adamgeneangel Goto Github PK

followers: 1.0 following: 0.0 repos: 5.0 gists: 0.0

Name: Adam Angel

Type: User

Company: @Google

Bio: Self driving car engineer @udacity Incoming research intern @google

Location: Chicago

Adam Angel's Projects

udacityimplementrouteplanner

Udacity-Implementing-Route-Planner In this project, it was required to build a route-planning algorithm (A* algorithm) to calculate the shortest path between two points on a map with minimal cost.

udacityjoyride

This project incorporates three parts to control a simulated car

Implementing a Matrix Class In this project you will implement a Matrix class in Python. Specifically, you will implement the following methods: class Matrix: def determinant(self): # your code def trace(self): # your code def inverse(self): # your code def transpose(self): # your code # Overloaded operators def __add__(self,other): # your code def __sub__(self,other): # your code def __mul__(self,other): # your code When your class is working properly you will be able to manipulate matrices in code as if they were regular numbers (for the most part). For example: > A = Matrix([ [2,4], [3,1] ]) > print( A.transpose()) 2.0 3.0 4.0 1.0 > > I = Matrix([ [1,0], [0,1] ]) > > print(A*I) 2.0 4.0 3.0 1.0 > > print(A * A.inverse()) 1.0 0.0 0.0 1.0 Project Instruction Your project workspace will contain several files. On the next page, you will see something like this: notebook screenshot We recommend that you open all of these files in new tabs (except datagenerator.py and test.py, which you won't need to modify) so that your browser looks something like this: jupyter multiple tabs matrix.py - This contains the beginnings of a Matrix class (which you will complete) as well as some helper functions zeroes and identity. This is the file you will be doing most of your work in. matrix_playground.ipynb - A notebook that imports your Matrix class and calls the test code. You may find it useful to use this notebook as a place to use the matrix math code you will write in matrix.py. matrix_cheat_sheet.ipynb - A Jupyter notebook with a glossary, explanation of matrix notation and list of matrix equations. Use this as a reference when filling out the methods in the Matrix class! kalman_filter_demo.ipynb - You don't need to do anything with this notebook but you may find it interesting. Once your matrix class is working properly, the KF implemented here will actually work! Other Files (feel free to ignore). test.py - Contains test code which demonstrates the expected functionality of your code. datagenerator.py - this just contains some helper code which is used by the Kalman Filter.

udacitytrafficlightclassifier

In this project, you’ll use your knowledge of computer vision techniques to build a classifier for images of traffic lights! You'll be given a dataset of traffic light images in which one of three lights is illuminated: red, yellow, or green.all_lights Images from the dataset. Left to right: red, green, and yellow traffic lights. #Classification Steps In the provided notebook, you'll pre-process these images, extract features that will help distinguish the different types of images, and use those features to classify the traffic light images into three categories: red, yellow, or green. The tasks will be broken down into a few sections: Loading and visualizing the data. The first step in any classification task is to be familiar with your data; you'll need to load in the images of traffic lights and visualize them! Pre-processing. The input images and output labels need to be standardized; that is, all the input should be of the same type of data and of the same size, and the output should be a numerical label. This way, you can analyze all the input images using the same procedures, and you know what output to expect when you eventually classify a new image. processing_steps Pre-processed, standardized images Feature extraction. Next, you'll extract some features from each image that will be used to distinguish and classify these images. This is where you have a lot of creativity; features should be 1D vectors or even single values that provide some information about an image that can help classify it as a red, yellow, or green traffic light. feature_ext_steps An example of feature extraction steps Classification and visualizing error. Finally, you'll write one function that uses your features to classify any traffic light image. This function will take in an image and output a label. You'll also be given code to classify a test set of data, compare your predicted label with the true label, and determine the accuracy of your classification model. Evaluate your model. To pass this project, your classifier must be >90% accurate and never classify any red lights as green; it's likely that you'll need to improve the accuracy of your classifier by changing existing features or adding new features. I'd also encourage you to try to get as close to 100% accuracy as possible! Next, read through the instructions and get ready to build a classifier!

udacitytranslatingpythontocpp

Udacity's Self Driving Car Nanodegree Project Translating Python Code to C++ This is the project of Udacity's Self Driving Car Nanodegree Program in which we have to convert a Python code to C++ just because of the speed of C++.

adamgeneangel Goto Github PK

Adam Angel's Projects

udacityimplementrouteplanner

udacityjoyride

udacitymatrixclass

udacitytrafficlightclassifier

udacitytranslatingpythontocpp

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent