Top 223 attention-mechanism open source projects

Code/Model release for NIPS 2017 paper "Attentional Pooling for Action Recognition"

Code for paper "Attention on Attention for Image Captioning". ICCV 2019

My take on a practical implementation of Linformer for Pytorch.

Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

Attention mechanism Implementation for Keras.

Transformer based on a variant of attention that is linear complexity in respect to sequence length

Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.

Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.

Implementation of the Point Transformer layer, in Pytorch

Coherent Semantic Attention for image inpainting(ICCV 2019)

Image Captions Generation with Spatial and Channel-wise Attention

Sparse and structured neural attention mechanisms

Train and visualize Hierarchical Attention Networks

Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/

Attention over nodes in Graph Neural Networks using PyTorch (NeurIPS 2019)

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".

Hierarchical Attention Networks | a PyTorch Tutorial to Text Classification

attention based joint model for intent detection and slot filling

Attention-based multimodal fusion for sentiment analysis

attention-based LSTM/Dense implemented by Keras

A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.

Implementation of Slot Attention from GoogleAI

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

Chinese Poetry Generation

Pytorch Implementation of PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection

Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention

Important paper implementations for Question Answering using PyTorch

[Params: Only 272K!!!] Efficient Image Super-Resolution Using Pixel Attention, in ECCV Workshop, 2020.

Hierarchical Attentive Recurrent Tracking

Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)

Fully featured implementation of Routing Transformer

基于seq2seq模型的简单对话系统的tf实现，具有embedding、attention、beam_search等功能，数据集是Cornell Movie Dialogs

[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning

A bidirectional LSTM with attention for multiclass/multilabel text classification.

Deep-Learning based CTR models implemented by PyTorch

Attention-guided CNN for image denoising(Neural Networks,2020)

The code of CIKM'19 paper《Hierarchical Multi-label Text Classification: An Attention-based Recurrent Network Approach》

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

Implementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.

A neural network to generate captions for an image using CNN and RNN with BEAM Search.

Keras Implementation of Aspect based Sentiment Analysis

An Implementation of 'Attention is all you need' with Chinese Corpus

Densely Residual Laplacian Super-resolution, IEEE Pattern Analysis and Machine Intelligence (TPAMI), 2020

从零开始学习YOLOv3教程解读代码+注意力模块(SE,SPP,RFB etc)

A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

Tensorflow Implement of GeoMAN, IJCAI-18

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

official implementation of the spatial-temporal attention neural network (STANet) for remote sensing image change detection

[CVPR 2020] Official Implementation: "Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models".

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

Reformer, the efficient Transformer, in Pytorch

Revisiting Video Saliency: A Large-scale Benchmark and a New Model (CVPR18, PAMI19)