mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-15 18:27:20 +08:00
.. image:: https://badge.fury.io/py/labml-nn.svg :target: https://badge.fury.io/py/labml-nn .. image:: https://pepy.tech/badge/labml-nn :target: https://pepy.tech/project/labml-nn LabML Neural Networks ===================== This is a collection of simple PyTorch implementation of various neural network architectures and layers. We will keep adding to this. Transformers ------------ `Transformers module <https://github.com/lab-ml/labml_nn/tree/master/labml_nn/transformers>`_ contains implementations for `multi-headed attention <https://github.com/lab-ml/labml_nn/blob/master/labml_nn/transformers/mha.py>`_ and `relative multi-headed attention <https://github.com/lab-ml/labml_nn/blob/master/labml_nn/transformers/relative_mha.py>`_. Installation ------------ .. code-block:: console pip install labml_nn Links ----- `💬 Slack workspace for discussions <https://join.slack.com/t/labforml/shared_invite/zt-egj9zvq9-Dl3hhZqobexgT7aVKnD14g/>`_ `📗 Documentation <http://lab-ml.com/>`_ `📑 Articles & Tutorials <https://medium.com/@labml/>`_ `👨🏫 Samples <https://github.com/lab-ml/samples>`_ Citing LabML ------------ If you use LabML for academic research, please cite the library using the following BibTeX entry. .. code-block:: bibtex @misc{labml, author = {Varuna Jayasiri, Nipun Wijerathne}, title = {LabML: A library to organize machine learning experiments}, year = {2020}, url = {https://lab-ml.com/}, }
Description
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
attentiondeep-learningdeep-learning-tutorialganliterate-programmingloramachine-learningneural-networksoptimizerspytorchreinforcement-learningtransformertransformers
Readme
152 MiB
Languages
Python
89.4%
Jupyter Notebook
10.5%
Makefile
0.1%