CycleGAN Horse-to-Zebra Translation Trained on ImageNet Competition Data

Turn horses into zebras in a photo

Number of layers: 94 | Parameter count: 2,855,811 | Trained size: 12 MB |

Training Set Information

ImageNet Large Scale Visual Recognition Challenge 2012 classification dataset, consisting of 1.2 million training images, with 1,000 classes of objects. Only classes "horse" and "zebra" were used for training.

Examples

Download Example Notebook

Open in Wolfram Cloud

Resource retrieval

Get the pre-trained net:

In[1]:=

$NetModel["CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"]$

Out[1]=

Basic usage

Run the net on a photo:

In[2]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/aed98646-c29a-4f43-872c-aecb42178385"]

Out[2]=

Adapt to any size

Automatic image resizing can be avoided by replacing the net encoders. First get the net:

In[3]:=

$net = NetModel[ "CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"]$

Out[3]=

Get a photo:

In[4]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/1afdcdc9-5d45-4e7c-9745-a16a44be3c18"]

Create a new encoder with the desired dimensions:

In[5]:=

Out[5]=

Attach the new net encoder and run the network:

In[6]:=

Out[6]=

In[7]:=

Out[7]=

Net information

Inspect the sizes of all arrays in the net:

In[8]:=

$NetInformation[ NetModel["CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"], "ArraysSizes"]$

Out[8]=

Obtain the total number of parameters:

In[9]:=

$NetInformation[ NetModel["CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"], "ArraysTotalElementCount"]$

Out[9]=

Obtain the layer type counts:

In[10]:=

$NetInformation[ NetModel["CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"], "LayerTypeCounts"]$

Out[10]=

Display the summary graphic:

In[11]:=

$NetInformation[ NetModel["CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"], "SummaryGraphic"]$

Out[11]=

Export to MXNet

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

In[12]:=

$jsonPath = Export[FileNameJoin[{$TemporaryDirectory, "net.json"}], NetModel["CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"], "MXNet"]$

Out[12]=

Export also creates a net.params file containing parameters:

In[13]:=

Out[13]=

Get the size of the parameter file:

In[14]:=

Out[14]=

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

In[15]:=

$ResourceObject[ "CycleGAN Horse-to-Zebra Translation Trained on ImageNet \ Competition Data"]["ByteCount"]$

Out[15]=

Represent the MXNet net as a graph:

In[16]:=

Out[16]=

Construction Notebook

Download Construction Notebook

Open in Wolfram Cloud

Requirements

Wolfram Language 11.3 (March 2018) or above

Resource History

Date Created: 12 February 2018
Latest Update: 21 June 2018

Reference

J. Zhu, T. Park, P. Isola, A. A. Efros, "Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks," arXiv:1703.10593 (2017)
Available from: https://github.com/junyanz/CycleGAN
Rights: BSD 3-Clause "Modified" License