eltoto1219 Goto Github PK

angular-scouting

FIRST Scouting web app from Yeti Robotics

bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

bottom-up-top-down-vqa

This is a replication of the winning 2017 VQA model. This project more specifically investigates how different weight normalization techniques and the use of different parameter optimizers effect overall validation performance

comp426final

cs224-nlp-course

CS224n: Natural Language Processing with Deep Learning Course Projects

eltoto1219.github.io

halonet-pytorch

Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones

logo-classifier

lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

material-design-lite

Material Design Components in HTML/CSS/JS

mirna-workflow

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

multimodal-pretraining

nlp

🤗nlp – Datasets and evaluation metrics for Natural Language Processing in NumPy, Pandas, PyTorch and TensorFlow

nlp1-2017-vqa

py-bottom-up-attention

PyTorch bottom-up attention with Detectron2

qa-world

qtl-analysis

In This QTL Analyis, we studied the Wergedal 2006 dataset. The purpose for this study was to Identify QTL regions that help regulate femur mechanical properties, geometric properties, and BMD.

recurrent-neuralnetwork-

The goal of this model is to experiment with how well a basic Recurrent Neural Network with Long-Short-Term-Memory cells can predict the daily adjusted daily closing prices for the company Tesla in December of 2016.

remote-control-files

Repo where I can continuously save/customize my rc files for bash and vim and encrypt credentials for ease of working on different servers

software-product-sprint

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

trasformer

Architecture from "Attention is all you need" on an English to Vietnamese dataset

vltk

A toolkit for vision-language processing to support the increasing popularity of mulit-modal transformer-based models