Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Spatial Transformer Network for Distorted MNIST

Portfolio project by @pkim02.

Implementation proof: see IMPLEMENTATION.md for the STN localization network, affine grid generation, differentiable sampling, baseline comparison, and visualization evidence.

Project Goal

An implementation of a Spatial Transformer Network that learns affine transformations to improve classification on distorted MNIST inputs.

Notebooks

  • spatial_transformer_network.ipynb: Spatial Transformer Network for Distorted MNIST

What I Implemented

  • Localization network that predicts affine transformation parameters.
  • Grid generation and differentiable sampling with PyTorch.
  • STN-augmented CNN and baseline CNN comparison.
  • Visualization of transformed inputs and model behavior.

Results

The notebook keeps visual outputs and accuracy comparisons showing how the STN module improves robustness to spatial distortions.

The notebooks keep most executed outputs so reviewers can inspect the results directly on GitHub. Full reproduction may require downloading the referenced public datasets or pretrained weights.

How To Run

python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
jupyter notebook

Open the notebook listed above and run cells in order. GPU is optional for review, but recommended for rerunning training-heavy experiments.

Citations

Copyright And Data Note

This repository contains a cleaned portfolio version of my own implementation work. Assignment prompts, submission metadata, personal identifiers, and course-provided local figures were removed. The MIT license applies only to the code and documentation in this repository. Papers, datasets, pretrained weights, and any third-party libraries or assets keep their original licenses and terms.

About

Spatial Transformer Network implementation with affine grid sampling, visualization, and baseline comparison.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages