Wolfram Neural Net Repository

Immediate Computable Access to Neural Net Models

Inception V1 Trained on Extended Salient Object Subitizing Data

Count the number of prominent items in an image

Released in 2016, this neural net is a fine-tuning of the Inception V1 model trained on the Extended Salient Object Subitizing dataset. In order to improve the performance, the dataset has been enlarged by more than a factor of 2 with synthetic images, obtained by placing segmented objects over background images.

Number of layers: 147 | Parameter count: 5,978,677 | Trained size: 24 MB |

Training Set Information

Performance

Examples

Resource retrieval

Get the pre-trained net:

In[1]:=
NetModel["Inception V1 Trained on Extended Salient Object Subitizing \ Data"]
Out[1]=

Basic usage

Obtain the number of salient objects in an image:

In[2]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/806a1d53-f765-49a5-85f0-2793da36dc24"]
Out[2]=

Obtain the probabilities:

In[3]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/f6ac822f-9ec2-4a24-afe4-b0d5dec37ebe"]
Out[3]=

Net information

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

In[4]:=
NetInformation[ NetModel["Inception V1 Trained on Extended Salient Object Subitizing \ Data"], "ArraysElementCounts"]
Out[4]=

Obtain the total number of parameters:

In[5]:=
NetInformation[ NetModel["Inception V1 Trained on Extended Salient Object Subitizing \ Data"], "ArraysTotalElementCount"]
Out[5]=

Obtain the layer type counts:

In[6]:=
NetInformation[ NetModel["Inception V1 Trained on Extended Salient Object Subitizing \ Data"], "LayerTypeCounts"]
Out[6]=

Display the summary graphic:

In[7]:=
NetInformation[ NetModel["Inception V1 Trained on Extended Salient Object Subitizing \ Data"], "SummaryGraphic"]
Out[7]=

Export to MXNet

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

In[8]:=
jsonPath = Export[FileNameJoin[{$TemporaryDirectory, "net.json"}], NetModel["Inception V1 Trained on Extended Salient Object \ Subitizing Data"], "MXNet"]
Out[8]=

Export also creates a net.params file containing parameters:

In[9]:=
paramPath = FileNameJoin[{DirectoryName[jsonPath], "net.params"}]
Out[9]=

Get the size of the parameter file:

In[10]:=
FileByteCount[paramPath]
Out[10]=

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

In[11]:=
ResourceObject[ "Inception V1 Trained on Extended Salient Object Subitizing \ Data"]["ByteCount"]
Out[11]=

Represent the MXNet net as a graph:

In[12]:=
Import[jsonPath, {"MXNet", "NodeGraphPlot"}]
Out[12]=

Requirements

Wolfram Language 11.2 (September 2017) or above

Resource History

  • Date Created: 17 August 2017
  • Latest Update: 21 June 2018

Reference