GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → myaooo → Rnnvis

myaooo / Rnnvis

A visualization tool for understanding and debugging RNNs

Programming Languages

python
139335 projects - #7 most used programming language

Labels

tensorflowvisualizationlstmrnn

Projects that are alternatives of or similar to Rnnvis

Tensorflow Bitcoin Robot
A Bitcoin trade robot based on Tensorflow LSTM model.Just for fun.
Stars: ✭ 155 (-4.32%)
Mutual labels:  lstm, rnn
Load forecasting
Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (-1.23%)
Mutual labels:  lstm, rnn
Text predictor
Char-level RNN LSTM text generator📄.
Stars: ✭ 99 (-38.89%)
Mutual labels:  lstm, rnn
Pytorch Pos Tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Stars: ✭ 96 (-40.74%)
Mutual labels:  lstm, rnn
Chinese Chatbot
中文聊天机器人，基于10万组对白训练而成，采用注意力机制，对一般问题都会生成一个有意义的答复。已上传模型，可直接运行，跑不起来直播吃键盘。
Stars: ✭ 124 (-23.46%)
Mutual labels:  lstm, rnn
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-40.12%)
Mutual labels:  lstm, rnn
Ml Ai Experiments
All my experiments with AI and ML
Stars: ✭ 107 (-33.95%)
Mutual labels:  lstm, rnn
Copper price forecast
copper price(time series) prediction using bpnn and lstm
Stars: ✭ 81 (-50%)
Mutual labels:  lstm, rnn
Linear Attention Recurrent Neural Network
A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)
Stars: ✭ 119 (-26.54%)
Mutual labels:  lstm, rnn
Pytorch Rnn Text Classification
Word Embedding + LSTM + FC
Stars: ✭ 112 (-30.86%)
Mutual labels:  lstm, rnn
Word Rnn Tensorflow
Multi-layer Recurrent Neural Networks (LSTM, RNN) for word-level language models in Python using TensorFlow.
Stars: ✭ 1,297 (+700.62%)
Mutual labels:  lstm, rnn
Rnn poetry generator
基于RNN生成古诗
Stars: ✭ 143 (-11.73%)
Mutual labels:  lstm, rnn
Cnn lstm for text classify
CNN, LSTM, NBOW, fasttext 中文文本分类
Stars: ✭ 90 (-44.44%)
Mutual labels:  lstm, rnn
Poetry Seq2seq
Chinese Poetry Generation
Stars: ✭ 159 (-1.85%)
Mutual labels:  lstm, rnn
Lstm chem
Implementation of the paper - Generative Recurrent Networks for De Novo Drug Design.
Stars: ✭ 87 (-46.3%)
Mutual labels:  lstm, rnn
See Rnn
RNN and general weights, gradients, & activations visualization in Keras & TensorFlow
Stars: ✭ 102 (-37.04%)
Mutual labels:  lstm, rnn
Machine Learning
My Attempt(s) In The World Of ML/DL....
Stars: ✭ 78 (-51.85%)
Mutual labels:  lstm, rnn
Pytorch Sentiment Analysis Classification
A PyTorch Tutorials of Sentiment Analysis Classification (RNN, LSTM, Bi-LSTM, LSTM+Attention, CNN)
Stars: ✭ 80 (-50.62%)
Mutual labels:  lstm, rnn
Lstms.pth
PyTorch implementations of LSTM Variants (Dropout + Layer Norm)
Stars: ✭ 111 (-31.48%)
Mutual labels:  lstm, rnn
Lstm Crypto Price Prediction
Predicting price trends in cryptomarkets using an lstm-RNN for the use of a trading bot
Stars: ✭ 136 (-16.05%)
Mutual labels:  lstm, rnn
View All Similar Projects ➔

RNNVis

A visualization tool for understanding and debugging RNNs.

Online demo: http://rnnvis.hkustvis.org

The major goal of this project is to explore possible ways to help better unerstanding of RNN models (Vanilla RNN, LSTM, GRU, etc.) and help practitioners to debug their model and data, and help reasearchers improve model architecture and performances.

Note: This is an underdeveloped project.

Setup

  1. Install TensorFlow r0.12.1 (gpu is also supported)

  2. To install all the dependency packages, under the project dir, run:

    pip install -r requirements.txt

  3. Example datasets are already in the cached_data dir.

    To set up the mongodb, you must first have mongodb installed on your system and have a mongod instance running. More details

    Then, at the project root dir, run

    python -m rnnvis.main seeddb

TODO

  • [ ] Remove the dependency of Mongo for easier extension.

  • [ ] Migration to TensorFlow 1.0 and Vuex.

Usage

Run Training Test

  1. Run tests on PTB datasets to see whether the code runs normally:

    python -m tests.test_language_model --config_path=./config/model/lstm.yml --data_path=./cached_data/simple-examples/data

Training an RNN model

  1. To train a rnn model using predefined procedures, run:

    python -m tests.train_with_db --config_path=./config/model/lstm-large3.yml

    you can modify the model file under the /config directory and customize your model and training parameters.

Visualizing the hidden states of a model

  1. Since the system is built on top of the hidden states of RNN. You need to first record the hidden states of the model by running it on a dataset (the hidden states record will be stored in mongodb for latter use). To do so, you can run:

    python -m tests.test_eval_record --config_path=./config/model/lstm-large3.yml

  2. Then, to run the visualization server, first modify the ./config/models.yml to config which models you want to load. Then run:

    python -m rnnvis.main server

    to host a server for the visualization. Also note that it will take some time for the visualization to pop up (depend on the size of your model and the dataset) the first time you attempt to run the visualization.

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].