Wolfram Neural Net Repository

Immediate Computable Access to Neural Net Models

CycleGAN Photo-to-Cezanne Translation

Turn a photo into a Cezanne-style painting

Released in 2017, this model exploits a novel technique for image translation, in which two models translating from A to B and vice versa are trained jointly with adversarial training. In addition to the adversarial loss, cycle consistency is also enforced in the loss function: when the output of the first translator is fed into the second, the final result is encouraged to match the input of the first translator. This allows successful training for image translation tasks in which only unpaired training data can be collected. This model was trained to translate photos into Cezanne-style paintings.

Number of layers: 96 | Parameter count: 2,855,811 | Trained size: 12 MB |

Training Set Information

Examples

Resource retrieval

Get the pre-trained net:

In[1]:=
NetModel["CycleGAN Photo-to-Cezanne Translation"]
Out[1]=
Image

Basic usage

Run the net on a photo:

In[2]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/ba1acfc0-664b-4f5e-ba67-d95f4d5bdf4b"]
Out[2]=
Image

Adapt to any size

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

In[3]:=
net = NetModel["CycleGAN Photo-to-Cezanne Translation"]
Out[3]=
Image

Get a photo:

In[4]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/d70f41d5-1f9f-4688-a652-9d7a84f47ee3"]

Create a new encoder with the desired dimensions:

In[5]:=
netEnc = NetEncoder[{"Image", ImageDimensions[img]}]
Out[5]=
Image

Attach the new net encoder and run the network:

In[6]:=
resizedNet = NetReplacePart[ net, {"Input" -> netEnc, "Output" -> NetDecoder[{"Image"}]}]
Out[6]=
Image
In[7]:=
resizedNet[img]
Out[7]=
Image

Net information

Inspect the sizes of all arrays in the net:

In[8]:=
NetInformation[ NetModel["CycleGAN Photo-to-Cezanne Translation"], "ArraysSizes"]
Out[8]=
Image

Obtain the total number of parameters:

In[9]:=
NetInformation[ NetModel["CycleGAN Photo-to-Cezanne Translation"], \ "ArraysTotalElementCount"]
Out[9]=
Image

Obtain the layer type counts:

In[10]:=
NetInformation[ NetModel["CycleGAN Photo-to-Cezanne Translation"], "LayerTypeCounts"]
Out[10]=
Image

Display the summary graphic:

In[11]:=
NetInformation[ NetModel["CycleGAN Photo-to-Cezanne Translation"], "SummaryGraphic"]
Out[11]=
Image

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 Photo-to-Cezanne Translation"], "MXNet"]
Out[12]=
Image

Export also creates a net.params file containing parameters:

In[13]:=
paramPath = FileNameJoin[{DirectoryName[jsonPath], "net.params"}]
Out[13]=
Image

Get the size of the parameter file:

In[14]:=
FileByteCount[paramPath]
Out[14]=
Image

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

In[15]:=
ResourceObject["CycleGAN Photo-to-Cezanne Translation"]["ByteCount"]
Out[15]=
Image

Represent the MXNet net as a graph:

In[16]:=
Import[jsonPath, {"MXNet", "NodeGraphPlot"}]
Out[16]=
Image

Requirements

Wolfram Language 11.3 (March 2018) or above

Resource History

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

Reference