Udacity Nanodegree
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
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
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
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
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
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
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
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
Hey there, my name is Cezanne Camacho and I’m an instructor here at Udacity. I’ve been working on our self-driving car course which focuses on how a car sees the world through cameras and sensors and then makes driving decisions based on what it sees. And deep learning is one of the most exciting tools … Read more
What is a function declaration, and why is it important? A function declaration has multiple pieces and this is a little easier to look at in code. Maybe let’s look at your tests normalize function. When you look at just the way the function is defined, there’s the bool and then the tests normalize and … Read more
Something else I noticed interesting about methods or functions in C++. I actually found this one out by accident when I wrote two functions that had the same name. Let me see if I can find it. So I wrote two functions that were both called close enough, and one was meant to compare two … Read more
>> You said the header files they have function declarations. They can have a lot more. If you wanted to define a type that was the grid type, instead of using this vector vector float. Because you get kind of tired of saying that. >> I was writing that a lot, yeah. >> You can … Read more
So I think I have some understanding of this, but if for example, doubles are more precise than floats, why not just always use doubles? Because they’re bigger. It doesn’t really matter if you’re doing a small program, but if you needed to do a program where you had a million variables, doubles are twice … Read more
So in researching some C++ stuff, I kept seeing the term static typing and language is being referred to as statically typed, and C++ was one of those. Can you explain what does it mean for a language to be statically typed? When you go to C++, you’re going to have to tell the compiler … Read more
So welcome Elicia. Thank you so much for coming in today. Hey, Andy. Thank you for inviting me. So I have been trying to learn C++. I’m not an expert myself. And the first thing I did when I was trying to learn this language was try to convert some of that histogram filter code … Read more
Now that you’re all set up, it’s time to start writing some code. But before we jump in, we should say a couple things about how these lessons are formatted. Right. And the goal of this course is simple in some ways: translate Python code to C++. Now there’s a good amount you’ll need to … Read more
C++ is the language of self-driving cars. It’s also a programming language that’s a lot closer to what devices like the NVIDIA PX2 understand than a higher level language like Python. So if you want to get a job in this field, it’s something you’re going to have to learn. And while C++ is in … Read more
Great job. You’ve reached the end of the lesson and you don’t have to memorize all the things you learned here and you can look them up. But it’s good that you get an understanding of how functions work and C++ and similar constructs. So pat yourself at the shoulder. Okay. You got to this … Read more
>> So I guess the misconception I had was that the unique identifier to the function was the name, close enough. But it’s not, it’s the signature. It’s this whole, it’s the return value, the name, and all the inputs and their types. >> Yes. >> Okay, that’s helpful. >> Good.
So with the Test-Normalized function we had the return-type bold, the name Test-Normalized, open and closed parenthesis, but I imagine this isn’t the total picture because this function didn’t take any arguments. That’s true. And if it was in a header file instead of that open curly brace you would have a semicolon to say … Read more
댓글을 달려면 로그인해야 합니다.