Generating a Dataset with GANs

We used GANs to generate new data from an existing dataset for data augmentation. We use the dataset Pima Indians Diabetes Database from Kaggle. All of our code can be found in the notebook Deep_Learning_From_Scratch_Original.ipynb.

Our approach is based on the paper Data Augmentation Using GANs by Fabio Henrique K. dos S. Tanaka.

Wanna know what we found?

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
.ipynb_checkpoints		.ipynb_checkpoints
diabetes_escalonated		diabetes_escalonated
fake_data/diabetes_escalonated		fake_data/diabetes_escalonated
images/diabetes_escalonated		images/diabetes_escalonated
original_data		original_data
results/diabetes_escalonated		results/diabetes_escalonated
values_analysis		values_analysis
.gitignore		.gitignore
Deep_Learning_From_Scratch_Final_Report.pdf		Deep_Learning_From_Scratch_Final_Report.pdf
Deep_Learning_From_Scratch_Original.ipynb		Deep_Learning_From_Scratch_Original.ipynb
README.md		README.md
classification_random_tree.ipynb		classification_random_tree.ipynb
compare_data.py		compare_data.py
create_fake_data.ipynb		create_fake_data.ipynb
data_analysis.ipynb		data_analysis.ipynb
data_treatment.py		data_treatment.py
discriminator.py		discriminator.py
fake_data_analysis.ipynb		fake_data_analysis.ipynb
generator.py		generator.py
simple_gan.ipynb		simple_gan.ipynb
train_generator_discriminator.ipynb		train_generator_discriminator.ipynb
train_generator_discriminator.py		train_generator_discriminator.py
utils.py		utils.py
youtube_url.txt		youtube_url.txt