Authors: Daniel Vigild Juhász, Frederik Kromann Hansen & Lau Johansson
This repository contains hand-in assignment for the DTU course 02514 Deep learning in computer vision.
Read our article here
This notebook is a implementation of a simple CNN trained on a dataset with images of hotdogs and not-hotdogs.
Look at the implemented model here
This notebook is a implementation of a simple CNN trained on SVHN dataset.
The goal is to:
- 1: The network is trained to be able to classify single digits.
- 2: Use the trained network as a sliding window algorithm to detect bounding boxes around digits
Look at the implemented model here