learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-08-15 02:07:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

badgeg

Browse Source
This commit is contained in:
Varuna Jayasiri
2021-01-03 12:16:01 +05:30
parent 927acc2d81
commit 6fe86efdff
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
Makefile
View File

@ -26,6 +26,7 @@ docs: ## Render annotated HTML
pylit --remove_empty_sections --title_md -t ../../pylit/templates/nn -d html -w labml_nn
pages: ## Copy to lab-ml site
pylit --remove_empty_sections --title_md -t ../../pylit/templates/nn -d html labml_nn
@cd ../pages; git pull
cp -r html/* ../pages/

7
labml_nn/hypernetworks/hyper_lstm.py
View File

@ -11,12 +11,11 @@ We have implemented HyperLSTM introduced in paper
[This blog post](https://blog.otoro.net/2016/09/28/hyper-networks/)
by David Ha gives a good explanation of HyperNetworks.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/hypernetworks/experiment.ipynb)
We have an experiment that trains a HyperLSTM to predict text on Shakespear dataset.
Here's the link to code: [experiment.py](experiment.html)
Here's the link to code: [`experiment.py`](experiment.html)
This is the training results: [View Run](https://web.lab-ml.com/run?uuid=9e7f39e047e811ebbaff2b26e3148b3d).
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/hypernetworks/experiment.ipynb)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://web.lab-ml.com/run?uuid=9e7f39e047e811ebbaff2b26e3148b3d)
HyperNetworks uses a smaller network to generate weights of a larger network.
There are two variants: static hyper-networks and dynamic hyper-networks.