markvasin

MSc-Project

Multimodal Learning and Reasoning for Visual Question Answering

openvqa

Implementation of the VQA model from my MSc project

subsea-object-detection

vqa_project

Implementation of the baseline VQA models

Blocksworld

Evaluating Search Methods using Blocksworld Tile Puzzle

deep_learning_exercise

Deep Learning Exercises

detectron2-ResNeSt

A fork of Detectron2 with ResNeSt backbone

docker-python

Kaggle Python docker image

Kaggle-Quora-Insincere-Questions-Classification

Kaggle Competition - Quora Insincere Question Classification

nscl_reproducability_challenge

Reproducibility Challenge - The Neuro-Symbolic Concept Learner

GoogleCodeJam2015

HackerRank-Java

HackerRank competition code

HackerRank-Python

markvasin

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

mvsmark.github.io

Personal Website for markvasin.me

negotiation_agent

Automated Negotiation Agent

reasoning-in-artificial-neural-networks

A research review about reasoning in Artificial Neural Networks.

RL_mountain_car

Reinforcement Learning Project - Mountain Car

sartorius-cell-instance-segmentation

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite