Released in 2016, this net automatically colorizes a grayscale image, exploiting a combination of local and global image features. Local features are extracted in a fully convolutional fashion, while the extraction of global features was developed leveraging the labels of the Places dataset during training.
Number of layers: 62 |
Parameter count: 45,505,890 |
Trained size: 182 MB |
Examples
Resource retrieval
Get the pre-trained net:
Out[1]= |  |
Evaluation function
This net takes a grayscale image as input and outputs the A and B channels in the LAB color space. It needs an evaluation function to merge its output with the luminance of the input:
Basic usage
Colorize a grayscale image using the evaluation function:
Out[3]= |  |
Performance evaluation
Get a color image:
Compare the colorization performed by the net with the ground truth:
Out[5]= |  |
Net information
Inspect the number of parameters of all arrays in the net:
Out[6]= |  |
Obtain the total number of parameters:
Out[7]= |  |
Obtain the layer type counts:
Out[8]= |  |
Display the summary graphic:
Out[9]= |  |
Export to MXNet
Export the net into a format that can be opened in MXNet:
Out[10]= |  |
Export also creates a net.params file containing parameters:
Out[11]= |  |
Get the size of the parameter file:
Out[12]= |  |
The size is similar to the byte count of the resource object:
Out[13]= |  |
Represent the MXNet net as a graph:
Out[14]= |  |
Requirements
Wolfram Language 11.2
(September 2017) or above
Resource History
Reference