Rony Kalfarisi's Projects
This repository holds all the code for the site http://www.adventuresinmachinelearning.com
Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.
A Tensorflow 2 (Keras) implementation of DA-RNN (A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction, arXiv:1704.02971)
Implementation of Deep Patient Representation of Clinical Notes at Intensive Care Unit for Multi-Task Prediction
An open source library for deep learning end-to-end dialog systems and chatbots.
Deep Learning for Time Series Classification
Docker-Compose template for orchestrating a Flask app with a Celery queue using Redis
A Tensorflow Implementation of Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
Structured Edge Detection Toolbox
Code for Document Similarity on Reuters dataset using Encode, Embed, Attend, Predict recipe
This is a test repository
MIMICIII Sepsis Survival Analysis
Categorizing food and grocery products using Transfer Learning from Inception V3
Tensorflow implementation of "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"
Attention mechanism Implementation for Keras.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
MIMIC Code Repository: Code shared by the research community for the MIMIC-III database
Predicting 30-day ICU readmissions from the MIMIC-III database
ML Deployment, Two Ways
Models and examples built with TensorFlow
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
本项目为2018年山东大学第四届“可视计算”暑期学校无人车小组的DIY项目,参考山东大学提出的基于点云的PointCNN点卷积神经网络,使用KITTI数据集对车辆的点云输入进行语义分割,并就划分出的车辆图像进行三维包装盒的预测,以帮助无人车定位车辆的三维位置。
Code and models accompanying "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Config files for my GitHub profile.
Data Science Notebook on a Classification Task, using sklearn and Tensorflow.
Implementation of SqueezeSegV2, Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud