Search Results - RepositoryStats

769

7.7k

mit

81

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

gpt tts vall-e voice-clone text-to-speech emotional-speech transformer-architecture

Created 2023-07-29

137 commits to master branch, last one about a year ago

Awesome-Transformer-Attention cmhungsteve

490

4.7k

unknown

130

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

vit detr papers transformer awesome-list transformers deep-learning self-attention transformer-cv computer-vision transformer-models vision-transformer visual-transformer attention-mechanism transformer-awesome transformer-with-cv attention-mechanisms transformer-architecture

Created 2021-09-15

1,600 commits to main branch, last one 4 months ago

llama2.mojo tairov

141

2.1k

mit

28

Inference Llama 2 in one file of pure 🔥

mojo simd llama llama2 tensor modular inference parallelize performance vectorization transformer-architecture

Created 2023-09-10

124 commits to master branch, last one 7 months ago

spago nlpodyssey

86

1.8k

bsd-2-clause

39

Self-contained Machine Learning and Natural Language Processing library in Go

nlp bart bert lstm deeplearning deep-learning language-model neural-network bert-as-service machine-learning computation-graph question-answering recurrent-networks automatic-translation artificial-intelligence transformer-architecture automatic-differentiation named-entities-recognition natural-language-processing

Created 2020-01-05

2,161 commits to main branch, last one 11 months ago

sockeye awslabs

323

1.2k

apache-2.0

50

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

pytorch seq2seq sockeye transformer translation deep-learning attention-model encoder-decoder machine-learning attention-mechanism machine-translation transformer-network deep-neural-networks sequence-to-sequence transformer-architecture attention-is-all-you-need neural-machine-translation sequence-to-sequence-models

Created 2017-06-08

836 commits to main branch, last one about a month ago

CRATE Ma-Lab-Berkeley

96

1.2k

mit

21

Code for CRATE (Coding RAte reduction TransformEr).

compression sparsification white-box-architecture transformer-architecture

Created 2023-05-29

79 commits to main branch, last one 4 months ago

swin-transformer-pytorch berniwal

128

807

mit

10

Implementation of the Swin Transformer in PyTorch.

pytorch deep-learning attention-model machine-learning transformer-pytorch artificial-intelligence transformer-architecture

Created 2021-03-27

20 commits to master branch, last one 3 years ago

generative-ai genieincodebottle

178

715

mit

15

Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.

ai llm gpt-4 llama llmops openai gemini-api generativeai genai-chatbot genai-roadmap generative-ai generative-ai-tools generativeaichatapp large-language-models generative-ai-projects transformer-architecture generative-ai-architecture

Created 2024-01-09

345 commits to main branch, last one 19 hours ago

joeynmt joeynmt

213

682

apache-2.0

16

Minimalist NMT for educational purposes

nmt seq2seq joey-nmt education rnn-pytorch transformer nmt-tutorial nmt-frameworks seq2seq-pytorch machine-translation pytorch-transformers transformer-architecture neural-machine-translation

Created 2018-10-15

904 commits to main branch, last one 11 months ago

Illumination-Adaptive-Transformer cuiziteng

44

492

apache-2.0

6

🌕 [BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-pro...

bmvc pytorch low-level-vision image-enhancement image-restoration low-light-enhance transformer-models exposure-correction image-reconstruction transformer-architecture low-light-image-enhancement

Created 2021-12-08

311 commits to main branch, last one 9 months ago

CPT fastnlp

73

482

unknown

5

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

ptms chinese text-generation pretrained-models language-understanding transformer-architecture

Created 2021-08-25

26 commits to master branch, last one about a year ago

maxvit google-research

31

453

apache-2.0

9

[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...

cnn mlp image resnet transformer architecture segmentation classification computer-vision image-processing object-detection vision-transformer transformer-architecture

This repository has been archived (exclude archived)

Created 2022-07-07

14 commits to main branch, last one about a year ago

ChangeFormer wgcban

58

444

mit

3

[IGARSS'22]: A Transformer-Based Siamese Network for Change Detection

pytorch deep-learning climate-change multi-temporal remote-sensing siamese-network change-detection satellite-imagery attention-mechanism transformer-encoder transformer-architecture

Created 2021-12-02

234 commits to main branch, last one 10 months ago

MultiModalMamba kyegomez

24

440

mit

9

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.

ai ml ssm zeta mamba torch pytorch transformers machine-learning attention-mechanism artificial-intelligence transformer-architecture

Created 2024-01-04

46 commits to main branch, last one 9 months ago

Deep-Learning-Specialization-Coursera abdur75648

354

421

apache-2.0

7

This repo contains the updated version of all the assignments/labs (done by me) of Deep Learning Specialization on Coursera by Andrew Ng. It includes building various deep learning models from scratch...

