Pinned Repositories
Double-deep-Q-learning-Space-Invaders
This repository contains Double deep Q learning algorithm implemented on Atari Space Invaders game. The agent is trained completely on Google Colab.
Long-texts-Sentiment-Analysis-RoBERTa
PyTorch implementation of Sentiment Analysis of the long texts written in Serbian language (which is underused language) using pretrained Multilingual RoBERTa based model (XLM-R) on the small dataset.
Speech-Emotion-Classification-with-PyTorch
This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.
Twitter-Sentiment-Analysis-RoBERTa
Sentiment Analysis of tweets written in underused Slavic languages (Serbian, Bosnian and Croatian) using pretrained multilingual RoBERTa based model XLM-R on 2 different datasets.
Variational-Autoencoder-for-Face-Generation
Keras implementation of Variation Autoencoder for face generation. Analysis of the distribution of the latent space of the VAE. Vector arithemtic in the latent space. Morphing between the faces. The model was trained on CelebA dataset
WGAN-GP-for-Face-Generation
Keras implementation of WGAN GP for face generation. The model is trained on CelebA dataset.
Canny-edge-detection-algorithm
Matlab implementation of Canny edge detection algorithm from scratch.
Generisanje-lica-pomocu-varijacionih-autoenkodera-i-generativnih-suprotstavljenih-modela
pytorch-neural-style-transfer
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the image - for better understanding of how NST works.
AMR-Line-extraction-from-Lidar-sensor-with-Split-and-Merge-algorithm
Line (wall) extraction using Lidar sensor data with recursive Split and Merge algorithm.
kosta-jo's Repositories
kosta-jo/Generisanje-lica-pomocu-varijacionih-autoenkodera-i-generativnih-suprotstavljenih-modela
kosta-jo/pytorch-neural-style-transfer
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the image - for better understanding of how NST works.