💻 Software & Environment Setup
Data Science & Analytics
The computational toolchain and environment used throughout Generative Adversarial Networks Course.
Generative adversarial networks faculty developmentGenerative adversarial networks training ColombiaWasserstein gan training for researchersGenerative adversarial networks workshopCyclegan training for researchersGenerative adversarial networks for PhD students
# Recommended conda environmentconda create -n dstc_env python=3.11 -yconda activate dstc_envpip install numpy pandas scikit-learn matplotlib seabornPython 3.11 + Jupyter
Interactive analysis notebooks
Interactive analysis notebooks
pandas / NumPy
Data wrangling & numerics
Data wrangling & numerics
scikit-learn
Modelling & evaluation
Modelling & evaluation
Plotly / Seaborn
Statistical visualisation
Statistical visualisation
Supported OS: Linux (Ubuntu 22.04+), macOS, or Windows via WSL2.
Hardware: 16 GB RAM minimum; a CUDA GPU helps for deep-learning modules.
Earn government-registered certification in Generative Adversarial Networks Course
e-Certificate and e-Marksheet issued on successful completion.
