Deep Learning Frameworks
You have learned to implement deep learning algorithms using Python and NumPy almost from scratch. Glad you did so, because I hope you understand what these deep learning algorithms are actually doing. But you will find that unless you apply a more complex model, such as a convolutional neural network, or a recurrent neural network, or when you start to apply a very large model, it becomes less and less practical, at least for most people It is unrealistic to start from scratch by yourself.
Fortunately, there are many good deep learning software frameworks that can help you implement these models. By analogy, I guess you know how to do matrix multiplication, and you should also know how to program two matrices to multiply, but when you are building a large application, you probably do n’t want to use your own matrix multiplication function, but rather To access a numerical linear algebra library, it will be more efficient, but it is useful if you understand how multiplication of two matrices is. I think deep learning is very mature now. Using some deep learning frameworks will be more practical and will make your work more effective. Let us look at the frameworks.
There are many deep learning frameworks that can make it easier to implement neural networks. Let's talk about the main ones. Each framework is aimed at a certain user or development group. I think every framework here is a reliable choice for a certain type of application. Many people have written articles to compare these deep learning frameworks and how well these deep learning frameworks have developed. , And because these frameworks are constantly evolving and improving every month, if you want to see a discussion about the pros and cons of these frameworks, I leave it to you to search online, but I think many frameworks are fast Progress is getting better and better, so I will not make a strong recommendation, but share with you the criteria for choosing a framework.
An important criterion is ease of programming, which includes both the development and iteration of neural networks, as well as the configuration of products. For the actual use of thousands or even hundreds of millions of users, it depends on what you want to do.
The second important criterion is running speed, especially when training large data sets, some frameworks allow you to run and train neural networks more efficiently.
There is another standard that people do n’t mention often, but I think it ’s very important whether that framework is really open. If a framework is really open, it needs not only open source but also good management. Unfortunately, in the software industry, some companies have a history of open source software, but the company maintains full control of the software. When several years passed and people started using their software, some companies began to gradually close the resources that were once open. , Or transfer the function to their exclusive cloud service. So one thing I will pay attention to is whether you can believe that this framework can remain open source for a long time, rather than under the control of a company, it may choose to stop open source for some reason in the future, even if the software is now based on Released in the form of open source. But at least in the short term, it depends on your preference for the language, depending on whether you prefer Python , Java or ** C ++ ** or whatever, also depends on the application you are developing, whether it is computer vision or natural language processing or wire Advertisement, etc., I think multiple frameworks here are good choices.
The program framework is here. By providing a higher degree of abstraction than the numerical linear algebra library, each of the program frameworks here can make you more efficient when developing deep machine learning applications.
Course PPT
