Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Visualization for Sequential Neural Networks with Attention
| Date | Stars |
|---|---|
| 2026-07-31 | 457 |
| 2026-08-01 | 457 |
| 2026-08-02 | 457 |
| 2026-08-06 | 457 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Seq2Seq-Vis
[](https://circleci.com/gh/sgratzl/Seq2Seq-Vis)
[](https://hub.docker.com/r/sgratzl/seq2seq-vis/)
[](https://opensource.org/licenses/Apache-2.0)
[ ](https://github.com/HendrikStrobelt/Seq2Seq-Vis/releases)
### A visual debugging tool for Sequence-to-Sequence models
*by IBM Research in Cambridge and Harvard SEAS -- more info [seq2seq-vis.io](http://seq2seq-vis.io)
- [Seq2Seq-Vis](#seq2seq-vis)
* [Install and run with `conda`](#install-and-run-with-conda)
+ [1 - Install dependencies (server and client) and create virtual environment](#1---install-dependencies-server-and-client-and-create-virtual-environment)
+ [2 - Install custom OpenNMT-py version](#2---install-custom-opennmt-py-version)
+ [3 - Download some example data](#3---download-some-example-data)
+ [4 - Run the system](#4----run-the-system)
* [Install and run with `docker`](#install-and-run-with-docker)
* [Prepare and run own models](#prepare-and-run-own-models)
+ [1 - Prepare your data](#1---prepare-your-data)
+ [2 - Create a `s2s.yaml` file to describe project](#2---create-a-s2syaml-file-to-describe-project)
+ [3 - Command Line Parameters](#3---command-line-parameters)
* [Change frontend](client/README.md)
- [Cite us](#cite-us)
- [Contributors](#contributors)
- [License](#license)
## Install and run with `conda`
We require using [miniconda](https://conda.io/docs/user-guide/install/index.html) to create a virtual environment and install all dependencies via scripts.
Seq2Seq-Vis currently works with a special version of OpenNMT-py modified version by [Sebastian Gehrmann](https://github.com/sebastianGehrmann/OpenNMT-py/tree/states_in_translation). We provide a script to install this special branch.
after installation you should have a file structure like this:
```
MyS2S/Seq2Seq-Vis ==> the tool
MyS2S/Seq2Seq-Vis/0316-fakedates/ ==> example data
MyS2S/OpenNMT-py ==> modified OpenNMT
```
### 1 - Install dependencies (server and client) and create virtual environment
create root directory (`MyS2S`)and then:
```bash
git clone https://github.com/HendrikStrobelt/Seq2Seq-Vis.git
cd Seq2Seq-Vis
```
and run in `/Seq2Seq-Vis`:
```bash
source setup_cpu.sh
```
### 2 - Install custom OpenNMT-py version
return to root directory:
```bash
cd ..
source Seq2Seq-Vis/setup_onmt_custom.sh
```
### 3 - Download some example data
Here we provide some example data for a character based dataset which converts date strings (e.g. "March 03, 1999" , "03/03/99") into a base form "mm-dd-yyyy". [Download here ~177MB](https://drive.google.com/file/d/1myjJ-surrO76ImnLd4MMJ0-527Ss2e0V/view?usp=sharing) save it to `/Seq2Seq-Vis` and unzip:
```bash
unzip fakedates.zip
```
### 4 - Run the system
```bash
python3 server.py --dir 0316-fakedates/
```
go here: [http://localhost:8080/client/index.html?in=M a r c h _ 0 3 , 1 9 9 9](http://localhost:8080/client/index.html?in=M%20a%20r%20c%20h%20_%200%203%20,%20%201%209%209%209)
You should see:
<img src="docs/pics/s2s_dates_01.png" width="400">
Enjoy exploring !
## Install and run with `docker`
Thanks, [Samuel Gratzl](https://github.com/sgratzl/Seq2Seq-Vis) for contributing a docker configuration and [image](https://hub.docker.com/r/sgratzl/seq2seq-vis/).
Here are the steps:
1. pull image: `docker pull sgratzl/seq2seq-vis`
2. download data [Download here ~177MB](https://drive.google.com/file/d/1myjJ-surrO76ImnLd4MMJ0-527Ss2e0V/view?usp=sharing)
and unzip: `unzip fakedates.zip`
3. run container with bound data: <br> `docker run --rm -it -v "${PWD}/0316-fakedates:/data" -p "8080:8080" sgrExcerpt of 7,872 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6461b1c320c9e924, llm:Repository description: "Visualization for Sequential Neural Networks with Attention"; language: Python; project focuses on visualizing seq2seq models and attention mechanisms.
matched fp:6461b1c320c9e924, llm:Repository description: "Visualization for Sequential Neural Networks with Attention"; language: Python; project focuses on visualizing seq2seq models and attention mechanisms.
matched fp:6461b1c320c9e924, llm:Repository description: "Visualization for Sequential Neural Networks with Attention"; language: Python; project focuses on visualizing seq2seq models and attention mechanisms.