A collection of PyTorch implementations of neural network architectures and layers.
Project description
labml.ai Neural Networks
This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations,
The website renders these as side-by-side formatted notes. We believe these would help you understand these algorithms better.
We are actively maintaining this repo and adding new implementations almost weekly. for updates.
Modules
✨ Transformers
- Multi-headed attention
- Transformer building blocks
- Transformer XL
- Compressive Transformer
- GPT Architecture
- GLU Variants
- kNN-LM: Generalization through Memorization
- Feedback Transformer
- Switch Transformer
- Fast Weights Transformer
✨ Recurrent Highway Networks
✨ LSTM
✨ HyperNetworks - HyperLSTM
✨ Capsule Networks
✨ Generative Adversarial Networks
- Original GAN
- GAN with deep convolutional network
- Cycle GAN
- Wasserstein GAN
- Wasserstein GAN with Gradient Penalty
- Style GAN 2
✨ Sketch RNN
✨ Reinforcement Learning
- Proximal Policy Optimization with Generalized Advantage Estimation
- Deep Q Networks with with Dueling Network, Prioritized Replay and Double Q Network.
✨ Optimizers
✨ Normalization Layers
- Batch Normalization
- Layer Normalization
- Instance Normalization
- Group Normalization
- Weight Standardization
- Batch-Channel Normalization
Installation
pip install labml-nn
Citing LabML
If you use LabML for academic research, please cite the library using the following BibTeX entry.
@misc{labml,
author = {Varuna Jayasiri, Nipun Wijerathne},
title = {LabML: A library to organize machine learning experiments},
year = {2020},
url = {https://nn.labml.ai/},
}
Project details
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
labml-nn-0.4.99.tar.gz
(144.5 kB
view hashes)
Built Distribution
labml_nn-0.4.99-py3-none-any.whl
(209.8 kB
view hashes)
Close
Hashes for labml_nn-0.4.99-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a2750f20959bac9b80cd3a12fe2a7631c458783b8e842611517d30cd0c78c982 |
|
MD5 | c9cb4b6667041df83360487f41d974c5 |
|
BLAKE2b-256 | f62bc6a745f28b7489251f7674261f9d5f5a0a7fe54aaa8bcb47882893c65e4d |