blaku01 / poke_gen

poke-gen

Description

The primary goal of Poke-Gen is to blend the fascination of the Pokemon universe with the excitement of deep learning experimentation. By creating an entertaining project, I aim to see the progression of GAN models and illustrate how each iteration builds upon the previous one. The codebase serves as both a source of amusement and an educational resource for individuals interested in diving into the world of AI and GANs.

Installation

conda env create -f environment.yaml

conda activate poke_gen

# clone project
git clone [email protected]:blaku01/poke_gen.git
cd poke_gen

# install pytorch according to instructions
# https://pytorch.org/get-started/

# install requirements
pip install -r requirements.txt

How to run

Train model with default configuration

# train on CPU
python src/train.py trainer=cpu

# train on GPU
python src/train.py trainer=gpu

Train model with chosen experiment configuration from configs/experiment/

python src/train.py experiment=experiment_name.yaml

You can override any parameter from command line like this

python src/train.py trainer.max_epochs=20 data.batch_size=64