Resource retrieval

Retrieve the resource object:

In[1]:=

Out[1]=

Get the pre-trained net:

In[2]:=

Out[2]=

Basic usage

Compute a feature vector for a given image:

In[3]:=

Get the length of the feature vector:

In[4]:=

Out[4]=

Use a batch of face images:

In[5]:=

Compute the feature vectors for the batch of images, and obtain the dimensions of the features:

In[6]:=

In[7]:=

Out[7]=

Reduce the feature vectors to two dimensions with t-SNE:

In[8]:=

Out[8]=

In[9]:=

Out[9]=

Visualize the results:

In[10]:=

Out[10]=

Obtain the five closest faces to a given one:

In[11]:=

Out[11]=

Net information

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

In[12]:=

Out[12]=

Obtain the total number of parameters:

In[13]:=

Out[13]=

Obtain the layer type counts:

In[14]:=

Out[14]=

Display the summary graphic:

In[15]:=

Out[15]=

Export to MXNet

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

In[16]:=

Out[16]=

Export also creates a net.params file containing parameters:

In[17]:=

Out[17]=

Get the size of the parameter file:

In[18]:=

Out[18]=

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

In[19]:=

Out[19]=