🚀 Cross attention map tools for huggingface/diffusers

Tools for eye data processing, analysis, and visualisation, in R.

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

CLIP GUI - XAI app ~ explainable (and guessable) AI with ViT & ResNet models

Explainable AI, attention visualization in LLM

In the dynamic landscape of medical artificial intelligence, this study explores the vulnerabilities of the Pathology Language-Image Pretraining (PLIP) model, a Vision Language Foundation model, under targeted attacks like PGD adversarial attack.

Visualizing query-key interactions in language + vision transformers

KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

Attention weight visualisation for sentiment analysis.

Implementation of Visual Attention (ViT) for Image Classification using pytorch

Get CLIP ViT text tokens about an image, visualize attention as a heatmap.

Easy-to-read implementation of self-supervised learning using vision transformer and knowledge distillation with no labels - DINO 😃

Extract explainablity from RoBERTa 🪆 ad Born 🐈 while classifying depresson 🎭

Implementation of GRU-based Encoder-Decoder Architecture with Bahdanau Attention Mechanism for Machine Translation from German to English.

Shopify-Pipedrive Integration This project provides a JavaScript program that integrates Shopify and Pipedrive, allowing you to automate the process of creating deals in Pipedrive based on Shopify orders. The program follows a series of steps to fetch data from Shopify and Pipedrive, create or update records, and establish connections between them.

Implemented image caption generation method propossed in Show, Attend, and Tell paper using the Fastai framework to describe the content of images. Achieved 24 BLEU score for Beam search size of 5. Designed a Web application for model deployment using the Flask framework.

Encoder-Decoder CNN-LSTM Model with an attention mechanism for image captioning. Trained using the Microsoft COCO Dataset.

Transfer learning pretrained vision transformers for breast histopathology

This project presents Attention-enhanced Multi-channel Recurrent Convolutional Network (AMRCN), for explainable fake news detection.