Skip to content

Repository files navigation

ML2 — DCGAN on the 102-Category Flowers Dataset

About the course

This repository is part of my coursework for Deep Learning (ML2), a university course covering modern deep learning. Topics include neural-network training and optimization, convolutional architectures, sequence models (RNN/LSTM/Transformers), generative models (VAEs/GANs/diffusion), adversarial robustness, and self-supervised/contrastive learning.

About this assignment

HW4 is the final project of the course: train a deep generative model from scratch and actually get it to sample convincing images. The chosen model is a DCGAN — a generator built from ConvTranspose2d / BatchNorm2d / ReLU blocks ending in Tanh, and a matching convolutional discriminator. The generator is trained on the 102-category Oxford Flowers dataset at 64×64, with the report covering training stability, mode-collapse symptoms, and a latent-space walk. The generation script loads the trained weights and produces image grids for the write-up.

Contents

  • hw4_code.py — training and evaluation code
  • hw4_generation.pyGenerator network definition and sampling utilities
  • hw4_model.pkl — trained generator weights
  • hw4_report.pdf — write-up of the DCGAN design, training curves and samples
  • hw4_code_IPYNB.pdf — PDF export of the code notebook
  • HW4.pdf — the assignment sheet
  • requirements.txt — Python dependencies used during training

Suheil Khourieh

About

DCGAN trained on the 102-category Oxford Flowers dataset, with report on stability and latent-space walks.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Contributors

Languages