DeepTab

DeepTab copied to clipboard

- Include stat. basis expansion functions for num preprocessing

AnFreTh

Make fp32/64 optional for users Precision for A100 problematic with fixed fp32

AnFreTh

Hyperparameter Optimization

1

- Implement (Bayesion) Hyperparameter Optimization for users

AnFreTh

- Write unittests that cover all possibilities and edge cases

AnFreTh

See whether inclusion of SAINT in its current form is reasonable

AnFreTh

include NODE architecture

AnFreTh

- get all relevant tabular datasets for comparisons - implement logic on how to store those datasets

AnFreTh

[FAQ]cannot assign 'int' as child module 'precision' (torch.nn.Module or None expected)

2

Hello, author! I used your example_classification.py and got the following error: Feature: feature_0 (imputer -> normalizer -> ple), Encoded feature dimension: 50 -------------------------------------------------- Feature: feature_1 (imputer -> normalizer -> ple),...

SoloTillDawn

Improve Mamba Speed

7

Hello AnFreTh, Thank you for your work on this project. I am currently using Mambular to process tabular data, but I am experiencing very slow training speeds. On average, each...

Jasmine-ycj

There is few optimizers which can show better generalization and training time: AdEMAMix and AdEMAMixShampoo It can be included in repo or add some interface to change optimizer by yourself

EpicUsaMan