Py Part 8 V1

So, in this video, I’ll be showing you how to use transfer learning to train a network that can properly classify those images of cats and dogs. What we’ll do here is use a pre-trained network to actually detect and extract features from the images. This is really good for solving many challenging problems in … Read more

PyTorch – Part 7

In this video, I’ll be showing you how to load image data. This is really useful for what you’ll be doing in real projects. So previously, we used MNIST. Fashion-MNIST were just toy datasets for testing your networks, but you’ll be using full-size images like you’d get from smartphone cameras and your actual projects that … Read more

Py Part 6 V1

In this video and notebook, I’ll be showing you how to save and load models. Like I said previously, you typically don’t want to have to train a new model every time you want to use it. So instead, you’ll train it once and then save it, and then if you need to use it … Read more

Py Part 5 V2

Hello, welcome back. So in this video and notebook, I’m going to be talking about inference and validation. So, inference means when we have a tree network and we’re using our network to make predictions. So neural networks have this issue where they have a tendency to perform too well on the training data, and … Read more

PyTorch – Part 4

Welcome back. So, in this notebook, you’ll be building your own neural network to classify clothing images. So, like I talked about in the last video, MNIST is actually a fairly trivial dataset these days. It’s really easy to get really high accuracy with a neural network. So instead, you’re going to be using Fashion-MNIST, … Read more

Py Part 3 V2

Hello, in this notebook, I’ll be showing you how to train a neural network with PyTorch. So, remember from the previous part we built a neural network but it wasn’t able to actually tell us what the digit was in these images. So, what we want is we want to be able to pass in … Read more

Py Part 2 V1

Hello everyone and welcome back.So,in this video, I’m going to be showing you how you actually build neural networks with PyTorch. At the end of this notebook which I’ll provide for you you’ll build your own neural network. So, let’s get started. So, the first step we import things like Normal, to import PyTorch we … Read more

Part 1 V2

Hello everyone and welcome to this lesson on deep learning with PyTorch. So, here I’ve built a bunch of Jupyter Notebooks that will lead you through actually writing the code to implement deep learning networks and Python. So, here we’re using the PyTorch framework which is somewhat newer than TensorFlow and Keras. It’s being developed … Read more

2 – Nd113 C L2 01 V1

Okay, now you’ll learn some of the lower level features of C++, and thanks for enduring this with us. Now comes the real challenge. How fast can you make your history on filter? I want to challenge you to use all those features to write the fastest possible C++ implementation, and once you found it, … Read more

1 – Nd113 Story 1 V1

So now that you suffer through all these wonderful things like, pointers, and memory allocations. So, let me tell you the story of the worst self-driving car bucket I ever caused and had to fix. Took me many months to find it. Okay. So we are, now back in 2005 driving Stanley, the self-driving car, … Read more

7 – C Opt 05 L V3

At this point, you have seen how inefficient code can cause your program to slow down by performing unnecessary CPU operations and memory accesses. Next, we will discuss the practicalities of optimizing your code. Code optimization is a big topic that involves analyzing algorithms, understanding how a computer executes instructions, and learning the nuances of … Read more

6 – 04 L C And RAM V1 RENDER V1

Let’s go into some detail about how C++ uses RAM. You can think of RAM as a set of slots where you can store information. When your program executes data, it is usually stored in RAM. This data can be overridden and in fact when you turn your computer off, data in RAM is erased … Read more

5 – 03 L Binary V1 RENDER V1

From a high level perspective, you’ve been able to see that limiting CPU instructions can make your code run faster. As humans, we think about interacting with a computer in terms of a programming language like C++. However, computers only understand instructions in binary. So everything you write will be seen by the computer as … Read more

4 – Nd113 Embedded Terminal V1

Hi. My name is Andrew Pastor, and I am a Content Developer for the Intro to Self-Driving Car Nanodegree. In this lesson, C++ Intro to Optimization, and the following lesson, C++ Optimization Practice, you’ll be using a feature of the classroom that you haven’t seen yet. When you go to the next part of the … Read more

3 – 02 L Intro To Comp HW V1 RENDER V1

Optimization is all about eliminating instructions that are not needed, while still getting the result you expect from your program. The fewer times that a program has to access memory and perform calculations, the more efficient your program will be. Optimization isn’t just about shoving your code through some black box until its performance increases, … Read more

2 – C Opt 01 L V2

Hi, I’m Anthony, the product lead here at Udacity for robotics. You’ve already learned a lot of syntax in C++, including how to write functions and classes. Now you should feel confident that anything you could write in Python, you could also write in C++. But let’s take a step back and talk about why … Read more

1 – Course Introduction

So, it’s me again, Sebastian. Hey, congratulations. You just completed something quite amazing, you translated something from Python to C++ and it sounds tedious. But I hope you learned from some of the basics how programming languages work. And how different programming languages work, because they are different. Both are the main industry standard and … Read more

2 – Why Use Object Oriented Programming

Yes, I would love to talk more about object oriented programming. Often I want to solve things with functions, I think I’m inclined to think that way. But I know there is value in thinking object orintendly. Why when designing a self-driving car, for example, why do we want to use object oriented programming? Object … Read more

1 – Introduction

C++ is a lifelong learning opportunity. Here’s a secret on me: in most of my life I wrote my code in C++ and to the present day there’s C++ code I would not be able to understand. And the reason is there’s a lot of things in C++ that are really complicated. So in the … Read more

1 – Introduction To Compilation

So far, you’ve been writing code within the Udacity classroom, in an environment that looks like this, but you’re also going to want to be able to run your programs locally on your own computer. And this brings up another important difference between Python and C++. You learned about the first major difference at the … Read more