ahmedhefnawy's Projects
My personal repository
Android application to work on statistics and medical advice to reduce the spread of the epidemic [COVID-19], using the Java programming language, Android Studio tools ...
A collection of Deep Learning projects and resources
NanoDegree Data analysis Project.The data comes from the FBI's National Instant Criminal Background Check System. The NICS is used by to determine whether a prospective buyer is eligible to buy firearms or explosives. Gun shops call into this system to ensure that each customer does not have a criminal record or isnβt otherwise ineligible to make a purchase. The data has been supplemented with state level data from census.gov. _The NICS data is found in one sheet of an .xlsx file. It contains the number of firearm checks by month, state, and type. _The U.S. census data is found in a .csv file. It contains several variables at the state level. Most variables just have one data point per state (2016), but a few have data for more than one year
Graph based retrieval + GenAI = Better RAG in production
Hands-On Graph Neural Networks Using Python, published by Packt
Tuning CNN Hyperparmeterts - Batch size - Number of epochs - learning rate - Dropout Regularization rate% - using Gridsearch with sk-learn,keras,tf to detect optimal hyperparameters for object detection problem in MNISt fashion dataset.
wrape Keras model as part of evaluating model performance in scikit-learn. -use Keras neural network models with scikit-learn.- neural network using Keras for multiclass classification,- evaluate a Keras neural network model using scikit-learn with k-fold cross validation.
- Using Keras library with TensorFlow backend, three Multilayer perceptron models were built and evaluated using KFold cross validation. - experiments adjusting the network topology to lift model performance.
LLM Finetuning with peft
How to use Metrics to Evaluate your Machine Learning Algorithm
A to Z Math tools , linear Algebra, Statistics, matrics... etc
your guide to preprocessing your supervised learning problems
Solve binary classification problem Using > Neural network < with RELU activation method, imported form kaggle and edited with some Configuration.
fashion clothes detection using cnn by tensorflow,keras,.32 fliters first then 64 then128
An extension of Open3D to address 3D Machine Learning tasks
PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
π Guides, papers, lecture, notebooks and resources for prompt engineering
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
Python: Problem_Sloving, OOP, Complexity Analysis, Sorting Algorithm , Time, Maping, Filtering, , ..etc
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Earth observation tools for Meta AI Segment Anything
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
text classification using RNN with BBC news dataset with simplr RNN model.
Implementing a solution to classify species of iris flowers using machine learning
Advanced predictive model #Configuration using reguralization and data transformation to prepare the data to ml model that produce a power accuracy