-
Trying to use the gamma likelihood with Laplace approximation fails:
```python
lik = GPy.likelihoods.Gamma()
inf = GPy.inference.latent_function_inference.Laplace()
m_gam = GPy.core.GP(X, Y, k…
-
* The Pycom board: GPy and Fipy
* The firmware version are: v1.18.2.r7, CATM1-41065, NB1-41019
running os.uname(): (sysname='GPy', nodename='GPy', release='1.18.2.r7', version='v1.8.6-849-df9f23…
-
Hi,
My GP model has positive log-likelihood after optimisation and furthermore I don't get any warning message that something could be going wrong. Here is the code to reproduce the problem:
``…
-
Hi!
I hope this is the right place for this question. I have built and optimized a Sparse Gaussian Process Regression model using the GPy library. The documentation recommends to save the model as…
-
X-API-KEYなどをはじめとしたKey情報を隠蔽するのに、それが良いらしいけど、実施するとどうなるのか？ということがいまいちよくわからない。
[NuxtのJamstack構成におけるAPIキーの隠蔽方法について](https://blog.microcms.io/nuxt-secure-api-key/)
[【入門】Netlify Functionsコトハジメ](https://qii…
-
Here I would like to train a GP model on a very high dimension X, I will first decompose the X into 27 subspace_dim and then uses the addition of 27 MaternKernels as covar_module, however, the speed i…
-
Hi @wesselb,
If I am getting it right, Varz handles positivity constraints with `exp(x)` transformation which could be explosive for large values. How about adding more stable transformations for p…
-
预期是chang，实际是zhang
-
长沙拼成zhang sha
[[zhang] [sha] }
-
### 🐛 Describe the bug
在进行流水线并行训练gpt2_4B的时候,出现layernorm层的错误如上描述。
我用的是colossalAI-examples这份代码，采用8卡进行pipeline parallelize 运行的train_gpy.py文件，config文件为gpt2_configs/gpt2_pp.py 。
求解答，感激不尽！！！！
### Enviro…