2D GP fitting using Kronecker product
Project description
gpkron
A simple and fast 2D gaussian process fitting using Kronecker product.
same shape
from gpkron.gp2d import GP2D, RBF, Matern32
import numpy as np
Nx = 128; Ny = 256
xgrid = np.linspace(0, Nx, Nx)
ygrid = np.linspace(0, Ny, Ny)
sigma = 0.2
Dmat = np.sin(xgrid[:, np.newaxis]/20) * np.sin(ygrid[np.newaxis, :]/20) + \
np.random.randn(Nx, Ny)*sigma
Dprer = GP2D(Dmat, RBF, sigma, (20., 20.))
Dprem = GP2D(Dmat, Matern32, sigma, (40., 40.))
different shape
from gpkron.gp2d import GP2D, RBF, Matern32
import numpy as np
Nx = 16; Ny = 32
pshape=(64,128)
xgrid = np.linspace(0, Nx, Nx)
ygrid = np.linspace(0, Ny, Ny)
sigma = 0.2
Dmat = np.sin(xgrid[:, np.newaxis]/4) * np.sin(ygrid[np.newaxis, :]/4) + \
np.random.randn(Nx, Ny)*sigma
Dprer = GP2D(Dmat, RBF, sigma, (20., 20.), pshape=pshape)
Dprem = GP2D(Dmat, Matern32, sigma, (40., 40.), pshape=pshape)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distributions
gpkron-0.0.1-py3.8.egg
(4.4 kB
view hashes)
Close
Hashes for gpkron-0.0.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2c9c8a4f5a96f177937813d152c1377d59bd8f169603d35af86a262d8ac9ae96 |
|
MD5 | 478eac668ab30c188c8464c3a71e4f46 |
|
BLAKE2b-256 | 016eb1b07a8904b5cf13c78860faa3311a927158735f55ac7f45df6f1803f1cb |