drkostas / lstms-training-demo

RNNs and LSTMs

COSC525: Project 4: Train with Tensorflow

Table of Contents

• About
• Getting Started
  • Prerequisites
• Installing the requirements
  • Using the Makefile
  • Manual Installations
• Running the code
  • Execution Options
    • Running the files
• Todo
• License

About

Project 4 for the Deep Learning course (COSC 525). Training character-based RNN networks with Tensorflow on Beatles songs.

Getting Started

These instructions will get you a copy of the project up and running on your local machine.

Prerequisites

You need to have a machine with Python = 3.9 and any Bash based shell (e.g. zsh) installed.

$ python3.9 -V
Python 3.9

$ echo $SHELL
/usr/bin/zsh

Installing the requirements

Using the Makefile

All the installation steps are being handled by the Makefile.

Then, to create a conda environment, install the requirements, setup the library and run the tests execute the following commands:

$ make create_env
$ conda activate cosc525_project4
$ make requirements

Manual Installations

For manual installation, you can create a virtual environment and install the requirements by executing the following commands:

$ conda create -n cosc525_project4 -y python=3.9
$ conda activate cosc525_project4
$ pip install -e requirements.txt

Running the code

Execution Options

First, make sure you are in the correct virtual environment:

$ conda activate cosc525_project4

$ which python
/home/<user>/anaconda3/envs/src/bin/python

Running the files

In order to run the code use the --help option for instructions:

    $ python train.py --help

    $ python evaluate.py --help

License

This project is licensed under the Apache License - see the LICENSE file for details.