Name: Bashar Shami
Type: User
Company: Ingenieria Biomedica Arte
Bio: Biomedical Entrapruneur,Researcher, 3D printing ,Modelling , AI , robotics ,Application,Developing,Algorithms , Python ,C++,.Blender,3DSlicer,Autodesk.
Location: Jordan/AMMAN
Blog: https://github.com/basharbme
Bashar Shami's Projects
A clone of the game 2048 in the console written in vanilla python without any imports.
Implementation of an agent able to play 2048. Report, evaluation and implementation details in the GitHub repository. During the project I gained experience with Reinforcement learning technologies such as the gym framework and the Keras-rl library.
Deep learning to play the game 2048.
deep learning for 2048Game
2D dft for image processing in python
Code that converts a jpg image to a stl object
Modeling, simulation and control of Azimuth-Elevation, Target-Aligned and the proposed 3-RPS parallel manipulator
A collection of STL files used for building or modifying a FDM printer to print gels
Responsible implementation of 3D-GAN NIPS 2016 paper:Learning a Probabilistic Latent Space of ObjectShapes via 3D Generative-Adversarial Modeling,that can be found https://papers.nips.cc/paper/6096-learning-a-probabilistic-latent-space-of-object-shapes-via-3d-generative-adversarial-modeling.pdf
A pytorch implementation of 3D-GAN
3D-Guided Face Manipulation of 2D Images for the Prediction of Post-Operative Outcome after Cranio-Maxillofacial Surgery
A resource repository for 3D machine learning
"When fervent human curiosity is abandoned to the power of AI, the intrinsic executive function, cognitive control, interrogation, and discord will rapidly weaken to the surrender of the narrative/reality created by AI." ― Tamie M. Santiago
3d medical image analysis and deep learning using pytorch
This Repo Will contain the Preprocessing Code for 3D Medical Imaging
3D Liver Segmentation with GAN
Official Implementation in Pytorch and Tensorflow of 3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation
UNet Fully Convolutional NNs for 3D Object Detection
3d printing addon for Blender 2.8
During COVID-19 pandemic, a high number of patients with severe acute respiratory syndrome created a great demand for intensive care admission and invasive mechanical ventilation procedure (IMV). Because of the high number of patients, a lack of resources for fighting off the pandemic might happen. In this study, additive manufacturing was used to rapidly produce valves for final use with full-face snorkeling masks as part of medical devices for continuous positive airways pressure (CPAP), a non-invasive ventilation (NIV) procedure. A series of 2,200 valves were fabricated and used in contaminated with COVID-19 virus patients who presented hypoxia symptoms and respiratory distress. Around 30-40% of patients had their blood oxygen saturation level (SpO2) improved over 93% and could avoid or delay IMV and ICU admission. These results present a reduction of 3 to 4 weeks of patient intubation, improving the availability of ICU beds in hospitals that are working in a risk of shortage of such unities during the pandemic. Thus, this study shows the feasibility of using additive manufactured valves with snorkel facial masks to support medical devices for NIV procedures.
Please take a look into the README for further information.
two view structure from motion
List of projects for 3d reconstruction
This repository contains matlab code for processing an input dataset of images into a depth map. This depth map can then be converted to .stl for 3D printing
A simple implementation of 3D-Unet on a 3D Prostate Segmentation Task
3D Unet for Isointense Infant Brain Image Segmentation
An implementation of 3D U-Net CNN models for the task of voxel-wise semantic segmentation of 3D MR images for isolation of Low-Grade and High Grade Gliomas, the common types of brain tumour.