tabnet
torchsde
| tabnet | torchsde | |
|---|---|---|
| 8 | 5 | |
| 2,480 | 1,473 | |
| 0.7% | 2.0% | |
| 4.8 | 4.8 | |
| 3 months ago | 7 months ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tabnet
-
Time series data into a CNN
There's architectures that operate on tabular data from a few years back now that uses CNN's and self attention. .look at tabnet for inspiration: https://github.com/dreamquark-ai/tabnet
- [P] Stable Diffusion in Tensorflow / Keras
- [D] Opinions about TabNet
- Deep Learning Models to do Regression on a Tabular Data
-
Tried so many different models but cant get good accuracy
I tried some other projects like [tabnet](https://github.com/dreamquark-ai/tabnet) they are also yielding *decent* results, but not more than 0.64.
- [P] pytorch-widedeep v1.0.9: the Perceiver and the FastFormer for tabular data are now available in the library
- [D] Why Neural Networks for tabular data are bad?
-
Feature Importance in Multiclass problems
Are you solving a tabular problem? If it is so, you can use TabNet to plot them. It also supports multiclass and multilabel.
torchsde
-
Google Research • Differentiable SDE solvers with GPU support and efficient sensitivity analysis in PyTorch. For stochastic differential equations in your deep learning models
Github: https://github.com/google-research/torchsde
-
[D] Ideal deep learning library
So not just that paper, but also our follow-up papers on the same topic: Neural SDEs as Infinite-Dimensional GANs Efficient and Accurate Gradients for Neural SDEs are in fact implemented in PyTorch, specifically the torchsde library. (Disclaimer: of which I am a developer.)
-
[D] Is there any way for GAN to generate arbitrary length of time series signal?
Code: SDE-GAN example in torchsde.
-
[P] Final Year Computer Science Project Suggestions
If you're interested in finance then I'd recommend Neural SDEs: https://arxiv.org/abs/2102.03657 https://arxiv.org/abs/2105.13493 https://github.com/google-research/torchsde/blob/master/examples/sde_gan.py
-
Simple & Fast GAN Training [D]
This may or may not fit what you're after.
What are some alternatives?
tab-transformer-pytorch - Implementation of TabTransformer, attention network for tabular data, in Pytorch
torchdyn - A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
pytorch-widedeep - A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch
pysindy - A package for the sparse identification of nonlinear dynamical systems from data
autogluon - Fast and Accurate ML in 3 Lines of Code
SSD-pytorch - SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity
Linear-Multihead-Attention - Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)
NeuralCDE - Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)
Super-SloMo - PyTorch implementation of Super SloMo by Jiang et al.
functorch - functorch is JAX-like composable function transforms for PyTorch.
ExtractTable-py - Python library to extract tabular data from images and scanned PDFs
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs