How to use tensorflow to build a two-layer CNN Network
This article introduces the relevant knowledge of "how to use tensorflow to build a two-tier CNN network". In the operation of actual cases, many people will encounter such a dilemma, so let the editor lead you to learn how to deal with these situations. I hope you can read it carefully and be able to achieve something!
Briefly explain the characteristics of CNN:
(1) Local connection (2) weight sharing (3) pooling operation (4) hierarchical structure
01
-
The idea of building a network
1. Prepare training data
2. Define the node (placeholder) ready to accept data (placeholder)
3. Define convolution layer
4. Define loss expression
5. Choose the optimizer optimizer to minimize the loss
Steps to perform tensorflow:
(1) construct data flow graph
(2) execute the session
02
-
Specific implementation code
All right, I'm going to start!
Preparatory work
1. Prepare training data (use datasets with mnist)
2. Define the node (placeholder) ready to accept data (placeholder)
3. Define convolution layer
4. Define loss expression
5. Choose the optimizer optimizer to minimize the loss
The detailed code is as follows:
Https://github.com/SCUTPZW/AI_study/tree/master
This is the end of the content of "how to use tensorflow to build a two-tier CNN network". Thank you for reading. If you want to know more about the industry, you can follow the website, the editor will output more high-quality practical articles for you!
