Resource retrieval

Retrieve the resource object:

In[1]:=

Out[1]=

Retrieve the pre-trained net:

In[2]:=

Out[2]=

Basic usage

Apply the trained net to a set of inputs:

In[3]:=

Out[3]=

Give class probabilities for a single input:

In[4]:=

Out[4]=

Feature extraction

Create a subset of the MNIST dataset:

In[5]:=

Out[5]=

Remove the last linear layer of the net, which will be used as a feature extractor:

In[6]:=

Out[6]=

Visualize the features of a subset of the MNIST dataset:

In[7]:=

Out[7]=

Visualization of net operation

Extract the convolutional features from the first layer:

In[8]:=

Out[8]=

Visualize the features:

In[9]:=

Out[9]=

Training the uninitialized architecture

Retrieve the uninitialized architecture:

In[10]:=

Out[10]=

Retrieve the MNIST dataset:

In[11]:=

Out[11]=

Use the training dataset provided:

In[12]:=

Out[12]=

Use the test dataset provided:

In[13]:=

Out[13]=

Train the net:

In[14]:=

Out[14]=

Generate a ClassifierMeasurementsObject of the net with the test set:

In[15]:=

Out[15]=

Evaluate the accuracy on the validation set:

In[16]:=

Out[16]=

Visualize the confusion matrix:

In[17]:=

Out[17]=

Net information

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

In[18]:=

Out[18]=

Obtain the total number of parameters:

In[19]:=

Out[19]=

Obtain the layer type counts:

In[20]:=

Out[20]=

Display the summary graphic:

In[21]:=

Out[21]=

Export to MXNet

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

In[22]:=

Out[22]=

Export also creates a net.params file containing parameters:

In[23]:=

Out[23]=

Get the size of the parameter file:

In[24]:=

Out[24]=

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

In[25]:=

Out[25]=

Represent the MXNet net as a graph:

In[26]:=

Out[26]=