Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

spaGO is a beautiful and maintainable machine learning library written in Go designed to support relevant neural network architectures in natural language processing tasks

Minimalist NMT for educational purposes

transformer, multi-graph transformer, graph, graph classification, sketch recognition, sketch classification, free-hand sketch, official code of the paper "Multi-Graph Transformer for Free-Hand Sketch Recognition"

Simple State-of-the-Art BERT-Based Sentence Classification with Keras / TensorFlow 2. Built with HuggingFace's Transformers.

Fine-tuned pre-trained GPT2 for custom topic specific text generation. Such system can be used for Text Augmentation.

Seq2SeqSharp is a tensor based fast & flexible encoder-decoder deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, many different types of encoders/decoders(Transformer, LSTM, BiLSTM and so on), multi-GPUs supported and so on.

PyTorch implementation of the model presented in "Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention"

Attention Is All You Need | a PyTorch Tutorial to Machine Translation

PyTorch code for the paper: "Perceive, Transform, and Act: Multi-Modal Attention Networks for Vision-and-Language Navigation"

Attention Based Multi-modal Emotion Recognition; Stanford Emotional Narratives Dataset

The goal of this project is to create multi-modal implementation of Transformer architecture in Swift.

Curated implementation notebooks and scripts of deep learning based natural language processing tasks and challenges in TensorFlow.

Basic Gesture Recognition Using mmWave Sensor - TI AWR1642

BioShield is intended to be an AI system that predicts anti-viral molecules and search among already FDA approved drugs the most similar to be used on humans while the novel predicted molecule is tested and approved.

📄 Evidence Retrieval and Claim Verification for the FEVER shared task using Transformer Networks

Implementation of the transformer architecture (Vaswani et. al. 2017) in PyTorch.

Deep Classiflie is a framework for developing ML models that bolster fact-checking efficiency. As a POC, the initial alpha release of Deep Classiflie generates/analyzes a model that continuously classifies a single individual's statements (Donald Trump) using a single ground truth labeling source (The Washington Post). For statements the model deems most likely to be labeled falsehoods, the @DeepClassiflie twitter bot tweets out a statement analysis and model interpretation "report"

Abstractive Text Summarization using Transformer model

Deep_classiflie_db is the backend data system for managing Deep Classiflie metadata, analyzing Deep Classiflie intermediate datasets and orchestrating Deep Classiflie model training pipelines. Deep_classiflie_db includes data scraping modules for the initial model data sources. Deep Classiflie depends upon deep_classiflie_db for much of its analytical and dataset generation functionality but the data system is currently maintained as a separate repository here to maximize architectural flexibility. Depending on how Deep Classiflie evolves (e.g. as it supports distributed data stores etc.), it may make more sense to integrate deep_classiflie_db back into deep_classiflie. Currently, deep_classiflie_db releases are synchronized to deep_classiflie releases. To learn more, visit deepclassiflie.org.

General API for Deep Bayesian Variational Inference by Backpropagation. The repository has been designed to work with Transformers like architectures. Compatible with the HuggingFace Transformers models.

Implementación Transformers, adaptación del curso: "Procesamiento del Lenguaje Natural Moderno en Python. (Juan Gabriel Gomila)

A question answering bot based on the transformer architecture.

Based on Google's paper 'Attention Is All You Need', this sequence to sequence model speeds up RNNs by using 'Attention', enabling parallelization.