Which is better strided convolution or max pooling?
In essence, max-pooling (or any kind of pooling) is a fixed operation and replacing it with a strided convolution can also be seen as learning the pooling operation, which increases the model’s expressiveness ability. The down side is that it also increases the number of trainable parameters, but this is not a real problem in our days.
Which is cheaper to learn pooling or convolution?
Pooling is a fixed operation and convolution can be learned. On the other hand, pooling is a cheaper operation than convolution, both in terms of the amount of computation that you need to do and number of parameters that you need to store (no parameters for pooling layer).
Are there any downsides to strided convolutions in deep learning?
The down side is that it also increases the number of trainable parameters, but this is not a real problem in our days. There is a very good article by JT Springenberg, where they replace all the max-pooling operations in a network with strided-convolutions.
Which is better stride or pooling for downsampling?
If you use stride=1 and pooling for downsampling, then you will end up with convolution that does 4 times more computation + extra computation for the next pooling layer. The same trick was used in SqueezeNet and some other neural network architectures.
Where to find padding and stride in deep learning?
Padding and Stride — Dive into Deep Learning 0.16.6 documentation 6. Convolutional Neural Networksnavigate_next6.3. Padding and Stride search Quick search code Show Source MXNet PyTorch Notebooks Courses GitHub 中文版 Table Of Contents Preface
How does padding and stride affect the output?
Padding can increase the height and width of the output. This is often used to give the output the same height and width as the input. The stride can reduce the resolution of the output, for example reducing the height and width of the output to only (1/n)of the height and width of the input ((n)is an integer greater than (1)).