Created 2021-10-28

116 commits to main branch, last one about a year ago

ET-BERT linwhitehat

82

392

mit

4

The repository of ET-BERT, a network traffic classification model on encrypted traffic. The work has been accepted as The Web Conference (WWW) 2022 accepted paper.

pytorch pre-training burst-analysis mask-burst-modeling transformer-architecture encrypted-traffic-analysis same-origin-burst-prediction

Created 2022-02-09

133 commits to main branch, last one 7 days ago

SeqFormer wjf5203

31

345

other

7

SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)

transformer-architecture video-instance-segmentation

Created 2021-12-15

18 commits to main branch, last one 2 years ago

PyContinual ZixuanKe

62

302

unknown

8

PyContinual (An Easy and Extendible Framework for Continual Learning)

capsule-network transfer-learning continual-learning knowledge-transfer attention-mechanism text-classification catastrophic-forgetting transformer-architecture natural-language-processing

Created 2021-06-04

27 commits to main branch, last one 10 months ago

multigraph_transformer PengBoXiangShang

32

293

mit

7

IEEE TNNLS 2021, transformer, multi-graph transformer, graph, graph classification, sketch recognition, sketch classification, free-hand sketch, official code of the paper "Multi-Graph Transformer fo...

graph sketch pytorch transformer sparse-graphs sketch-recognition pytorch-implementation multi-graph-transformer transformer-architecture

Created 2019-12-16

75 commits to master branch, last one 3 years ago

a-PyTorch-Tutorial-to-Transformers sgrvinod

48

276

mit

7

Attention Is All You Need | a PyTorch Tutorial to Transformers

pytorch transformer pytorch-tutorial transformer-tutorial transformer-architecture attention-is-all-you-need

Created 2020-01-30

19 commits to master branch, last one about a year ago

ContinualLM UIC-Liu-Lab

19

262

unknown

11

An Extensible Continual Learning Framework Focused on Language Models (LMs)

language-model language-modeling transfer-learning continual-learning knowledge-transfer catastrophic-forgetting transformer-architecture domain-adaptive-pretraining natural-language-processing

Created 2023-02-12

10 commits to main branch, last one 10 months ago

transformer-from-scratch-notes hkproj

53

229

unknown

3

Notes about "Attention is all you need" video (https://www.youtube.com/watch?v=bCz4OMemCcA)

notes study-notes transformer attention-model transformer-architecture attention-is-all-you-need

Created 2023-05-25

6 commits to main branch, last one about a year ago

Seq2SeqSharp zhongkaifu

39

200

other

23

Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transfo...

gpu cuda lstm text image tensor seq2seq transformer translation deep-learning neural-network attention-model encoder-decoder vision-transformer machine-translation transformer-encoder sequence-to-sequence transformer-architecture

Created 2018-06-26

698 commits to master branch, last one 3 days ago

ernie labteral

31

199

apache-2.0

7

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

nlp bert keras albert roberta bert-model distilbert tensorflow bert-models huggingface tensorflow2 transformers bert-as-service bert-embeddings huggingface-transformer sentence-classification transformer-tensorflow2 transformer-architecture natural-language-processing

Created 2020-02-14

115 commits to master branch, last one 7 months ago

pytorch-psetae VSainteuf

42

192

mit

3

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

cvpr pytorch cvpr2020 agriculture deep-learning remote-sensing self-attention computer-vision satellite-image spatio-temporal machine-learning earth-observation transformer-architecture time-series-classification

Created 2019-11-18

25 commits to master branch, last one 2 years ago

TextAugmentation-GPT2 prakhar21

43

189

mit

7

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

gpt-2 text-augmentation textclassification nlp-machine-learning transformer-architecture natural-language-generation natural-language-processing

Created 2020-01-29

23 commits to master branch, last one 4 years ago

TransMEF miccaiif

17

159

unknown

7

Official PyTorch implementation of our AAAI22 paper: TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework via Self-Supervised Multi-Task Learning.

aaai2022 multi-exposure-fusion pytorch-implementation self-supervised-learning transformer-architecture

Created 2021-12-02

38 commits to main branch, last one 2 years ago

LongRoPE jshuadvd

14

126

unknown

6

Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper

ai gpt llm nlp natural tokenizers tokenization transformers deep-learning language-model machine-learning attention-mechanisms artificial-intelligence transformer-architecture attention-is-all-you-need natural-language-inference natural-language-processing natural-language-procressing natural-language-understanding

Created 2024-03-06

266 commits to master branch, last one 5 months ago

BA-Transformer jcwang123

21

124

unknown

1

[MICCAI 2021] Boundary-aware Transformers for Skin Lesion Segmentation

miccai pytorch skin-lesion-segmentation transformer-architecture

Created 2021-07-12

43 commits to main branch, last one 2 years ago

mmwave-gesture-recognition vilari-mickopf

21

121

mit

5

Basic Gesture Recognition Using mmWave Sensor - TI AWR1642

ai lstm keras conv1d conv2d mmwave python resnet awr1642 tensorflow mmwave-sensor neural-network machine-learning texas-instruments gesture-recognition transformer-architecture

Created 2019-09-12

82 commits to master branch, last one 3 months ago