Pytorch's low-level API mainly includes tensor operations, dynamic calculation graphs and automatic differentiation.
If the model is compared to a house, then the low-level API is [the brick of the model].
At the low-level API level, Pytorch can be used as an enhanced version of numpy.
The method provided by Pytorch is more comprehensive than numpy, and the calculation speed is faster. If necessary, you can also use the GPU for acceleration.
In the previous chapters, we already have an overall understanding of low-level APIs. In this chapter, we will focus on detailing tensor operations and dynamic calculation graphs.
The operations of tensors mainly include structural operations of tensors and mathematical operations of tensors.
Tensor structure operations such as: tensor creation, index slicing, dimension transformation, merge and split.
Tensor mathematical operations mainly include: scalar operations, vector operations, and matrix operations. In addition, we will introduce the broadcasting mechanism of tensor operations.
Dynamic calculation graph We will mainly introduce the characteristics of dynamic calculation graph, function in calculation graph, calculation graph and backpropagation.
If this book is helpful to you and want to encourage the author, remember to add a star⭐️ to this project and share it with your friends 😊!
If you need to further communicate with the author on the understanding of the content of this book, please leave a message under the public account "Algorithm Food House". The author has limited time and energy and will respond as appropriate.
You can also reply to the keyword in the background of the official account: Add group, join the reader exchange group and discuss with you.
