neural_style_transfer_streamlit

A web Application developed via streamlit for neural style transfer using Tensorflow . It provides flexibility to experiment with various ways.

Table of Content

• Demo
• Overview
• Directory Tree
• Installation
• To Do
• Bug / Feature Request
• Contribution
• Technologies Used
• Team
• Credits

Demo

Overview

A web Application developed via streamlit for neural style transfer using Tensorflow . It provides flexibility to experiment with various ways. You can set various parameters of your choice and can see different different results.

Directory Tree

├── images
|    ├── content_images
|    ├── style_images
|    ├── logo_image
├── outputs
|    ├── images
|    ├── videos
├── README.md
├── activation.bat
├── final.py
├── requirements.txt

In above directory structure outputs folder is created only when images and videos is required by user. Facility for choosing this option is given at top of side-bar of application.

Installation

1. Windows user can double click on activation.bat file to install required package
2. Linux User type following command in commnand line a) First create a virtual environment

python3.7 -m virtualenv venv

b) Move to venv directory and activate environment

cd venv
. bin/activate

c) Clone this project

git clone https://github.com/pandeynandancse/neural_style_transfer_streamlit.git

d) Move into cloned directory

cd neural_style_transfer_streamlit

e) Now install all requirements

pip install -r requirements.txt

Run

1. After successfull installation windows user can directly open the link that will be appeared
2. After successful installation open type

streamlit run final.py

and then open link

To Do

1. Add More Architecture Options
2. Add another loss functions options
3. More flexibility to choose parameters
4. Generated Video is not very much impressive , so correct it.

Bug / Feature Request

If you find a bug (the website couldn't handle the query and / or gave undesired results), kindly open an issue here by including your search query and the expected result.

If you'd like to request a new function, feel free to do so by opening an issue here. Please include sample queries and their corresponding results.

Contribution

If you'd like to do some contribution, feel free to do so by opening a pull request here. Please include sample queries and their corresponding results.

Technologies Used

Contributor

Nandan Pandey

Credits

Special Thanks to Tensorflow for it's wonderful tutorial : https://www.tensorflow.org/tutorials/generative/style_transfer