Kac NetImplementation of Knowledge Aided Consistency for Weakly Supervised Phrase Grounding in Tensorflow
EqtransformerEQTransformer, a python package for earthquake signal detection and phase picking using AI.
GrounderImplementation of Grounding of Textual Phrases in Images by Reconstruction in Tensorflow
Sturcture InpaintingSource code of AAAI 2020 paper 'Learning to Incorporate Structure Knowledge for Image Inpainting'
SimplednnSimpleDNN is a machine learning lightweight open-source library written in Kotlin designed to support relevant neural network architectures in natural language processing tasks
DeepaffinityProtein-compound affinity prediction through unified RNN-CNN
Sarcasm DetectionDetecting Sarcasm on Twitter using both traditonal machine learning and deep learning techniques.
Se3 Transformer PytorchImplementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. This specific repository is geared towards integration with eventual Alphafold2 replication.
Ca NetCode for Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation.
SockeyeSequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
TextclassifierText classifier for Hierarchical Attention Networks for Document Classification
Fed AttAttentive Federated Learning for Private NLM
Isab PytorchAn implementation of (Induced) Set Attention Block, from the Set Transformers paper
Ag CnnThis is a reimplementation of AG-CNN. ("Thorax Disease Classification with Attention Guided Convolutional Neural Network","Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification")
Pytorch GatMy implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
Chatbot cn基于金融-司法领域(兼有闲聊性质)的聊天机器人,其中的主要模块有信息抽取、NLU、NLG、知识图谱等,并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口
Pointer summarizerpytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"
Awesome Bert NlpA curated list of NLP resources focused on BERT, attention mechanism, Transformer networks, and transfer learning.
Performer PytorchAn implementation of Performer, a linear attention-based transformer, in Pytorch
Moran v2MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition
Nmt KerasNeural Machine Translation with Keras
Keras Self AttentionAttention mechanism for processing sequential data that considers the context for each timestamp.
Awesome Graph ClassificationA collection of important graph embedding, classification and representation learning papers with implementations.
Transformer TtsA Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
Pytorch Original TransformerMy implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
Neural spEnd-to-end ASR/LM implementation with PyTorch
PaperrobotCode for PaperRobot: Incremental Draft Generation of Scientific Ideas
SimgnnA PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).
TransformerA TensorFlow Implementation of the Transformer: Attention Is All You Need
Keras GatKeras implementation of the graph attention networks (GAT) by Veličković et al. (2017; https://arxiv.org/abs/1710.10903)
Yolo Multi Backbones AttentionModel Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization
Seq2seq chatbot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
Alphafold2To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released
AdaptiveattentionImplementation of "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning"
Vit PytorchImplementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Timesformer PytorchImplementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
TransformerA Pytorch Implementation of "Attention is All You Need" and "Weighted Transformer Network for Machine Translation"