Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,8 @@
This repository contains PyTorch code for training and visualising (through heatmaps) Recurrent Neural Networks.

## Recurrent Neural Networks
Recurrent Nets are Neural Network architecure for modelling sequences. The code in the repository is about the 2 main variants of RNN :- **LSTM and GRU**. <br>
The working of RNN can be summarized in the following gif
Recurrent Nets are Neural Network architecure for modelling sequences. The code in the repository is about the 2 main variants of RNN : **LSTM and GRU**. <br>
The working of RNN can be summarized in the following gif :-
<img src="assets/rnn.gif" height="400" width="500"/>

The input to the RNN in our case is vectorized representation of characters.
Expand Down Expand Up @@ -37,7 +37,7 @@ The simple folder contains code for implementing an RNN from scratch (without us
In all three repositories run
> python train.py --path/to/data

Check the argument parser code to know more about the arguments available
Check the argument parser code to know more about the arguments available.

## Visualization

Expand All @@ -51,4 +51,4 @@ Then run

Please see the argument parsers as well as the files that are being loaded and saved!! (if you are still facing problems file an issue here (code and installation related issues only)).

This code has been used for [ __this__ ](https://euler16.github.io/cs/2017/07/01/playing-with-rnn.html) blog post.
This code has been used for [ __this__ ](https://euler16.github.io/cs/2017/07/01/playing-with-rnn.html) blog post.