for the Kaggle Dogs vs. Cats image classification competition using deep learning.
Detects humans in images and estimates their poses by identifying body parts and connecting them with pose lines.
A curated collection of machine-learned models for autonomous driving tasks like perception, prediction, and planning.
ROS2 nodes for performing computer vision inference using TensorFlow models, enabling object detection and image classification in robotics.
A TensorFlow wrapper library for character-level and word-level text generation using recurrent neural networks.
Kotlin implementations of TensorFlow Lite example Android apps for on-device machine learning.
Catkin-friendly C++ bindings for TensorFlow, enabling easy integration of TensorFlow C++ API into ROS projects.
Generates embedding vectors from audio files using a TensorFlow model trained on AudioSet, deployable as a Docker container.
A high-level neural networks API for Delphi, written in Pascal with Python binding and support for TensorFlow, CNTK, or Theano backends.
A pre-trained BERT-based model for detecting positive or negative sentiment in short text fragments.
A TensorFlow implementation of convolutional highway networks for deep learning experiments.
A TensorFlow library implementing Restricted Boltzmann Machines and their variants for machine learning applications.
A lightweight, high-performance C++ wrapper for TensorFlow that simplifies development with a modern API.
An open-source pipeline for high-throughput, non-invasive extraction of phenotypic traits from plant images using deep learning.
V language bindings for Mozilla's DeepSpeech, enabling speech-to-text functionality in V applications.
A 3D convolutional network software package for extracting axonal and filamentous structures from cleared brain imaging data.
A proof-of-concept for decentralized machine learning using federated learning on the Golem network to distribute training across multiple nodes.
TensorFlow implementation of AlexNet with 3D convolutional layers for volumetric image recognition.
A simple, easy-to-understand library for diffusion models built with Flax and JAX, focusing on readability and learning.
A collection of classical machine learning models implemented with TensorFlow 2 and Keras, featuring TensorBoard visualizations.
A curated list of awesome Keras projects, libraries, and resources for deep learning.
A TensorFlow/TensorLayer implementation of Spatial Transformer Networks for learning image transformations like scaling, cropping, and rotation.
A Docker-based starter kit providing pre-configured Jupyter notebook environments for machine learning with TensorFlow, PyTorch, and essential libraries.
A TensorFlow wrapper for the D programming language, providing C API bindings and integration with Mir for numerical computing.
A BERT-based model that answers questions from a given text corpus, deployable as a Docker container.
A TensorFlow-based image segmentation model that assigns each pixel in an image to one of 21 object classes from the PASCAL VOC dataset.
A German ELMo deep contextualized word representation model trained on a specialized German Wikipedia text corpus for NLP tasks.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.