Pinned Repositories
-comarison-between-Keras-optimizers-in-ANN-by-keras-library
comarison between Keras optimizers in ANN by keras library 1-class SGD: Gradient descent (with momentum) optimizer. 2-class Adagrad: Optimizer that implements the Adagrad algorithm. 3-class Adadelta: Optimizer that implements the Adadelta algorithm.¶ 4-class RMSprop: Optimizer that implements the RMSprop algorithm. 5-class Adam: Optimizer that implements the Adam algorithm. 6-class Adamax: Optimizer that implements the Adamax algorithm. 7-class Nadam: Optimizer that implements the NAdam algorithm. 8-class AMSgrad: is a recent proposed improvement to Adam.
3D-Reconstruction-Project
Build-a-Bird-Eye-View-
In this project we will build a Bird View for image and video that be detected from a car in road.¶ We will go through 4 tasks to implement our project: Task 1: Importing libraries Task 2: Read the Image and make a grid Task3: Build a Bird View for image Task4 :Build a Bird View for video
Build-Portrait-Live-Mode-with-blurring
In this project ,we will Build Portrait Live Mode with blurring¶ We will go through 2 tasks to implement our project: Task 1: Importing libraries Task 2: Build Portrait Live Mode with blurring
Card-perspective-transformation-by-image-and-video
In this project we will build a Card perspective transformation by image and video We will go through 4 tasks to implement our project: Task 1: Importing libraries Task 2: Read the Image and make a pluring and morphological transformation¶ Task3: Build a Bird View for image Task4 :Build a Bird View for video
cd0025-supervised-learning
Project code for cd0025 Supervised Learning
comarison-between-activation-function-in-ANN-by-keras-library
comarison between activation function in ANN by keras library 1- sigmoid function. 2- softplus function. 3- softsign function. 4- softmax function.¶ 5- tanh function. 6- swish function. 7- exponential function. 8- elu function. 9- selu function.
combrise-between-all-unsupervised-machine-learning-algorithms-for-model-classification.
# In this project we will combrise between all unsupervised machine learning algorithms for model classification. We will go through 6 tasks to implement our project: Task 1: Import the important library and exploring the dataset. Task 2: Identifying Missing Data and dealing with them. Task 3: Creating visual methods to analyze the data. Task 4: Kmeans cluster model. Task 5: hierarichal cluster model. Task 6: DB scan cluster model
combrise-between-Logistic-regression-SVM-KNN-Nieve-Bayes-Decision-Tree-and-Random-Forest-for
In this project we will combrise between Logistic regression & SVM & KNN & Nieve Bayes & Decision Tree and Random Forest for models classification (shown below) using scikit-learn . Our training data set contains continuous and categorical data from the UCI Machine Learning Repository to predict whether or not a patient has heart disease.¶ We will go through 5 tasks to implement our project: Task 1: Import the important library and exploring the dataset. Task 2: Identifying Missing Data and dealing with them. Task 3: Split the Data into Dependent and Independent Variables Task 4: One-Hot Encoding Task 5: Centering and Scaling Task 6: Logistic regression model Tssk 7: Support vector machine classifier model. Task 8: K nearest neighbore classifier model. Task 9: Nieve Bayes model. Task 10: Decision Tree model. Task 11: Random Forest model.
comparison-between-Logistic-regression-and-SVM-and-KNN-model-in-medical-data
# In this project, you will learn practically how to choose the best features that help us to identify Medical Diagnosis of diabetes using Data analysis & data visualization and then using these features in logistic regression , SVM and KNN models . We will go through 5 tasks to implement our project: Task 1: Importing libraries and Exploring the Dataset. Task 2: Checking missing values. Task 3: Creating visual methods to analyze the data. Task 4: make logistic regression model Task 5: make Support vector machine classification model Task 6: make KNN model
heshamhashem's Repositories
heshamhashem/3D-Reconstruction-Project
heshamhashem/Card-perspective-transformation-by-image-and-video
In this project we will build a Card perspective transformation by image and video We will go through 4 tasks to implement our project: Task 1: Importing libraries Task 2: Read the Image and make a pluring and morphological transformation¶ Task3: Build a Bird View for image Task4 :Build a Bird View for video
heshamhashem/comparison-between-Logistic-regression-and-SVM-and-KNN-model-in-medical-data
# In this project, you will learn practically how to choose the best features that help us to identify Medical Diagnosis of diabetes using Data analysis & data visualization and then using these features in logistic regression , SVM and KNN models . We will go through 5 tasks to implement our project: Task 1: Importing libraries and Exploring the Dataset. Task 2: Checking missing values. Task 3: Creating visual methods to analyze the data. Task 4: make logistic regression model Task 5: make Support vector machine classification model Task 6: make KNN model
heshamhashem/-comarison-between-Keras-optimizers-in-ANN-by-keras-library
comarison between Keras optimizers in ANN by keras library 1-class SGD: Gradient descent (with momentum) optimizer. 2-class Adagrad: Optimizer that implements the Adagrad algorithm. 3-class Adadelta: Optimizer that implements the Adadelta algorithm.¶ 4-class RMSprop: Optimizer that implements the RMSprop algorithm. 5-class Adam: Optimizer that implements the Adam algorithm. 6-class Adamax: Optimizer that implements the Adamax algorithm. 7-class Nadam: Optimizer that implements the NAdam algorithm. 8-class AMSgrad: is a recent proposed improvement to Adam.
