Transformer-MM-Explainability[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
Stars: ✭ 484 (+284.13%)
zennitZennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Stars: ✭ 57 (-54.76%)
transformers-interpretModel explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Stars: ✭ 861 (+583.33%)
ALPS 2021XAI Tutorial for the Explainable AI track in the ALPS winter school 2021
Stars: ✭ 55 (-56.35%)
sageFor calculating global feature importance using Shapley values.
Stars: ✭ 129 (+2.38%)
hierarchical-dnn-interpretationsUsing / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
Stars: ✭ 110 (-12.7%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (-67.46%)
InterpretFit interpretable models. Explain blackbox machine learning.
Stars: ✭ 4,352 (+3353.97%)
knowledge-neuronsA library for finding knowledge neurons in pretrained transformer models.
Stars: ✭ 72 (-42.86%)
adaptive-waveletsAdaptive, interpretable wavelets across domains (NeurIPS 2021)
Stars: ✭ 58 (-53.97%)
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (-62.7%)
removal-explanationsA lightweight implementation of removal-based explanations for ML models.
Stars: ✭ 46 (-63.49%)
ArenaRData generator for Arena - interactive XAI dashboard
Stars: ✭ 28 (-77.78%)
mllpThe code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".
Stars: ✭ 15 (-88.1%)
deep-explanation-penalizationCode for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Stars: ✭ 110 (-12.7%)
ShapA game theoretic approach to explain the output of any machine learning model.
Stars: ✭ 14,917 (+11738.89%)
CaptumModel interpretability and understanding for PyTorch
Stars: ✭ 2,830 (+2146.03%)
policy-data-analyzerBuilding a model to recognize incentives for landscape restoration in environmental policies from Latin America, the US and India. Bringing NLP to the world of policy analysis through an extensible framework that includes scraping, preprocessing, active learning and text analysis pipelines.
Stars: ✭ 22 (-82.54%)
Pytorch Sentiment AnalysisTutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+2446.83%)
BangalASRTransformer based Bangla Speech Recognition
Stars: ✭ 20 (-84.13%)
ercEmotion recognition in conversation
Stars: ✭ 34 (-73.02%)
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 (+1338.89%)
Dalle PytorchImplementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Stars: ✭ 3,661 (+2805.56%)
bangla-bertBangla-Bert is a pretrained bert model for Bengali language
Stars: ✭ 41 (-67.46%)
simple transformersSimple transformer implementations that I can understand
Stars: ✭ 18 (-85.71%)
YunoYuno is context based search engine for anime.
Stars: ✭ 320 (+153.97%)
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 (+2096.83%)
transganformerImplementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper
Stars: ✭ 137 (+8.73%)
HugsVisionHugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (+22.22%)
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 (+4439.68%)
trapperState-of-the-art NLP through transformer models in a modular design and consistent APIs.
Stars: ✭ 28 (-77.78%)
awesome-dynamic-graphsA collection of resources on dynamic/streaming/temporal/evolving graph processing systems, databases, data structures, datasets, and related academic and industrial work
Stars: ✭ 89 (-29.37%)
SimpletransformersTransformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Stars: ✭ 2,881 (+2186.51%)
Spark NlpState of the Art Natural Language Processing
Stars: ✭ 2,518 (+1898.41%)
HVT[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"
Stars: ✭ 26 (-79.37%)
TermiNetwork🌏 A zero-dependency networking solution for building modern and secure iOS, watchOS, macOS and tvOS applications.
Stars: ✭ 80 (-36.51%)
KoBERT-TransformersKoBERT on 🤗 Huggingface Transformers 🤗 (with Bug Fixed)
Stars: ✭ 162 (+28.57%)
OpenDialogAn Open-Source Package for Chinese Open-domain Conversational Chatbot (中文闲聊对话系统,一键部署微信闲聊机器人)
Stars: ✭ 94 (-25.4%)
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 (+1553.97%)
classyclassy is a simple-to-use library for building high-performance Machine Learning models in NLP.
Stars: ✭ 61 (-51.59%)
C-TranGeneral Multi-label Image Classification with Transformers
Stars: ✭ 106 (-15.87%)
isarn-sketches-sparkRoutines and data structures for using isarn-sketches idiomatically in Apache Spark
Stars: ✭ 28 (-77.78%)
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 (+1824.6%)
n-grammer-pytorchImplementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch
Stars: ✭ 50 (-60.32%)
text2textText2Text: Cross-lingual natural language processing and generation toolkit
Stars: ✭ 188 (+49.21%)
Fast BertSuper easy library for BERT based NLP models
Stars: ✭ 1,678 (+1231.75%)
smaller-transformersLoad What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.
Stars: ✭ 66 (-47.62%)
COCO-LM[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Stars: ✭ 109 (-13.49%)
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 (+2605.56%)
text2classMulti-class text categorization using state-of-the-art pre-trained contextualized language models, e.g. BERT
Stars: ✭ 15 (-88.1%)
Reformer PytorchReformer, the efficient Transformer, in Pytorch
Stars: ✭ 1,644 (+1204.76%)
miniconsUtility for analyzing Transformer based representations of language.
Stars: ✭ 28 (-77.78%)
TorchBlocksA PyTorch-based toolkit for natural language processing
Stars: ✭ 85 (-32.54%)
awesome-mobile-roboticsUseful links of different content related to AI, Computer Vision, and Robotics.
Stars: ✭ 243 (+92.86%)