-
How to design Conv Network:
-
The first thing to understand is what is the sensory eye
-
first conv a pink pixel represents a 3x3 perceived region
-
Second conv a pink pixel represents a 5x5 perceived region
-
Three convolutional layers are superimposed, and the final sensory eye range is 7x7
-
Fewer parameters, more nonlinearities, and fewer computations
-
1x1 is actually the core point of the residual network 3.25 is not true 6C^2
-
The main idea of designing a network
-
深度学习-How to design Conv Network
最新推荐文章于 2024-07-16 00:35:19 发布