Discover JaxSulav/Rebalance-----ML-in-Unity Open Source project

Stars
2
Language ASP
Created over 6 years ago
Updated over 6 years ago

JaxSulav

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Using Reinforcement Learning to train a piece of floor to balance a ball over it. The PPO (Proximal Policy Optimization) algorithm is used to train the agent. Training process took around half hour with Tensorflow API in CPU and was trained up to 500,000 steps..

nn_cpp

Implementation of artificial neural network in C++. In this project, a cuztomizable neural network architecture is built from scratch and the model is trained, utilizing the backpropagation algorithm.

C++

Cleaning-data-with-Pandas-Python3-

Before working on any dataset, cleaning the dataset is crucial and takes most of the time. The dataset can contain many missing values which can be filled with various standard techniques. We can always refer to Matthew Brems slides linked alongside to know about those standards.

Jupyter Notebook

PriceProphet

Detection of product prices on an e-commerce website to help sellers determine the perfect price for their used, open box, new or old products.

Jupyter Notebook

Object-Detection-v2

Training a dataset on faster_rcnn_inception_v2_coco as implementation of a tensorflow model for multiple object detection purpose. The labeled dataset of about 300 images were fetched and trained using faster_rcnn_inception_v2_coco model through a pretty decent GPU (local machine) i.e Nvidia GTX 1050.

Python