GAN Walkthrough (DCGAN & WGAN-GP)

This is a walkthrough for people new to deep learning and GAN, to learn about and be able to run their own GAN. Disclaimer: All of the below is purely for educational purposes!

For the full blogpost, refer to: https://www.yinglinglow.com/blog/2018/02/13/GAN-walkthrough

Full credits go to Rowel Atienza for DCGAN code and keras-contrib for WGAN-GP code.

1. Obtaining Dataset
2. Cleaning Dataset
3. Set up Cloud Platform
4. Running the Model
5. Results

Goal

Generate new brand logos from logos designed by humans

Obtaining Dataset

Download the folder of pictures I used, from logos_originals_1367.zip.

Cleaning Dataset

# to center crop and resize the images
python3 1_5_resize_centre.py --path=/Users/xxx/to_resize/ --size=56

# to convert all pictures to one big array and pickle it
python3 1_6_resize_to_array.py --path=/Users/xxx/resized/ --height=56 --target_path=/Users/xxx/ --augment=True

# optional: to upload to AWS S3 using the AWS CLI
aws s3 cp /Users/xxx/X_train_56_1700.pkl s3://yourbucketname/

Set up cloud platform (if you do not have a GPU)

Work in progress - DCGAN works fine on both AWS and GCP but WGAN can only run on AWS :(

For AWS
Set up your EC2 (p2x.large) instance using the ami 'ami-ccba4ab4' by Adrian Rosebrock on: https://www.pyimagesearch.com/2017/09/20/pre-configured-amazon-aws-deep-learning-ami-with-python/

Then, install AWSCLI and pandas.

pip3 install awscli
pip3 install pandas

For GCP
Set up your gcloud compute instance using this: https://medium.com/@howkhang/ultimate-guide-to-setting-up-a-google-cloud-machine-for-fast-ai-version-2-f374208be43

Then, install AWSCLI and Keras.

conda install -c anaconda keras-gpu
conda install -c conda-forge awscli

Running the Model

# git clone everything in
git clone https://github.com/yinglinglow/gan_walkthrough.git
cd gan_walkthrough
mkdir gan
mkdir gan_models

# open tmux
tmux

# change your variables accordingly if necessary
export XTRAIN=X_train_56_1366.pkl
export CODE=WGAN_180218_final
export DATE=210218

# run the model
python3 $CODE.py

To save result files to AWS S3 directly
aws s3 cp gan/* s3://yourbucketname/
aws s3 cp gan_models/* s3://yourbucketname/

To save result files to your local computer
Run the below commands from your LOCAL terminal!!

# for AWS
scp -i yourpemfile.pem -r ubuntu@ec2-xx-xxx-xxx-xxx.us-west-2.compute.amazonaws.com:~/gan_walkthrough/gan/* .<br>
scp -i yourpemfile.pem -r ubuntu@ec2-xx-xxx-xxx-xxx.us-west-2.compute.amazonaws.com:~/gan_walkthrough/gan_models/* .

# for GCP
gcloud compute scp yourinstancename:gan_walkthrough/gan/* .

Results

1) DCGAN (56x56)
Epoch: 3000

2) WGAN-GP (56x56)
Epoch: 2000

Epoch: 2500

3) WGAN-GP (112x112)
Epoch: 2500