martinjm97 / Ennui
Licence: mit
An Elegant Neural Network User Interface to build drag-and-drop neural networks, train in the browser, visualize during training, and export to Python.
Stars: ✭ 90
Programming Languages
javascript
184084 projects - #8 most used programming language
python
139335 projects - #7 most used programming language
typescript
32286 projects
Projects that are alternatives of or similar to Ennui
Math And Ml Notes
Books, papers and links to latest research in ML/AI
Stars: ✭ 76 (-15.56%)
Mutual labels: neural-networks
Neural Networks
brief introduction to Python for neural networks
Stars: ✭ 82 (-8.89%)
Mutual labels: neural-networks
Knet.jl
Koç University deep learning framework.
Stars: ✭ 1,260 (+1300%)
Mutual labels: neural-networks
Wav2letter
Speech Recognition model based off of FAIR research paper built using Pytorch.
Stars: ✭ 78 (-13.33%)
Mutual labels: neural-networks
Attend infer repeat
A Tensorfflow implementation of Attend, Infer, Repeat
Stars: ✭ 82 (-8.89%)
Mutual labels: neural-networks
Sonnet
TensorFlow-based neural network library
Stars: ✭ 9,129 (+10043.33%)
Mutual labels: neural-networks
Mit Deep Learning
Tutorials, assignments, and competitions for MIT Deep Learning related courses.
Stars: ✭ 8,912 (+9802.22%)
Mutual labels: neural-networks
Awesome Medical Imaging
Awesome list of software that I use to do research in medical imaging.
Stars: ✭ 87 (-3.33%)
Mutual labels: neural-networks
Discogan Tensorflow
An implementation of DiscoGAN in tensorflow
Stars: ✭ 82 (-8.89%)
Mutual labels: neural-networks
Pumas.jl
Pharmaceutical Modeling and Simulation for Nonlinear Mixed Effects (NLME), Quantiative Systems Pharmacology (QsP), Physiologically-Based Pharmacokinetics (PBPK) models mixed with machine learning
Stars: ✭ 84 (-6.67%)
Mutual labels: neural-networks
Transfer Learning Conv Ai
🦄 State-of-the-Art Conversational AI with Transfer Learning
Stars: ✭ 1,217 (+1252.22%)
Mutual labels: neural-networks
Calenstyle
Responsive Drag-&-Drop Event Calendar Library for Web, Mobile Sites, Android, iOS & Windows Phone
Stars: ✭ 83 (-7.78%)
Mutual labels: drag-and-drop
Abigsurvey
A collection of 500+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML)
Stars: ✭ 1,203 (+1236.67%)
Mutual labels: neural-networks
Backpropaganda
A simple JavaScript neural network framework.
Stars: ✭ 86 (-4.44%)
Mutual labels: neural-networks
Dltk
Deep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+1287.78%)
Mutual labels: neural-networks
Vvedenie Mashinnoe Obuchenie
📝 Подборка ресурсов по машинному обучению
Stars: ✭ 1,282 (+1324.44%)
Mutual labels: neural-networks
Pytorch Openai Transformer Lm
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Stars: ✭ 1,268 (+1308.89%)
Mutual labels: neural-networks
Variational Capsule Routing
Official Pytorch code for (AAAI 2020) paper "Capsule Routing via Variational Bayes", https://arxiv.org/pdf/1905.11455.pdf
Stars: ✭ 84 (-6.67%)
Mutual labels: neural-networks
ENNUI
ENNUI is an Elegant Neural Network User Interface that allows users to:
- Build neural network architectures with a drag and drop interface.
- Train those networks on the browser.
- Visualize the training process.
- Export to Python.
Thanks to Gil Strang, it's hosted at https://math.mit.edu/ENNUI/
Installation
After cloning the repo, to install dependencies, run:
npm install
To Build the app, run:
npm run build
For Continuous Build and Integration, run:
npm run watch
To use chrome with localhost and the CIFAR-10 Dataset, make sure to close all chrome windows and run the following command to launch chrome: 'path/to/chrome.exe --allow-file-access-from-files'
Code Structure
ENNUI is frontend-only. The implementation is structed in two parts:
-
ENNUI/src/uiis home to the traditional frontend components such as the styling, the button logic, and the draggable components (e.g. the layers and activations). -
ENNUI/src/modelis the "backend" implementation supporting core functionality such as building neural networks, doing the code generation, and saving the state in the browser.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].