heshamhashem/Build-a-Bird-Eye-View-
In this project we will build a Bird View for image and video that be detected from a car in road.¶ We will go through 4 tasks to implement our project: Task 1: Importing libraries Task 2: Read the Image and make a grid Task3: Build a Bird View for image Task4 :Build a Bird View for video
heshamhashem/Build-Portrait-Live-Mode-with-blurring
In this project ,we will Build Portrait Live Mode with blurring¶ We will go through 2 tasks to implement our project: Task 1: Importing libraries Task 2: Build Portrait Live Mode with blurring
heshamhashem/cd0025-supervised-learning
Project code for cd0025 Supervised Learning
heshamhashem/comarison-between-activation-function-in-ANN-by-keras-library
comarison between activation function in ANN by keras library 1- sigmoid function. 2- softplus function. 3- softsign function. 4- softmax function.¶ 5- tanh function. 6- swish function. 7- exponential function. 8- elu function. 9- selu function.
heshamhashem/combrise-between-all-unsupervised-machine-learning-algorithms-for-model-classification.
# In this project we will combrise between all unsupervised machine learning algorithms for model classification. We will go through 6 tasks to implement our project: Task 1: Import the important library and exploring the dataset. Task 2: Identifying Missing Data and dealing with them. Task 3: Creating visual methods to analyze the data. Task 4: Kmeans cluster model. Task 5: hierarichal cluster model. Task 6: DB scan cluster model
heshamhashem/combrise-between-Logistic-regression-SVM-KNN-Nieve-Bayes-Decision-Tree-and-Random-Forest-for
In this project we will combrise between Logistic regression & SVM & KNN & Nieve Bayes & Decision Tree and Random Forest for models classification (shown below) using scikit-learn . Our training data set contains continuous and categorical data from the UCI Machine Learning Repository to predict whether or not a patient has heart disease.¶ We will go through 5 tasks to implement our project: Task 1: Import the important library and exploring the dataset. Task 2: Identifying Missing Data and dealing with them. Task 3: Split the Data into Dependent and Independent Variables Task 4: One-Hot Encoding Task 5: Centering and Scaling Task 6: Logistic regression model Tssk 7: Support vector machine classifier model. Task 8: K nearest neighbore classifier model. Task 9: Nieve Bayes model. Task 10: Decision Tree model. Task 11: Random Forest model.
heshamhashem/English--French-translator-by-using-RNN
Machine Learning Using Tensorflow (RNN) to implement language translator for English-French translation. Translating English sentences to French, using LSTM on RNN architecture. Accuracy of model : 95% We will go through 6 tasks to implement our project: TASK 1: IMPORT LIBRARIES AND DATASETS TASK 2: PERFORM DATA CLEANING TASK 3: VISUALIZE CLEANED UP DATASET TASK 4: PREPARE THE DATA BY PERFORMING TOKENIZATION AND PADDING TASK 5: build the RNN model TASK 6: ASSESS TRAINED MODEL PERFORMANCE
heshamhashem/Finding-Donors-for-CharityML
CharityML is a fictitious charity organization located in the heart of Silicon Valley that was established to provide financial support for people eager to learn machine learning. After nearly 32,000 letters were sent to people in the community, CharityML determined that every donation they received came from someone that was making more than $50,000 annually. To expand their potential donor base, CharityML has decided to send letters to residents of California, but to only those most likely to donate to the charity. With nearly 15 million working Californians, CharityML has brought you on board to help build an algorithm to best identify potential donors and reduce overhead cost of sending mail. Your goal will be evaluate and optimize several different supervised learners to determine which algorithm will provide the highest donation yield while also reducing the total number of letters being sent.
heshamhashem/Hough-Transformation-for-road
In this project we will build Hough Transformation for road
heshamhashem/LoanStatus_classification
In this project we will built this Support Vector Machine for classification (shown below) using scikit-learn to predict Loan_Status
heshamhashem/logistic-regression
n this project, you will learn practically how to choose the best features that help us to identify pulsar star using Data analysis & data visualization and then using these features in logistic regression model
heshamhashem/metro-capture-by-using-templet-matching
metro capture by using templet matching
heshamhashem/multi--linear-regression-model
In this project, you will learn practically how to choose the best features that affect Chance of Admit using Data analysis & data visualization and then using these features in multi linear regression model .
heshamhashem/Panorama-Maker
heshamhashem/Realtime-Hand-Detection-
Realtime Hand Detection by using CVZONE & mediapipe¶ Tasks:- 1- install important library. 2- use Cvzone to detect the Hand and Then measure the Distance between the farest fingers 1- install important library
heshamhashem/support-vector-classification
In this project we will built this Support Vector Machine for classification (shown below) using scikit-learn to predict whether or not a patient has heart disease
heshamhashem/TOY-Recognition-
An End to End Toy Recognition (between kiki and miki)
heshamhashem/Uber-Request-availability-model
in this project, you will learn practically how to handel the data then choose the best features that affect Availability of free uber cars using Data analysis & data visualization and then using these features in logistic regression.¶ We will go through 5 tasks to implement our project: Task 1: Importing libraries and Exploring the Dataset. Task 2: Checking missing values . Task 3: analyze the data. Task 4: Creating visual methods to analyze the data. Task 5: make logistic regression model