What can learning pytorch do?

PyTorch Is based on Python Scientific computing class library , There are mainly the following two applications ：

• As Numpy The replacement of , make the best of GPU Computing power .( At a low price GPU Card, find out )
• Provide a flexible 、 Fast deep learning platform .

Learn to pytorch Can do ？

PyTorch yes be based on Lua Scientific computing framework Torch. stay PyTorch and Keras/TensorFlow Before ,Caffe and Torch The in-depth learning package is the most popular . However , As deep learning begins to revolutionize almost all areas of Computer Science , Developers and researchers need an efficient 、 Easy to use libraries to build 、 Training and evaluation . Python and R They are the two most popular programming languages for data scientists and machine learning , So the researchers hope that in their Python It is natural to use deep learning algorithms in ecosystems .

PyTorch Solved the problem that researchers are using Keras and TensorFlow A lot of problems encountered in . although Keras Very easy to use , On the other hand ,TensorFlow You can also handle similar things in advance , But they're not Pythonic, And it's usually hard to sort out ,PyTorch By creating a Pythonic And easy to customize API These problems were solved , Allow new layer types to be implemented 、 Optimizer and novel architecture . But as the PyTorch 1.x and TensorFlow 2.x Since its publication , Each library's API Basically integrated . PyTorch and TensorFlow Now we have basically the same function , And provide API And function calls to do the same thing , Don't bother to say that it is the best deep learning open source framework .

PyTorch The performance on all these indicators is excellent .“ pythonic ” The coding style makes it easy to learn and use .GPU Speed up , Supporting distributed computing and automatic gradient computing helps to automatically execute backward transfer from forward expression .

Of course , because Python, It risks running slowly , But high performance C++ API (libtorch) This difference in speed is eliminated .

Share some of my artificial intelligence learning materials for free , For a long time , Very comprehensive . Including some AI Common framework actual combat video 、 Image recognition 、OpenCV、NLQ、 machine learning 、pytorch、 Computer vision 、 Videos such as deep learning and neural network 、 Courseware source code 、 Famous essence resources at home and abroad 、AI Hot papers 、 Industry reports, etc .

For better systematic learning AI, I recommend that you collect one .

Here are some screenshots , Free download method is attached at the end of the article .

One 、 AI must read books

Two 、 Free video on artificial intelligence courses and projects

3、 ... and 、 Collection of papers on artificial intelligence

Four 、 AI Industry Report

Learn Artificial Intelligence well , Read more , Do more , practice , If you want to improve your level , We must learn to settle down and learn slowly and systematically , Only in the end can we gain something .

Click on the business card below , Scan the code and download the information for free .