Mehdi Paak's repositories
aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
ae_git
run auto-encoder on clearml
APPIAN
APPIAN is an open-source automated software pipeline for analyzing PET images in conjunction with MRI. The goal of APPIAN is to make PET tracer kinetic data analysis easy for users with moderate computing skills and to facilitate reproducible research.
deploying-machine-learning-models
Deployment of Machine Learning Models
pytorch-grad-cam
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
ANN-function-approximator
To test the deep artificial neural networks as a universal function approximator using TensorFlow.
Time-Series-Forecast-Women-Employment-Data
A workflow to analyze and understand time series data, from data cleaning and stationarity to modelling and forecasting
Advanced-Vector-Extensions-AVX-vectorization
This program contains AVX functions to calculate the Euclidean distance between vectors using intel's YMM register intrinsics.
FE-shell-mesh-parser
a command line program to parse finite element surface mesh in Nastran or Dyna format. Mesh can contain Triangular and/or Quad shell/surface elements.
Sparse-Matrix-Reordering
A comparison between several reordering algorithms for minimal non-zero fill-ins in the Cholesky factorization when solving Ax=b.
GPU-sum-square
OpenMP parallelization of multiple GPUs; the sum of square kernel is used to test the performance.
Outlier-Detection
some outlier detection methods are explained and their use case is illustrated.
Sensitivity-Analysis
This is a Python (Jupyter) notebook in which I demonstrate how to perform a sensitivity analysis based on a linear regression model.