STAM-pytorchImplementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification
Stars: ✭ 109 (+21.11%)
RETRO-pytorchImplementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Stars: ✭ 473 (+425.56%)
keras-deep-learningVarious implementations and projects on CNN, RNN, LSTM, GAN, etc
Stars: ✭ 22 (-75.56%)
Vit PytorchImplementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Stars: ✭ 7,199 (+7898.89%)
Reformer PytorchReformer, the efficient Transformer, in Pytorch
Stars: ✭ 1,644 (+1726.67%)
nuwa-pytorchImplementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch
Stars: ✭ 347 (+285.56%)
Dalle PytorchImplementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Stars: ✭ 3,661 (+3967.78%)
long-short-transformerImplementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch
Stars: ✭ 103 (+14.44%)
transganformerImplementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper
Stars: ✭ 137 (+52.22%)
C3D-tensorflowAction recognition with C3D network implemented in tensorflow
Stars: ✭ 34 (-62.22%)
Transformers-RLAn easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"
Stars: ✭ 107 (+18.89%)
LSTM-AttentionA Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series
Stars: ✭ 53 (-41.11%)
lstm-attentionAttention-based bidirectional LSTM for Classification Task (ICASSP)
Stars: ✭ 87 (-3.33%)
MinkLocMultimodalMinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
Stars: ✭ 65 (-27.78%)
nlp-papersMust-read papers on Natural Language Processing (NLP)
Stars: ✭ 87 (-3.33%)
Nlp ArchitectA model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks
Stars: ✭ 2,768 (+2975.56%)
textUsing Transformers from HuggingFace in R
Stars: ✭ 66 (-26.67%)
Transformer-in-PyTorchTransformer/Transformer-XL/R-Transformer examples and explanations
Stars: ✭ 21 (-76.67%)
Pytorch Sentiment AnalysisTutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+3465.56%)
Nn🧑🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Stars: ✭ 5,720 (+6255.56%)
SimpletransformersTransformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Stars: ✭ 2,881 (+3101.11%)
TransmogrifaiTransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Apache Spark with minimal hand-tuning
Stars: ✭ 2,084 (+2215.56%)
SnowflakeNet(TPAMI 2022) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
Stars: ✭ 74 (-17.78%)
TransQuestTransformer based translation quality estimation
Stars: ✭ 85 (-5.56%)
gplPowerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
Stars: ✭ 216 (+140%)
question-generationNeural Models for Key Phrase Detection and Question Generation
Stars: ✭ 29 (-67.78%)
MiCT-Net-PyTorchVideo Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone
Stars: ✭ 48 (-46.67%)
Fengshenbang-LMFengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。
Stars: ✭ 1,813 (+1914.44%)
conv3d-video-action-recognitionMy experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves result…
Stars: ✭ 50 (-44.44%)
DARNNA Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
Stars: ✭ 90 (+0%)
memory-compressed-attentionImplementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"
Stars: ✭ 47 (-47.78%)
COCO-LM[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Stars: ✭ 109 (+21.11%)
UniFormer[ICLR2022] official implementation of UniFormer
Stars: ✭ 574 (+537.78%)
TA3N[ICCV 2019 Oral] TA3N: https://github.com/cmhungsteve/TA3N (Most updated repo)
Stars: ✭ 45 (-50%)
clip-italianCLIP (Contrastive Language–Image Pre-training) for Italian
Stars: ✭ 113 (+25.56%)
Fast BertSuper easy library for BERT based NLP models
Stars: ✭ 1,678 (+1764.44%)
amta-netAsymmetric Multi-Task Attention Network for Prostate Bed Segmentation in CT Images
Stars: ✭ 26 (-71.11%)
Spark NlpState of the Art Natural Language Processing
Stars: ✭ 2,518 (+2697.78%)
Optic-Disc-UnetAttention Unet model with post process for retina optic disc segmention
Stars: ✭ 77 (-14.44%)
Clue中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Stars: ✭ 2,425 (+2594.44%)
SA-DLSentiment Analysis with Deep Learning models. Implemented with Tensorflow and Keras.
Stars: ✭ 35 (-61.11%)
ChangeFormerOfficial PyTorch implementation of our IGARSS'22 paper: A Transformer-Based Siamese Network for Change Detection
Stars: ✭ 220 (+144.44%)
NARREThis is our implementation of NARRE:Neural Attentional Regression with Review-level Explanations
Stars: ✭ 100 (+11.11%)
naruNeural Relation Understanding: neural cardinality estimators for tabular data
Stars: ✭ 76 (-15.56%)
Haystack🔍 Haystack is an open source NLP framework that leverages Transformer models. It enables developers to implement production-ready neural search, question answering, semantic document search and summarization for a wide range of applications.
Stars: ✭ 3,409 (+3687.78%)
Im2LaTeXAn implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem
Stars: ✭ 16 (-82.22%)
Tokenizers💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
Stars: ✭ 5,077 (+5541.11%)
CogViewText-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
Stars: ✭ 708 (+686.67%)
stconvs2sCode for the paper "STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for Weather Forecasting" (Neurocomputing, Elsevier)
Stars: ✭ 40 (-55.56%)
KB-ALBERTKB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델
Stars: ✭ 215 (+138.89%)
VQGAN-CLIP-DockerZero-Shot Text-to-Image Generation VQGAN+CLIP Dockerized
Stars: ✭ 58 (-35.56%)
hashformersHashformers is a framework for hashtag segmentation with transformers.
Stars: ✭ 18 (-80%)
LIT[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"
Stars: ✭ 79 (-12.22%)