Pinned Repositories
aging
This project provides an API for face aging transformation using two models: ADFD and SAM. The backend is developed in Python, utilizing FastAPI, and deployed on a Google Cloud Platform (GCP) instance with Docker. It is seen that SAM has the better speed and accuracy compared to ADFD. The project needs NVIDIA-CUDA-cuDNN support when integrated.
analyze_bitcoin_price
Analzying Bitcoin prices using the machine learning techniques written from the scratch.
can.github.io
GitHub Pages
jobapp
The project has been written to learn Spring Boot tools and technologies using API Gateway, Zipkin, Lombok, Spring Cloud Eureka, JPA, Hibernate and RabbitMQ.
multi-agent-chess-game
Implementation of AlphaZero RL algorithm and a chess game is written and created like a Gym environment for the simulation.
reinforcement-learning
Reinforcement Learning Study and Codes
reinforcement-learning-a3c
Learning the A3C RL algorithm
reinforcement-learning-arl-airl
Implementation of ARL(Adversarial Reinforcement Learning)-AIRL(Adversarial Inverse Reinforcement Learning) with the DDPG backbone. Basically, two discriminators are used to discriminate reward estimation and actual reward for one task and to discriminate the superior IRL policy with emerging RL policy.
reinforcement-learning-intermediate
Learning advanced RL techniques and DQN.
werewolf-by-gan
GAN colorization project with the movie The Lighthouse. Special thanks to ArVis Technology for allowing the usage of their GPU for the project.
highcansavci's Repositories
highcansavci/reinforcement-learning-arl-airl
Implementation of ARL(Adversarial Reinforcement Learning)-AIRL(Adversarial Inverse Reinforcement Learning) with the DDPG backbone. Basically, two discriminators are used to discriminate reward estimation and actual reward for one task and to discriminate the superior IRL policy with emerging RL policy.
highcansavci/werewolf-by-gan
GAN colorization project with the movie The Lighthouse. Special thanks to ArVis Technology for allowing the usage of their GPU for the project.
highcansavci/aging
This project provides an API for face aging transformation using two models: ADFD and SAM. The backend is developed in Python, utilizing FastAPI, and deployed on a Google Cloud Platform (GCP) instance with Docker. It is seen that SAM has the better speed and accuracy compared to ADFD. The project needs NVIDIA-CUDA-cuDNN support when integrated.
highcansavci/jobapp
The project has been written to learn Spring Boot tools and technologies using API Gateway, Zipkin, Lombok, Spring Cloud Eureka, JPA, Hibernate and RabbitMQ.
highcansavci/multi-agent-chess-game
Implementation of AlphaZero RL algorithm and a chess game is written and created like a Gym environment for the simulation.
highcansavci/reinforcement-learning-ppo
Implementation of PPO RL algorithm and application of the LunarLander game.
highcansavci/diabetes_task
highcansavci/dronecube-app
highcansavci/dronecube-task
DroneCube Senior Software Engineer Task
highcansavci/dsajava
Data Structures and Algorithms for Java Programming Language
highcansavci/first-spring-project
First Spring Project
highcansavci/highcansavci.github.io
highcansavci/html-cheatsheet
HTML Cheatsheet
highcansavci/javascript-notes
JavaScript Study Notes
highcansavci/next-js-notes
Next JS Notes
highcansavci/nomad
highcansavci/react-js-notes
React.js Notes
highcansavci/react-js-product-filtering-project
React.js Product Filtering Project
highcansavci/react-js-small-projects
React.js Small Projects
highcansavci/react-redux
Learning Redux.js via React.js
highcansavci/reinforcement-learning-ddpg
Implementation of DDPG RL algorithm and application of the LunarLanderContinuous game.
highcansavci/reinforcement-learning-es-pendulum
Implementation of ES RL algorithm and application of the Pendulum game.
highcansavci/reinforcement-learning-sac
Implementation of SAC RL algorithm and application of the Pendulum game.
highcansavci/reinforcement-learning-td3
Implementation of TD3 RL algorithm and application of the LunarLanderContinuous game.
highcansavci/reinforcement-learning-trpo
Implementation of TRPO RL algorithm and application of the LunarLander game.
highcansavci/rtk-query-notes
Redux.js Query Notes
highcansavci/studentms
Zyfera Junior Developer Assignment
highcansavci/tailwind-css-notes
Tailwind CSS Notes and Projects
highcansavci/typescript-notes
TypeScript Notes
highcansavci/user-registration-project
User Registration Project Written Using Next.js