Public | Automated Build

Last pushed: 2 years ago
Short Description
How to use LSTM multi layer networks to make predictions with Tensorflow 0.10.0 and Jupyter.
Full Description


This is an example of a regressor based on recurrent networks:

The objective is to predict continuous values, sin and cos functions in this example, based on previous observations using the LSTM architecture. An example of using LSTM networks to make multilayer predictions (lstm-weather.ipynb) is provided in the project as well as using RNN without deep layers (lstm-sin.ipynb)

Docker container

$ docker run -d -p 8888:8888 claytantor/tensorflow-lstm-regression:latest

Version Info

  • Python 2.7.11
  • Pip 8.0.2
  • Tensorflow 0.10 (installed from whl)
  • Scipy 0.18.1
  • Pandas 0.18.1
  • Matplotlib 1.5.1
  • Jupyter 1.0.0
  • Scikit-learn 0.18
  • Pysqlite 2.8.3

Docker Hub

This project is also available as a fully configured docker container. It is possible to build it a docker container using the Dockerfile You can download and run it from docker hub at the project page: claytantor/tensorflow-lstm-regression

Building The Project

Create a Virtual Environment

It is reccomended that you create a virtualenv for the setup since this example is highly dependant on the versions set in the requirements file.

$ virtualenv ~/python/ltsm
$ source ~/python/ltsm/bin/activate
(ltsm) $

Install Requirements

This example depends on tensorflow-0.10.0rc0 to work. You will first need to install the requirements. You will need the appropriate version of tensorflow for your platform, this example is for mac. For more details goto TAG tensorflow-0.10.0rc0 Setup

(ltsm) $ wget
(ltsm) $ pip install -U ./tensorflow-0.10.0rc0-py2-none-any.whl
(ltsm) $ pip install -r ./requirements.tx

Running on Jupyter

Three Jupyter notebooks are provided as examples on how to use lstm for predicting shapes. They will be available when you start up Jupyter in the project dir.

(ltsm) $ jupyter notebook

Other Reading

For more details please look at this blog post Sequence prediction using recurrent neural networks(LSTM) with TensorFlow

Docker Pull Command