Released in 2017, this architecure combines the technique of dilated convolutions with the paradigm of residual networks, outperforming their nonrelated counterparts in image classification and semantic segmentation.
Number of layers: 142 |
Parameter count: 26,110,275 |
Trained size: 105 MB |
Examples
Resource retrieval
Get the pre-trained net:
Evaluation function
Write an evaluation function to handle net reshaping and resampling of input and output:
Label list
Define the label list for this model. Integers in the model’s output correspond to elements in the label list:
Basic usage
Obtain a segmentation mask for a given image:
Inspect which classes are detected:
Visualize the mask:
Advanced visualization
Associate classes to colors using the standard Cityscapes palette:
Write a function to overlap the image and the mask with a legend:
Inspect the results:
Net information
Inspect the number of parameters of all arrays in the net:
Obtain the total number of parameters:
Obtain the layer type counts:
Display the summary graphic:
Export to MXNet
Export the net into a format that can be opened in MXNet:
Export also creates a net.params file containing parameters:
Get the size of the parameter file:
The size is similar to the byte count of the resource object:
Requirements
Wolfram Language 11.3
(March 2018) or above
Resource History
Reference