From the course: Deep Learning with Python: Convolutional Neural Networks
Join today to access over 24,700 courses taught by industry experts.
Pooling layers - Python Tutorial
From the course: Deep Learning with Python: Convolutional Neural Networks
Pooling layers
- [Instructor] After one or more convolution layers comes a pooling layer. Pooling reduces the spatial size, width, and height of the feature maps while retaining the most important information. The most common type of pooling is max pooling. Max pooling involves partitioning a feature map into patches and outputting the maximum value in each patch. This effectively summarizes the presence of a feature in that region. Let's walk through an example that illustrates how max polling actually works. Say, at the end of the convolution process, we have the following feature map as one of several created by the network. Typically, pooling is done over two by two regions with a stride of two, so it usually has the width and height of the feature map. Similar to what happened during the convolution process, we start the pooling process from the top left corner. The maximum value in the selected region of the feature map is four. Next, we shift with a stride of two. The maximum value in this…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.