Zhuangfang Yi 依庄防's Projects
SegNet model implemented using keras framework
A car detection model implemented in Tensorflow.
A Kitti Road Segmentation model implemented in tensorflow.
Data Preparation for Satellite Machine Learning
Landlab codebase, wiki, and tests
Choropleth plugin for Leaflet (color scale based on value)
Oxford Deep NLP 2017 course
A PyTorch implementation of the Light Temporal Attention Encoder (L-TAE) for satellite image time series. classification
Find me at:
This is the code and data that accompanies a tutorial about how to use R and Mapbox together to map spatial data.
A node.js and browser JavaScript client to Mapbox services
Google Chrome, Firefox, and Thunderbird extension that lets you write email in Markdown and render it before sending.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Code accompanying the book "Machine Learning for Hackers"
Run MapReduce jobs on Hadoop or Amazon Web Services
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Notebooks for MXNet
NAIP WMS xml files for qgis
Shiny application on neighborhood diversity
After a hurricane, roads are often flooded or washed out, making them treacherous for motorists. Using state of the art deep learning methods, I attempted to automatically annotate flooded, washed out, or otherwise severely damaged roads. My goal is create a tool that can help detect and visualize anomalous roads in a simple user interface.
Deep Learning libraries tested on images and time series
Docker container for running JUPYTER Notebook within an ANACONDA environment, exploiting NVIDIA-DOCKER for GPUs
Most popular metrics used to evaluate object detection algorithms.
Recipes for using Python's pandas library
Using computer vision to detect if bike lanes are blocked
TensorFlow implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".
A tool for running deep learning algorithms for semantic segmentation with satellite imagery
Create interactive web graphics from R via plotly's JavaScript graphing library