Skip to content

Latest commit

 

History

History
70 lines (46 loc) · 2.44 KB

README.md

File metadata and controls

70 lines (46 loc) · 2.44 KB
Raw

TV-Scripts-Generation

This is a third project in the Udacity Deep Learning Nanodegree

In this project, you'll generate your own Seinfeld TV scripts using LSTM RNN. You'll be using a Seinfeld dataset of scripts from 9 seasons. The Neural Network you'll build will generate a new, "fake" TV script.

Project Overview

This project is based on the TV Script Generation repo for the Udacity Deep Learning NanoDegree.

It generates its own Seinfeld TV scripts using RNNs and a Seinfeld dataset of scripts from 9 seasons. The Neural Network will generate a new, "fake" TV script.

Project Instructions

Instructions

  1. Clone the repository and navigate to the downloaded folder.

    	git clone https://github.com/nihithreddy/TV-Scripts-Generation
	cd TV-Scripts-Generation

  2. Make sure you have already installed the necessary Python packages according to the requirements.txt file.

  3. Open a terminal window and navigate to the project folder. Open the notebook and follow the steps.

    	jupyter dlnd_tv_script_generation.ipynb

NOTE: In the notebook, you will need to train RNNs in PyTorch. If your RNN is taking too long to train, feel free to pursue one of the options under the section Accelerating the Training Process below.

Project Information

Contents

  1. Get the Data

  2. Explore the Data

  3. Implement Preprocessing Functions:

    • Lookup Table
    • Tokenize Punctuation
    • Pre-process all the data and save it

  4. Build the Neural Network

    • Check Access to GPU
    • Input Batching
    • Test the Dataloader
    • Model
    • Defining Forward and Backpropagation

  5. Neural Network Training

    • Train Loop
    • Hyperparameters
    • Training

  6. Generate TV Script

    • Generate Text
    • Generate a New Script

(Optional) Accelerating the Training Process

If your code is taking too long to run, you will need to either reduce the complexity of your chosen RNN architecture or switch to running your code on a GPU. If you'd like to use a GPU, you can spin up an instance of your own:

Amazon Web Services

You can use Amazon Web Services to launch an EC2 GPU instance. (This costs money)

Google Colab

You can run this notebook in Google Colab for free. You have to be careful about the access of the extracted data in the notebook.