Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

Train and visualize Hierarchical Attention Networks

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

Plot the vector graph of attention based text visualisation

Comparatively fine-tuning pretrained BERT models on downstream, text classification tasks with different architectural configurations in PyTorch.

Visualization for simple attention and Google's multi-head attention.

(ECCV 2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks

attention mechanism in keras, like Dense and RNN...

Lightweight visualization tool for neural attention mechanisms

PyTorch implementation of MTA-LSTM

PyTorch implementation of the End-to-End Memory Network with attention layer vizualisation support.

my codes for learning attention mechanism

Visual Attention based OCR

classifying patient illness by nurse notes

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.