Mohamad Okasha's repositories
ASUMobiCarG50
Remote controlled car project with a set of other functions using Arduino and some sensors
Enhancing-Image-Resolution-With-Autoencoders
use Keras with Tensorflow as its backend to train an autoencoder, and use this deep learning powered autoencoder to significantly enhance the quality of images. That is, this neural network will create high-resolution images from low-res source images.
AttendanceApp
a solution that would allow instructors to take the attendance of the session by only taking some pictures of the attending students.
PCI
Verilog behavioural code for PCI bus Arbiter and Devices communication.
Smart-Home
we'll be using 3 layered Architecture: Layer for the Application, Layer for the Drivers, and a MCAL Layer
DeepFace
Keras implementation of the renowned publication "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" by Taigman et al. Pre-trained weights on VGGFace2 dataset.
Deepfake-Keras-Implementation
implementing DCGAN or Deep Convolutional Generative Adversarial Network, and training the network to generate realistic looking synthesized images
Facial_Keypoints_Detection
First project for CVND: facial keypoint detection.
Implement_SLAM
Landmark Detection and Tracking (SLAM) project for CVND
mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
OverlappingRectangles
C++ program that takes some rectangles and group them into the minimum number of groups where each group has non overlapping rectangles
Predicting-House-Prices-with-regression
Solution for the House prices problem on kaggle
Real-Time-Face-Expression-Recognition
build and train a convolutional neural network (CNN) in Keras from scratch to recognize facial expressions
sagemaker-deployment
Code and associated files for the deploying ML models within AWS SageMaker
Siamese-Network-keras-Implementation
implement a Triplet Loss function, create a Siamese Network, and train the network with the Triplet Loss function. With this training process, the network will learn to produce Embedding of different classes from a given dataset in a way that Embedding of examples from different classes will start to move away from each other in the vector space.
Twits-Identifier
Classification of tweets from two twitter users to determine the probability that a particular tweet came from a particular user.