roiMaxPooling2dLayer
Neural network layer used to output fixed-size feature maps for rectangular ROIs
Description
An ROI max pooling layer outputs fixed size feature maps for every rectangular ROI within the input feature map. Use this layer to create a Fast or Faster R-CNN object detection network.
Given an input feature map of size [HWCN], whereCis the number of channels andNis the number of observations, the output feature map size is [heightwidthCsum
(M)], whereheight和widthare the output size.Mis a vector of lengthN和M(i) is the number of ROIs associated with thei-th input feature map.
该层有两个输入:
'in'
— The input feature map that will be cropped'roi'
— A list of ROIs to pool
Use the input names when connecting or disconnecting the ROI max pooling layer to other layers using连接器
(Deep Learning Toolbox)或者disconnectLayers
(Deep Learning Toolbox)(requires Deep Learning Toolbox™).
Creation
Syntax
Description
layer = roimaxpooling2dlayer(outputsize)
creates a max pooling layer for ROIs and sets theOutputSize
property.
Properties
Examples
Version History
See Also
trainFastRCNNObjectDetector
|trainFasterRCNNObjectDetector
|roiInputLayer
|maxPooling2dLayer
(Deep Learning Toolbox)|layerGraph
(Deep Learning Toolbox)|连接器
(Deep Learning Toolbox)|removeLayers
(Deep Learning Toolbox)
Topics
- 创建快速R-CNN对象检测网络
- 创建更快R-CNN对象检测Network
- Getting Started with R-CNN, Fast R-CNN, and Faster R-CNN
- Deep Learning in MATLAB(Deep Learning Toolbox)
- List of Deep Learning Layers(Deep Learning Toolbox)