Non-stationary GP package written from scratch in PyTorch

Last update: Mar 06, 2022

Related tags

Deep Learning nsgptorch

Overview

NSGP-Torch

Examples

`gpytorch` model with `skgpytorch`

# Import packages
import torch
from regdata import NonStat2D
from gpytorch.kernels import RBFKernel, ScaleKernel
from skgpytorch.models import ExactGPRegressor
from skgpytorch.metrics import mean_squared_error

# Hyperparameters
n_iters = 100

# Load data
datafunc = NonStat2D(backend="torch")
X_train, y_train, X_test = map(lambda x: x.to(torch.float32), datafunc.get_data())
y_test = datafunc.f(X_test[:, 0], X_test[:, 1]).to(torch.float32)

# Define a kernel
kernel = ScaleKernel(RBFKernel(ard_num_dims=X_train.shape[1]))

# Define a model 
model = ExactGPRegressor(X_train, y_train, kernel, device='cpu')

# Train the model
model.fit(n_iters=n_iters, random_state=seed)

# Predict the distribution
pred_dist = model.predict(X_train, y_train, X_test)

# Compute RMSE and/or NLPD
mse = mean_squared_error(pred_dist, y_test, squared=False)
nlpd = neg_log_posterior_density(pred_dist, y_test)

`nsgptorch` model with `skgpytorch`

# Import packages
import torch
from regdata import NonStat2D

from nsgptorch.kernels import rbf

from skgpytorch.models import ExactNSGPRegressor
from skgpytorch.metrics import mean_squared_error

# Hyperparameters
n_iters = 100

# Load data
datafunc = NonStat2D(backend="torch")
X_train, y_train, X_test = map(lambda x: x.to(torch.float32), datafunc.get_data())
y_test = datafunc.f(X_test[:, 0], X_test[:, 1]).to(torch.float32)

# Define a kernel list for each dimension
kernel_list = [rbf, rbf]

# Define inducing points for each dimension (must be none if not applicable)
inducing_points = [None, None]

# Define a model 
model = ExactNSGPRegressor(kernel_list, input_dim=2, inducing_points, device='cpu')

# Train the model
model.fit(X_train, y_train, n_iters=n_iters, random_state=seed)

# Predict the distribution
pred_dist = model.predict(X_train, y_train, X_test)

# Compute RMSE and/or NLPD
mse = mean_squared_error(pred_dist, y_test, squared=False)
nlpd = neg_log_posterior_density(pred_dist, y_test)

Plan

Each kernel is 1D
Multiply kernels to each other

Ideas

Compute distance once and save it
Update skgpytorch to use 1 std instead of 0.1
Do something about mean learning of gpytorch for comparison

Keras like implementation of Deep Learning architectures from scratch using numpy.

Mini-Keras Keras like implementation of Deep Learning architectures from scratch using numpy. How to contribute? The project contains implementations

5 Oct 10, 2021

This repo is to be freely used by ML devs to check the GAN performances without coding from scratch.

GANs for Fun Created because I can! GOAL The goal of this repo is to be freely used by ML devs to check the GAN performances without coding from scrat

13 Jan 26, 2022

Train a state-of-the-art yolov3 object detector from scratch!

TrainYourOwnYOLO: Building a Custom Object Detector from Scratch This repo let's you train a custom image detector using the state-of-the-art YOLOv3 c

616 Jan 8, 2023

ML From Scratch

ML from Scratch MACHINE LEARNING TOPICS COVERED - FROM SCRATCH Linear Regression Logistic Regression K Means Clustering K Nearest Neighbours Decision

66 Nov 2, 2022

In this project, we create and implement a deep learning library from scratch.

ARA In this project, we create and implement a deep learning library from scratch. Table of Contents Deep Leaning Library Table of Contents About The

22 Aug 23, 2022

Create and implement a deep learning library from scratch.

In this project, we create and implement a deep learning library from scratch. Table of Contents Deep Leaning Library Table of Contents About The Proj

22 Aug 23, 2022

AbelNN: Deep Learning Python module from scratch

AbelNN: Deep Learning Python module from scratch I have implemented several neural networks from scratch using only Numpy. I have designed the module

2 Apr 12, 2022

Weighted K Nearest Neighbors (kNN) algorithm implemented on python from scratch.

kNN_From_Scratch I implemented the k nearest neighbors (kNN) classification algorithm on python. This algorithm is used to predict the classes of new

1 Dec 14, 2021

Controlling the MicriSpotAI robot from scratch

Project-MicroSpot-AI Controlling the MicriSpotAI robot from scratch Colaborators Alexander Dennis Components from MicroSpot The MicriSpotAI has the fo

5 Oct 20, 2022

Non-stationary GP package written from scratch in PyTorch

Related tags

Overview

NSGP-Torch

Examples

gpytorch model with skgpytorch

nsgptorch model with skgpytorch

Plan

Ideas

You might also like...

Keras like implementation of Deep Learning architectures from scratch using numpy.

This repo is to be freely used by ML devs to check the GAN performances without coding from scratch.

Train a state-of-the-art yolov3 object detector from scratch!

ML From Scratch

In this project, we create and implement a deep learning library from scratch.

Create and implement a deep learning library from scratch.

AbelNN: Deep Learning Python module from scratch

Weighted K Nearest Neighbors (kNN) algorithm implemented on python from scratch.

Controlling the MicriSpotAI robot from scratch

Releases(v0.1.2)

v0.1.2(Jan 15, 2022)

v0.1.0(Jan 15, 2022)

Owner

Zeel B Patel

Gender Classification Machine Learning Model using Sk-learn in Python with 97%+ accuracy and deployment

Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows"

Dataset and codebase for NeurIPS 2021 paper: Exploring Forensic Dental Identification with Deep Learning

Sematic-Segmantation - Semantic Segmentation on MIT ADE20K dataset in PyTorch

Final term project for Bayesian Machine Learning Lecture (XAI-623)

1st place solution in CCF BDCI 2021 ULSEG challenge

Official codes: Self-Supervised Learning by Estimating Twin Class Distribution

This is the source code of the 1st place solution for segmentation task (with Dice 90.32%) in 2021 CCF BDCI challenge.

Official PyTorch implementation of the paper "Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory (SB-FBSDE)"

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

Revealing and Protecting Labels in Distributed Training

OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

Data, notebooks, and articles associated with the RSNA AI Deep Learning Lab at RSNA 2021

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera.

Python Library for learning (Structure and Parameter) and inference (Statistical and Causal) in Bayesian Networks.

Code & Experiments for "LILA: Language-Informed Latent Actions" to be presented at the Conference on Robot Learning (CoRL) 2021.

SCAAML is a deep learning framwork dedicated to side-channel attacks run on top of TensorFlow 2.x.

Paddle-Skeleton-Based-Action-Recognition - DecoupleGCN-DropGraph, ASGCN, AGCN, STGCN

Pytorch and Torch testing code of CartoonGAN

Estimation of human density in a closed space using deep learning.

`gpytorch` model with `skgpytorch`

`nsgptorch` model with `skgpytorch`