Neural Additive Models (NAM) - Pytorch
Project description
nam-pytorch
Unofficial PyTorch implementation of Neural Additive Models (NAM) by Agarwal, et al. [abs, pdf]
Installation
You can access nam-pytorch via pip:
$ pip install nam-pytorch
Usage
import torch
from nam_pytorch import NAM
nam = NAM(
num_features=784,
link_func="sigmoid"
)
images = torch.rand(32, 784)
pred = nam(images) # [32, 1]
Contributing
As always, if there are any issues with / suggestions for the code, feel free to raise an issue or submit a PR.
License
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nam_pytorch-0.0.1.tar.gz
(2.2 kB
view hashes)
Built Distribution
Close
Hashes for nam_pytorch-0.0.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | bc611b1f785cdd50a5ebc6356e2b9f611514b89618d2684ff00ce2becf3c0574 |
|
| MD5 | 8da39e074212bd991cf9283bb8d1ffd5 |
|
| BLAKE2b-256 | 84fb5028751f4817e77221d7dd1deb56a09fbf430d36739c526bac0838bd1919 |
