Resource retrieval

Get the pre-trained net:

In[1]:=

Out[1]=

NetModel parameters

This model consists of a family of individual nets, each identified by a specific parameter combination. Inspect the available parameters:

In[2]:=

Out[2]=

Pick a non-default net by specifying the parameters:

In[3]:=

Out[3]=

Pick a default uninitialized net:

In[4]:=

Out[4]=

Basic usage

Classify an image:

In[5]:=

Out[5]=

The prediction is an Entity object, which can be queried:

In[6]:=

Out[6]=

Get a list of available properties for the predicted Entity:

In[7]:=

Out[7]=

Obtain the probabilities of the 10 most likely entities predicted by the net:

In[8]:=

Out[8]=

An object outside the list of the ImageIdentify Net classes will be misidentified:

In[9]:=

Out[9]=

Obtain the list of names of all available classes:

In[10]:=

Out[10]=

Feature extraction

Remove the last three layers of the trained net so that the net produces a vector representation of an image:

In[11]:=

Out[11]=

Get a set of images:

In[12]:=

Visualize the features of the set of images:

In[13]:=

Out[13]=

Transfer learning

Use the pre-trained model to build a classifier for telling apart images of motorcycles and bicycles. Create a test set and a training set:

In[14]:=

In[15]:=

Remove the linear layer from the pre-trained net:

In[16]:=

Out[16]=

Create a new net composed of the pre-trained net followed by a linear layer and a softmax layer:

In[17]:=

Out[17]=

Train on the dataset, freezing all the weights except for those in the linearNew layer (use TargetDevice -> "GPU" for training on a GPU):

In[18]:=

Out[18]=

Perfect accuracy is obtained on the test set:

In[19]:=

Out[19]=

Net information

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

In[20]:=

Out[20]=

Obtain the total number of parameters:

In[21]:=

Out[21]=

Obtain the layer type counts:

In[22]:=

Out[22]=

Export to ONNX

Export the net to the ONNX format:

In[23]:=

Out[23]=

Get the size of the ONNX file:

In[24]:=

Out[24]=

Check some metadata of the ONNX model:

In[25]:=

Out[25]=

Import the model back into Wolfram Language. However, the NetEncoder and NetDecoder will be absent because they are not supported by ONNX:

In[26]:=

Out[26]=

In[27]:=

Out[27]=