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 (-43.79%)
thermostatCollection of NLP model explanations and accompanying analysis tools
Stars: ✭ 126 (-85.37%)
zennitZennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Stars: ✭ 57 (-93.38%)
mllpThe code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".
Stars: ✭ 15 (-98.26%)
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (-94.54%)
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 (-87.22%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (-95.24%)
InterpretFit interpretable models. Explain blackbox machine learning.
Stars: ✭ 4,352 (+405.46%)
megMolecular Explanation Generator
Stars: ✭ 14 (-98.37%)
ALPS 2021XAI Tutorial for the Explainable AI track in the ALPS winter school 2021
Stars: ✭ 55 (-93.61%)
knowledge-neuronsA library for finding knowledge neurons in pretrained transformer models.
Stars: ✭ 72 (-91.64%)
hierarchical-dnn-interpretationsUsing / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
Stars: ✭ 110 (-87.22%)
Basic-UI-for-GPT-J-6B-with-low-vramA repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.
Stars: ✭ 90 (-89.55%)
transformers-lightningA collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transformers.
Stars: ✭ 45 (-94.77%)
ArenaRData generator for Arena - interactive XAI dashboard
Stars: ✭ 28 (-96.75%)
textUsing Transformers from HuggingFace in R
Stars: ✭ 66 (-92.33%)
RETRO-pytorchImplementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Stars: ✭ 473 (-45.06%)
Ask2TransformersA Framework for Textual Entailment based Zero Shot text classification
Stars: ✭ 102 (-88.15%)
Transformer-in-PyTorchTransformer/Transformer-XL/R-Transformer examples and explanations
Stars: ✭ 21 (-97.56%)
TransQuestTransformer based translation quality estimation
Stars: ✭ 85 (-90.13%)
expmrcExpMRC: Explainability Evaluation for Machine Reading Comprehension
Stars: ✭ 58 (-93.26%)
mmnMoore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
Stars: ✭ 39 (-95.47%)
oreilly-bert-nlpThis repository contains code for the O'Reilly Live Online Training for BERT
Stars: ✭ 19 (-97.79%)
STAM-pytorchImplementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification
Stars: ✭ 109 (-87.34%)
clip-italianCLIP (Contrastive Language–Image Pre-training) for Italian
Stars: ✭ 113 (-86.88%)
awesome-huggingface🤗 A list of wonderful open-source projects & applications integrated with Hugging Face libraries.
Stars: ✭ 436 (-49.36%)
adversarial-robustness-publicCode for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"
Stars: ✭ 49 (-94.31%)
backpropBackprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
Stars: ✭ 229 (-73.4%)
EgoCNNCode for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)
Stars: ✭ 16 (-98.14%)
X-TransformerX-Transformer: Taming Pretrained Transformers for eXtreme Multi-label Text Classification
Stars: ✭ 127 (-85.25%)
transformer generalizationThe official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.
Stars: ✭ 58 (-93.26%)
jax-modelsUnofficial JAX implementations of deep learning research papers
Stars: ✭ 108 (-87.46%)
graspEssential NLP & ML, short & fast pure Python code
Stars: ✭ 58 (-93.26%)
bert attn vizVisualize BERT's self-attention layers on text classification tasks
Stars: ✭ 41 (-95.24%)
Chinese-Minority-PLMCINO: Pre-trained Language Models for Chinese Minority (少数民族语言预训练模型)
Stars: ✭ 133 (-84.55%)
xai-iml-sotaInteresting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
Stars: ✭ 51 (-94.08%)
glcapsnetGlobal-Local Capsule Network (GLCapsNet) is a capsule-based architecture able to provide context-based eye fixation prediction for several autonomous driving scenarios, while offering interpretability both globally and locally.
Stars: ✭ 33 (-96.17%)
naruNeural Relation Understanding: neural cardinality estimators for tabular data
Stars: ✭ 76 (-91.17%)
pysentimientoA Python multilingual toolkit for Sentiment Analysis and Social NLP tasks
Stars: ✭ 274 (-68.18%)
3D-GuidedGradCAM-for-Medical-ImagingThis Repo containes the implemnetation of generating Guided-GradCAM for 3D medical Imaging using Nifti file in tensorflow 2.0. Different input files can be used in that case need to edit the input to the Guided-gradCAM model.
Stars: ✭ 60 (-93.03%)
question generatorAn NLP system for generating reading comprehension questions
Stars: ✭ 188 (-78.16%)
neuro-symbolic-sudoku-solver⚙️ Solving sudoku using Deep Reinforcement learning in combination with powerful symbolic representations.
Stars: ✭ 60 (-93.03%)
kernel-modNeurIPS 2018. Linear-time model comparison tests.
Stars: ✭ 17 (-98.03%)
dlime experimentsIn this work, we propose a deterministic version of Local Interpretable Model Agnostic Explanations (LIME) and the experimental results on three different medical datasets shows the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME).
Stars: ✭ 21 (-97.56%)
KB-ALBERTKB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델
Stars: ✭ 215 (-75.03%)
LIT[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"
Stars: ✭ 79 (-90.82%)
interpretable-mlTechniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.
Stars: ✭ 17 (-98.03%)
responsible-ai-toolboxThis project provides responsible AI user interfaces for Fairlearn, interpret-community, and Error Analysis, as well as foundational building blocks that they rely on.
Stars: ✭ 615 (-28.57%)
nlp workshop odsc europe20Extensive tutorials for the Advanced NLP Workshop in Open Data Science Conference Europe 2020. We will leverage machine learning, deep learning and deep transfer learning to learn and solve popular tasks using NLP including NER, Classification, Recommendation \ Information Retrieval, Summarization, Classification, Language Translation, Q&A and T…
Stars: ✭ 127 (-85.25%)
adaptive-waveletsAdaptive, interpretable wavelets across domains (NeurIPS 2021)
Stars: ✭ 58 (-93.26%)
SnowflakeNet(TPAMI 2022) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
Stars: ✭ 74 (-91.41%)
code-transformerImplementation of the paper "Language-agnostic representation learning of source code from structure and context".
Stars: ✭ 130 (-84.9%)
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 (-74.91%)
XAIatERUM2020Workshop: Explanation and exploration of machine learning models with R and DALEX at eRum 2020
Stars: ✭ 52 (-93.96%)