Durer

Motivation

To create a web app based on WGAN-GP that generates realistic Albrecht Dürer paintings

Requirements

Python 3.8 or above with all requirements dependencies installed. To install run:

$ pip3 install -r requirements.txt

To run non super-res version

$ streamlit run duhrer.py

or check it out here: https://duhrer.herokuapp.com/

To run super-res version

$ streamlit run durer.py

To check out paintings with different super-res manaully

$ python3 check.py

-->

super-res

non super-res

Architecture and other details

Trained for nearly 150 epochs on approximately 8000 Albrecht Dürer paintings

LapSRN_x8 used to upscale paintings by a factor of 8 (pretrained)

w1 ---> weights saved at 100 epochs, w2 ---> weights saved at 150 epochs, total epochs ~150

Partial Dataset ---> https://www.kaggle.com/ikarus777/best-artworks-of-all-time

all images resized to 64 x 64 x 3(channel)

Results

final scores: loss_g: 0.5128, loss_d: 1.1873, real_score: 0.5859, fake_score: 0.0469

Might Do

Upload WGAN-GP Notebook

Name	Name	Last commit message	Last commit date
Latest commit History 99 Commits
SAMPLES	SAMPLES
SUPERSAMPLES	SUPERSAMPLES
WEIGHTS	WEIGHTS
__pycache__	__pycache__
lib	lib
modules	modules
scripts	scripts
src	src
utils	utils
LICENSE	LICENSE
LapSRN_x8.pb	LapSRN_x8.pb
Procfile	Procfile
README.md	README.md
app.md	app.md
app.py	app.py
app.txt	app.txt
check.py	check.py
config.md	config.md
config.py	config.py
config.txt	config.txt
duhrer.py	duhrer.py
durer.py	durer.py
index.md	index.md
index.py	index.py
index.txt	index.txt
main.md	main.md
main.py	main.py
main.txt	main.txt
requirements.txt	requirements.txt
res.py	res.py
setup.sh	setup.sh
utils.md	utils.md
utils.py	utils.py
utils.txt	utils.txt

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Repository files navigation

Durer

Motivation

Requirements

To run non super-res version

To run super-res version

To check out paintings with different super-res manaully

-->

super-res

non super-res

Architecture and other details

Trained for nearly 150 epochs on approximately 8000 Albrecht Dürer paintings

LapSRN_x8 used to upscale paintings by a factor of 8 (pretrained)

w1 ---> weights saved at 100 epochs, w2 ---> weights saved at 150 epochs, total epochs ~150

Partial Dataset ---> https://www.kaggle.com/ikarus777/best-artworks-of-all-time

all images resized to 64 x 64 x 3(channel)

Results

final scores: loss_g: 0.5128, loss_d: 1.1873, real_score: 0.5859, fake_score: 0.0469

Might Do

About

Uh oh!

Releases

Packages

Languages

Search code, repositories, users, issues, pull requests...

License

parikshitkumar1/Image-Generation-using-Generative-Networks

Folders and files

Latest commit

History

Repository files navigation

Durer

Motivation

Requirements

To run non super-res version

To run super-res version

To check out paintings with different super-res manaully

-->

super-res

non super-res

Architecture and other details

Trained for nearly 150 epochs on approximately 8000 Albrecht Dürer paintings

LapSRN_x8 used to upscale paintings by a factor of 8 (pretrained)

w1 ---> weights saved at 100 epochs, w2 ---> weights saved at 150 epochs, total epochs ~150

Partial Dataset ---> https://www.kaggle.com/ikarus777/best-artworks-of-all-time

all images resized to 64 x 64 x 3(channel)

Results

final scores: loss_g: 0.5128, loss_d: 1.1873, real_score: 0.5859, fake_score: 0.0469

Might Do

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages