14 results found Sort:

imperial-qore
TranAD imperial-qore
163
550
bsd-3-clause
11
[VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.
anomaly-detection transformer-models adversarial-learning multi-head-attention unsupervised-learning
Created 2021-03-01
110 commits to main branch, last one about a year ago
sooftware
attentions sooftware
71
520
mit
3
PyTorch implementation of some attentions for Deep Learning Researchers.
pytorch attention additive-attention multi-head-attention dot-product-attention location-aware-attention location-sensitive-attension relative-positional-encoding relative-multi-head-attention
Created 2020-03-21
89 commits to master branch, last one 2 years ago
anicolson
DeepXi anicolson
127
503
mpl-2.0
25
Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.
tcn mmse keras deepxi mhanet resnet deep-xi deepmmse mmse-lsa attention robust-asr tensorflow noise-estimation residual-networks source-separation speech-separation speech-enhancement multi-head-attention a-priori-snr-estimator minimum-mean-square-error
Created 2018-05-25
425 commits to master branch, last one 2 years ago
poloclub
dodrio poloclub
33
352
mit
6
Exploring attention weights in transformer-based models with linguistic knowledge.
nlp transformer deep-learning visualization attention-mechanism multi-head-attention interactive-visualizations
Created 2020-10-30
186 commits to master branch, last one about a year ago
Rintarooo
VRP_DRL_MHA Rintarooo
38
180
mit
2
"Attention, Learn to Solve Routing Problems!"[Kool+, 2019], Capacitated Vehicle Routing Problem solver
vrp pytorch reinforce tensorflow policy-gradient multi-head-attention deep-reinforcement-learning capacitated-vehicle-routing-problem
Created 2020-06-24
89 commits to master branch, last one 4 years ago
monk1337
Various-Attention-mechanisms monk1337
25
124
unknown
6
This repository contain various types of attention mechanism like Bahdanau , Soft attention , Additive Attention , Hierarchical Attention etc in Pytorch, Tensorflow, Keras
keras pytorch attention attention-lstm self-attention attention-model luong-attention attention-network bahdanau-attention sentence-attention attention-mechanism attention-mechanisms multi-head-attention hierarchical-attention scaled-dot-product-attention
Created 2018-07-04
59 commits to master branch, last one 3 years ago
datnnt1997
multi-head_self-attention datnnt1997
16
71
unknown
1
A Faster Pytorch Implementation of Multi-Head Self-Attention
attention multi-head self-attention attention-mechanism multihead-attention multi-head-attention transformer-attention pytorch-self-attention multihead-self-attention multi-head-self-attention
Created 2020-07-28
6 commits to master branch, last one 2 years ago
youngbin-ro
Multi2OIE youngbin-ro
18
56
mit
5
Multi^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT (Findings of ACL: EMNLP 2020)
bert multilingualism sequence-labeling multi-head-attention information-extraction open-information-extraction
Created 2020-09-17
24 commits to master branch, last one 2 years ago
JacobHanimann
scDINO JacobHanimann
9
47
apache-2.0
4
Self-Supervised Vision Transformers for multiplexed imaging datasets
morphology phenotyping single-cell unsupervised multi-channel greyscale-image vision-transformer multi-head-attention high-content-screening self-supervised-learning fluorescence-microscopy-imaging
Created 2023-01-16
33 commits to master branch, last one 7 months ago
knotgrass
attention knotgrass
10
44
unknown
3
several types of attention modules written in PyTorch for learning purposes
pytorch attention transformer transformers softmax-layer attention-mechanism multi-head-attention multi-query-attention grouped-query-attention scale-dot-product-attention
Created 2023-06-28
45 commits to main branch, last one 4 months ago
engelnico
point-transformer engelnico
8
39
unknown
3
This is the official repository of the original Point Transformer architecture.
pytorch sortnet modelnet modelnet40 transformer segmentation shapenetpart deep-learning 3d-point-cloud 3d-pointclouds classification 3d-segmentation modelnet-dataset shapenet-dataset 3d-classification attention-mechanism multi-head-attention transformer-architecture
Created 2021-08-24
9 commits to main branch, last one 2 years ago
Bruce-Lee-LY
flash_attention_inference Bruce-Lee-LY
3
34
bsd-3-clause
1
Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
gpu llm mha cuda nvidia cutlass inference tensor-core flash-attention flash-attention-2 large-language-model multi-head-attention
Created 2023-08-16
1 commits to master branch, last one 4 months ago
IParraMartin
An-Explanation-Is-All-You-Need IParraMartin
1
32
unknown
2
The original transformer implementation from scratch. It contains informative comments on each block
ai gpt nlp gpt-2 gpt-3 gpt-4 pytorch begginers transformer translation deep-learning language-model machine-learning begginer-friendly attention-mechanism multi-head-attention artificial-intelligence
Created 2024-06-15
41 commits to main branch, last one 7 months ago
Bruce-Lee-LY
decoding_attention Bruce-Lee-LY
1
27
bsd-3-clause
2
Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
gpu llm mha cuda nvidia cuda-core inference flashinfer flash-attention decoding-attention large-language-model multi-head-attention
Created 2024-08-14
1 commits to master branch, last one 2 months ago