GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → jason71995 → Keras_ODENet

jason71995 / Keras_ODENet

Licence: other
Implementation of (2018) Neural Ordinary Differential Equations on Keras

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningneural-networkkerasneural-ode

Projects that are alternatives of or similar to Keras ODENet

sciml.ai
The SciML Scientific Machine Learning Software Organization Website
Stars: ✭ 38 (-33.33%)
Mutual labels:  neural-ode
DiffEqParamEstim.jl
Easy scientific machine learning (SciML) parameter estimation with pre-built loss functions
Stars: ✭ 36 (-36.84%)
Mutual labels:  neural-ode
SciMLBenchmarks.jl
Benchmarks for scientific machine learning (SciML) software and differential equation solvers
Stars: ✭ 195 (+242.11%)
Mutual labels:  neural-ode
DiffEqGPU.jl
GPU-acceleration routines for DifferentialEquations.jl and the broader SciML scientific machine learning ecosystem
Stars: ✭ 131 (+129.82%)
Mutual labels:  neural-ode
LatentDiffEq.jl
Latent Differential Equations models in Julia.
Stars: ✭ 34 (-40.35%)
Mutual labels:  neural-ode
LPDC-Net
CVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"
Stars: ✭ 27 (-52.63%)
Mutual labels:  neural-ode
DiffEqSensitivity.jl
A component of the DiffEq ecosystem for enabling sensitivity analysis for scientific machine learning (SciML). Optimize-then-discretize, discretize-then-optimize, and more for ODEs, SDEs, DDEs, DAEs, etc.
Stars: ✭ 186 (+226.32%)
Mutual labels:  neural-ode
CRNN
Chemical Reaction Neural Network
Stars: ✭ 43 (-24.56%)
Mutual labels:  neural-ode
BoundaryValueDiffEq.jl
Boundary value problem (BVP) solvers for scientific machine learning (SciML)
Stars: ✭ 23 (-59.65%)
Mutual labels:  neural-ode
DiffEqCallbacks.jl
A library of useful callbacks for hybrid scientific machine learning (SciML) with augmented differential equation solvers
Stars: ✭ 43 (-24.56%)
Mutual labels:  neural-ode
MultiScaleArrays.jl
A framework for developing multi-scale arrays for use in scientific machine learning (SciML) simulations
Stars: ✭ 63 (+10.53%)
Mutual labels:  neural-ode

Neural Ordinary Differential Equations in Keras

Introduction

Implementation of (2018) Neural Ordinary Differential Equations.

Attention

ODE solver are use tf.contrib.integrate.odeint which only supported "dopri5" method now.

Environment

GPU: Nvidia GTX 670

python==3.6
tensorflow==1.4.0
keras==2.1.0

Result

Result on 10 epochs

MNIST ODENet

training time: 730s

train_loss: 0.0112 - train_acc: 0.9962 - val_loss: 0.0234 - val_acc: 0.9929

MNIST ResNet

training time: 120s

train_loss: 0.0096 - train_acc: 0.9968 - val_loss: 0.0307 - val_acc: 0.9908

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].