daveboat Goto Github PK
Name: David Yan
Type: User
Company: Meta
Location: Toronto
Blog: daveboat.github.io
Name: David Yan
Type: User
Company: Meta
Location: Toronto
Blog: daveboat.github.io
Some quick and dirty code which uses gradient ascent to find the input image which maximizes the output probability for a particular class.
A toy model for classification with tensorflow 2.0, for demonstration purposes
D2Go is a toolkit for efficient deep learning
Dave's blog
Denseflow_GPU modified for opencv4 and with simplified operation
Some common functions for personal use
a toy (practice) model for classifying golf clubs
Modeling and simulation of the effect of CW radar on the spin of a golf ball in flight
Google Research
Preparation material for software engineering/machine learning interviews
keras implementation of Faster R-CNN
Lime: Explaining the predictions of any machine learning classifier
An example/toy model demonstrating multitask (multi-head) classification of images using keras
Some directions for compiling opencv on ubuntu 18.04, mostly to remind myself
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Pytorch implementation of RetinaNet object detection.
An implementation of focal loss in pytorch meant to be understandable and easily swappable with nn.functional.cross_entropy and nn.CrossEntropyLoss
A minimal and easy-to-understand implementation of spatial pyramid pooling in pytorch
An implementation of the BINN hierarchical inference head from "Structured Label Inference for Visual Understanding"
A quick example of training a convolutional GAN on MNIST digits
Some directions (mainly for my own use) for how to set up CUDA, CUDnn for deep learning on Ubuntu 18.04
MATLAB code used in the papers "Adaptive Time-stepping Schemes for the Solution of the Poisson-Nernst-Planck Equations" and "A Study of the Numerical Stability of an ImEx Scheme with Application to the Poisson-Nernst-Planck Equations"
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.