squeezesegv2Network
Create SqueezeSegV2 segmentation network for organized lidar point cloud
Since R2024a. Recommended over squeezesegv2Layers
.
Description
creates a SqueezeSegV2 segmentation network and returns it as net
= squeezesegv2Network(inputSize
,numClasses
)net
, a
dlnetwork
(Deep Learning Toolbox) object, for organized point
clouds of size inputSize
and the number of classes
numClasses
.
SqueezeSegV2 is a convolutional neural network that predicts pointwise labels for an organized lidar point cloud.
specifies options using one or more name-value arguments in addition to the input arguments
in the preceding syntax. For example,
net
= squeezesegv2Network(___,Name=Value
)squeezesegv2Network(inputSize,numClasses,NumEncoderModules=4)
sets the
number of encoders used to create the network to four.
Note
This function requires Deep Learning Toolbox™.
Examples
Input Arguments
Output Arguments
More About
References
[1] Wu, Bichen, Xuanyu Zhou, Sicheng Zhao, Xiangyu Yue, and Kurt Keutzer. “SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud.” In 2019 International Conference on Robotics and Automation (ICRA), 4376–82. Montreal, QC, Canada: IEEE, 2019.https://doi.org/10.1109/ICRA.2019.8793495.
Version History
Introduced in R2024aSee Also
Functions
pointnetplusNetwork
|pcsemanticseg
|trainnet
(Deep Learning Toolbox) |evaluateSemanticSegmentation
Objects
dlnetwork
(Deep Learning Toolbox)