Examples

Resource retrieval

Get the pre-trained net:

In[1]:=

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:

In[2]:=

Basic usage

Colorize a grayscale image using the evaluation function:

In[3]:=

Out[3]=

Performance evaluation

Get a color image:

In[4]:=

Compare the colorization performed by the net with the ground truth:

In[5]:=

Out[5]=

Net information

Inspect the number of parameters of all arrays in the net:

In[6]:=

Out[6]=

Obtain the total number of parameters:

In[7]:=

Out[7]=

Obtain the layer type counts:

In[8]:=

Out[8]=

Display the summary graphic:

In[9]:=

Out[9]=

Export to MXNet

Export the net into a format that can be opened in MXNet:

In[10]:=

Out[10]=

Export also creates a net.params file containing parameters:

In[11]:=

Out[11]=

Get the size of the parameter file:

In[12]:=

Out[12]=

The size is similar to the byte count of the resource object:

In[13]:=

Out[13]=

Represent the MXNet net as a graph:

In[14]:=

Out[14]=

Requirements

Wolfram Language 11.2 (September 2017) or above

Resource History

• Date Created: 9 October 2017
• Latest Update: 21 June 2018

Reference

• S. Iizuka, E. Simo-Serra, H. Ishikawa, "Let There Be Color!: Joint End-to-End Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification," ACM Transactions on Graphics (Proc. of SIGGRAPH 2016) 35(4) (2016)
• Available from: https://github.com/satoshiiizuka/siggraph2016_colorization
• Rights: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)