Dinar's repositories
TrafficSign
In this project, I use convolutional neural network to classify traffic signs. Specifically, I trained a model to classify traffic signs from the German Traffic Sign Dataset. I used TensorFlow for model development and trained it on GPU.
BehavioralCloning
The goal of the project - to build a neural network (in Keras) which can drive a car in a simulation track.
LineDetection
The goal of this project is to create a pipeline that find lines on the road
machine-learning
Several Jupyter Notebooks for machine learning
Self-Driving-Car
Several projects how to program Self-Driving-Cars
sentiment-analysis
The aim - is to develop a model that will give accurate predictions for the customer's test sample, but the training sample for is not given. It should be collected by parsing
VehicleDetectionTracking
The goal is to create a pipeline to identify and track vehicles in a video from a front-facing camera on a car with a traditional Computer Vision approach for object detection: processing stages, feature extraction, spatial sampling and classification
AdvancedLaneDetection
The Goal of this Project is to write a software pipeline to identify the lane boundaries in a video from a front-facing camera on a car. The camera calibration images, test road images, and project videos are available in the project repository.
ExtendedKalmanFilter
The goal of the project is implementation of Extended Kalman filter C++. Be using simulated lidar and radar measurements we detecting a bicycle that travels around your vehicle. The Kalman filter for lidar measurements and radar measurements is used to track the bicycle's position and velocity.
face-generation
Introduction to Deep Convolutional Generative Adversarial Networks (DCGANs) for Face Generation
Image-Captioning
Create a neural network architecture to automatically generate captions from images.
Dog-Breed-Classifier
Given an image of a dog, algorithm identifies its breed using convolution neural networks in PyTorch
ModelPredictiveControl
The goal of the project is implementation of Model Predictive Control to drive the car around the track.
object_detection_YOLO5
The idea of the project is to try (setup environment, inference and train) a PyTorch-based object detection model YOLO5 created by ultralytics.
PIDController
Implementation of a PID controller in C++ to maneuver the vehicle around the virtual track! The simulator provides the cross track error (CTE) and the velocity (mph) in order to compute the appropriate steering angle and speed
TwoDimensionalParticleFilter
The goal of the project is implementation of a 2 dimensional particle filter in C++. Given a map and some initial localization information (analogous to what a GPS would provide), at each time step the filter will get observation and control data.
UnscentedKalmanFilter
The goal of the project is implementation of unscented Kalman filter using the CTRV motion model.