Brando Koch's repositories
attention-is-all-you-need-paper
Original transformer paper: Implementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.
pytorch-sequence-models
This repository implements a variety of sequence model architectures from scratch in PyTorch. Effort has been put to make the code well structured so that it can serve as learning material.
neural-style-transfer-paper
Pytorch Implementation of L. A. Gatys, A. S. Ecker and M. Bethge, "Image Style Transfer Using Convolutional Neural Networks," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 2414-2423, doi: 10.1109/CVPR.2016.265.
real-estate-price-prediction
This repository presents an end-to-end process of approaching a machine learning project from data collection to deployment. Problem at hand is price prediction of Cleveland real estate although the underlying code is made flexible enough to provide a structured way of tackling a wide variety of tabular problems with minimal changes.
annotated_whisper
This is my refactor of the whisper ASR model by OpenAI. When released the whisper repository had a very complicated function call stack and a lot of boilerplate which was unnecessary. This repo is the result of my exploration of the original whisper codebase during which I was heavily refactoring and removing parts I found redundant.
multimodal-emotion-classification
Multimodal emotion classification from the MELD dataset
yolov5-synthetic-data
Training/Application of the YOLOv5 object detection algorithm on a synthetic dataset generated in Unity and its Perception module
RPSLS-FERIT2022-1st-Place
This repository presents my solution to FERIT's 2022 Rock, Paper, Scissors, Lizard, Spock competition which achieved 1st place with a score of 1942/2000.
brandokoch
Repository generating the GitHub cover page
GAT
Graph Attention Networks (https://arxiv.org/abs/1710.10903)
gradient-calculation-linear-regression
This repository provides the calculus and linear algebra behind the linear regression gradient calculation. Both vectorized and non-vectorized forms are shown.
petnica-ml7
This repository contains unofficial solutions to Petnica Summer Institute Machine Learning Conference - PSIML7 Assignments required for Acceptance.
pytorch-original-transformer
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.