A pure pytorch implementation of xLSTM.
Project description
xLSTM
A pure pytorch implementation of the XLSTM paper.
TODO
- Ensure correct with paper
- Create some usage examples
- Implement paralleization
- CUDA?
- Allow for different initializations according to: https://pytorch.org/docs/stable/nn.init.html
- Allow for flattening of x for greater shape conformity
- Allow for batching
- Add tests
- https://github.com/catid/audio_prediction/tree/master
- other classic RNN/LSTM tasks
References
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
torchxlstm-0.0.3.tar.gz
(4.3 kB
view hashes)
Built Distribution
Close
Hashes for torchxlstm-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 984abe69a05a5ca621aa0fc6dc8a286490de4fd7b917facca60b6e6bd1ab2139 |
|
MD5 | a1aa454da85371798aa9b7eb4950ec80 |
|
BLAKE2b-256 | 096137204fd3e7830676ff8fdb3b8edf172a4ae73a997da08c36fb5f0e7fe595 |