Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/keplr-io/quiver
Interactive convnet features visualization for Keras
https://github.com/keplr-io/quiver
convolutional-neural-networks deep-learning visualization
Last synced: 5 days ago
JSON representation
Interactive convnet features visualization for Keras
- Host: GitHub
- URL: https://github.com/keplr-io/quiver
- Owner: keplr-io
- License: mit
- Created: 2016-11-13T22:35:44.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2020-09-04T00:19:41.000Z (about 4 years ago)
- Last Synced: 2024-04-14T11:13:17.595Z (7 months ago)
- Topics: convolutional-neural-networks, deep-learning, visualization
- Language: JavaScript
- Homepage: https://keplr-io.github.io/quiver/
- Size: 517 KB
- Stars: 1,737
- Watchers: 58
- Forks: 222
- Open Issues: 32
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Quiver
[](https://gitter.im/quiverEngine/Lobby)
Interactive convnet features visualization for Keras
**The quiver workflow**
[Video Demo](https://www.youtube.com/watch?edit=vd&v=tgRW3BRi_FA)
1. Build your model in keras
```python
model = Model(...)
```
2. Launch the visualization dashboard with 1 line of code
```python
quiver_engine.server.launch(model, classes=['cat','dog'], input_folder='./imgs')
```
3. Explore layer activations on all the different images in your input folder.
## Quickstart
**Installation**
```bash
pip install quiver_engine
```
If you want the latest version from the repo
```bash
pip install git+git://github.com/keplr-io/quiver.git
```
**Usage**
Take your keras `model`, launching Quiver is a one-liner.
```python
from quiver_engine import server
server.launch(model)
```
This will launch the visualization at `localhost:5000`
**Options**
```python
server.launch(
model, # a Keras Model
classes, # list of output classes from the model to present (if not specified 1000 ImageNet classes will be used)
top, # number of top predictions to show in the gui (default 5)
# where to store temporary files generatedby quiver (e.g. image files of layers)
temp_folder='./tmp',
# a folder where input images are stored
input_folder='./',
# the localhost port the dashboard is to be served on
port=5000,
# custom data mean
mean=[123.568, 124.89, 111.56],
# custom data standard deviation
std=[52.85, 48.65, 51.56]
)
```
## Development
**Building from master**
Check out this repository and run
```bash
cd quiver_engine
python setup.py develop
```
**Building the Client**
```bash
cd quiverboard
npm install
export QUIVER_URL=localhost:5000 # or whatever you set your port to be
npm start
```
Note this will run your web application with webpack and hot reloading. If you don't care about that, or are only in this section because pip install somehow failed for you, you should tell it to simply build the javascript files instead
```
npm run deploy:prod
```
## Credits
- This is essentially an implementation of some ideas of [deepvis](https://github.com/yosinski/deep-visualization-toolbox) and related works.
- A lot of the pre/pos/de processing code was taken from [here](https://github.com/fchollet/deep-learning-models) and other writings of [fchollet](https://github.com/fchollet).
- The dashboard makes use of [react-redux-starter-kit](https://github.com/davezuko/react-redux-starter-kit)
## Citing Quiver
```
misc{bianquiver,
title={Quiver},
author={Bian, Jake},
year={2016},
publisher={GitHub},
howpublished={\url{https://github.com/keplr-io/quiver}},
}
```