n_features) , my example is (n, 2048) ''' (X, Y), likelihood=gpflow.likelihoods.Bernoulli(), kernel=gpflow.kernels.SquaredExponential())
opt = gpflow.optimizer
但是,这会直接将GPflow安装在anaconda下。File "/Users/Chu/Documents/GPflow-master/GPflow/__init__.py", line 18, in <module>
from . importChu/Documents/GPflow-master/GPflow/transforms.py", line 1
我在Python语言中使用Sklearn和GPFlow执行高斯回归。我注意到,对于相同的内核和相同的输入,我得到了非常不同的输出。我必须为sklearn内核添加一个块,因为否则矩阵是奇异的。代码如下:import numpy as npimport tensorflow as tffrom sklearn.gau