SeongRyeong

If you create a2c model and then try to apply it to kfac, it says that there is no attribute called steps. After checking, it seems that not all attributes...

edge_attr have dimension issue.

3

## 🐛 Bug There is a bug in the edge num feature on edge attr. A problem arises when the dimension is 2D. please check. ``` data.x.shape , data.edge_index.shape ,...

Is torch also supported?

1

if it is supported. Can you show the use case? Thanks!

environment issue

2

**Describe the bug** It is not working. please help me **To Reproduce** Please provide sample code to reproduce the bug. ```python command = np.array([0, 0, 0, 100]) env.reset() for _...

[Error] What if I want to apply embedding_column to category variables in Parametric UMAP?

2

When reducing dimensions from tabular data, I want to reduce dimensions by using an embedding method for category variables. However, I don't think this method is possible with the input...

ValueError: redefine phi relevance function: all points are 0

4

I have a issue about redefine my data have some issue( same x , but different y values) ``` import smogn rg_mtrx = [ [35000, 1, 0], ## over-sample ("minority")...

[feature] Save all model checkpoints in TuneSearchCV?

3

Hi, I have a question. When using TuneSearchCV, can you save all the models with the highest performance for each trial?

I hope you can make a class for Korean.

2

I am making the following code for Korean. If Korean is reflected officially, I think many Koreans will use it. :) ``` from pregex.core.classes import AnyLetter class AnyKor(AnyLetter): def __init__(self)...

now I use the multi-thread. and when my training code is terminated, but it does not kill pid. how can solve this?

hi i want to use bayesianoptimization in h2o.deeplearning. so i try this code. `initial_weight_distribution = c("UniformAdaptive","Uniform", "Normal") loss = c("Automatic", "CrossEntropy", "Huber" , "Absolute" , "Quadratic") activation = c("RectifierWithDropout" ,...