Transformer-in-TransformerAn Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
Stars: ✭ 40 (-88.27%)
DabData Augmentation by Backtranslation (DAB) ヽ( •_-)ᕗ
Stars: ✭ 294 (-13.78%)
uformer-pytorchImplementation of Uformer, Attention-based Unet, in Pytorch
Stars: ✭ 54 (-84.16%)
tutelTutel MoE: An Optimized Mixture-of-Experts Implementation
Stars: ✭ 183 (-46.33%)
PyhgtCode for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric
Stars: ✭ 313 (-8.21%)
php-halHAL+JSON & HAL+XML API transformer outputting valid (PSR-7) API Responses.
Stars: ✭ 30 (-91.2%)
SwinIRSwinIR: Image Restoration Using Swin Transformer (official repository)
Stars: ✭ 1,260 (+269.5%)
TadTREnd-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]
Stars: ✭ 55 (-83.87%)
EmbeddingEmbedding模型代码和学习笔记总结
Stars: ✭ 25 (-92.67%)
SIGIR2021 ConureOne Person, One Model, One World: Learning Continual User Representation without Forgetting
Stars: ✭ 23 (-93.26%)
Restormer[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
Stars: ✭ 586 (+71.85%)
Contextualized Topic ModelsA python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.
Stars: ✭ 318 (-6.74%)
Walk-TransformerFrom Random Walks to Transformer for Learning Node Embeddings (ECML-PKDD 2020) (In Pytorch and Tensorflow)
Stars: ✭ 26 (-92.38%)
bert-as-a-service TFXEnd-to-end pipeline with TFX to train and deploy a BERT model for sentiment analysis.
Stars: ✭ 32 (-90.62%)
golgothaContextualised Embeddings and Language Modelling using BERT and Friends using R
Stars: ✭ 39 (-88.56%)
TransformerEasy Attributed String Creator
Stars: ✭ 278 (-18.48%)
TS-CAMCodes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.
Stars: ✭ 96 (-71.85%)
saintThe official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
Stars: ✭ 209 (-38.71%)
text2keywordsTrained T5 and T5-large model for creating keywords from text
Stars: ✭ 53 (-84.46%)
Locomotive Scroll🛤 Detection of elements in viewport & smooth scrolling with parallax.
Stars: ✭ 4,231 (+1140.76%)
CSV2RDFStreaming, transforming, SPARQL-based CSV to RDF converter. Apache license.
Stars: ✭ 48 (-85.92%)
TransformerImplementation of Transformer model (originally from Attention is All You Need) applied to Time Series.
Stars: ✭ 273 (-19.94%)
HRFormerThis is an official implementation of our NeurIPS 2021 paper "HRFormer: High-Resolution Transformer for Dense Prediction".
Stars: ✭ 357 (+4.69%)
Vision-Language-TransformerVision-Language Transformer and Query Generation for Referring Segmentation (ICCV 2021)
Stars: ✭ 127 (-62.76%)
Filipino-Text-BenchmarksOpen-source benchmark datasets and pretrained transformer models in the Filipino language.
Stars: ✭ 22 (-93.55%)
OverlapPredator[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
Stars: ✭ 293 (-14.08%)
Remi"Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions", ACM Multimedia 2020
Stars: ✭ 273 (-19.94%)
momentumTrack movement and basic events with CSS custom properties
Stars: ✭ 19 (-94.43%)
attention-is-all-you-need-paperImplementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.
Stars: ✭ 97 (-71.55%)
Cognitive Speech TtsMicrosoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
Stars: ✭ 312 (-8.5%)
neodigm55An eclectic low-code vanilla JavaScript UX micro-library for those that defiantly think for themselves.
Stars: ✭ 14 (-95.89%)
pynmta simple and complete pytorch implementation of neural machine translation system
Stars: ✭ 13 (-96.19%)
graphtransRepresenting Long-Range Context for Graph Neural Networks with Global Attention
Stars: ✭ 45 (-86.8%)
AllrankallRank is a framework for training learning-to-rank neural models based on PyTorch.
Stars: ✭ 269 (-21.11%)
XpersonaXPersona: Evaluating Multilingual Personalized Chatbot
Stars: ✭ 54 (-84.16%)
PDNThe official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Stars: ✭ 44 (-87.1%)
Transformer TensorflowTensorFlow implementation of 'Attention Is All You Need (2017. 6)'
Stars: ✭ 319 (-6.45%)
Transformer-ocrHandwritten text recognition using transformers.
Stars: ✭ 92 (-73.02%)
Perspective🖼Parallax scrolling effect. And more.
Stars: ✭ 80 (-76.54%)
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (+140.76%)
Nlp Interview Notes本项目是作者们根据个人面试和经验总结出的自然语言处理(NLP)面试准备的学习笔记与资料,该资料目前包含 自然语言处理各领域的 面试题积累。
Stars: ✭ 207 (-39.3%)
YOLOv5-Lite🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Stars: ✭ 1,230 (+260.7%)
scrollxpAlpine.js-esque library for scrolling animations on websites
Stars: ✭ 50 (-85.34%)
transformerA PyTorch Implementation of "Attention Is All You Need"
Stars: ✭ 28 (-91.79%)
amrlibA python library that makes AMR parsing, generation and visualization simple.
Stars: ✭ 107 (-68.62%)
SOLQ"SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.
Stars: ✭ 159 (-53.37%)
FancyscrollviewA SwiftUI ScrollView Designed to imitate the App Store and Apple Music ScrollViews (with or without a Parallax Header)
Stars: ✭ 330 (-3.23%)
RezeroOfficial PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"
Stars: ✭ 317 (-7.04%)
VedastrA scene text recognition toolbox based on PyTorch
Stars: ✭ 290 (-14.96%)
bert in a flaskA dockerized flask API, serving ALBERT and BERT predictions using TensorFlow 2.0.
Stars: ✭ 32 (-90.62%)