Data-Science-kosta
This organization contains everything from machine learning and neural networks to statistics and probabilities
Pinned Repositories
Detection-of-abnormal-moving-of-a-drone
Classification of abnormal moving of a drone using logistic regression
Emotions-classification-with-TensorFlow
Classification of emotions using deep CNN on 2 different datasets. Works in real time through desktop camera
Forecasting-air-pollution-LSTM-model-and-Regression-trees-model
Forecasting air pollution from given weather data. Two models were implemented: Regression Trees and LSTM model.
Language-detection-bigram-model
Detection of language of a written text using bigram letter model.
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.
Data-Science-kosta's Repositories
Data-Science-kosta/Speech-Emotion-Classification-with-PyTorch
This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.
Data-Science-kosta/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.
Data-Science-kosta/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.
Data-Science-kosta/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
Data-Science-kosta/WGAN-GP-for-Face-Generation
Keras implementation of WGAN GP for face generation. The model is trained on CelebA dataset.
Data-Science-kosta/Forecasting-air-pollution-LSTM-model-and-Regression-trees-model
Forecasting air pollution from given weather data. Two models were implemented: Regression Trees and LSTM model.
Data-Science-kosta/Emotions-classification-with-TensorFlow
Classification of emotions using deep CNN on 2 different datasets. Works in real time through desktop camera
Data-Science-kosta/Language-detection-bigram-model
Detection of language of a written text using bigram letter model.
Data-Science-kosta/Detection-of-abnormal-moving-of-a-drone
Classification of abnormal moving of a drone using logistic regression