Wolfram Research

ShuffleNet-V1 Trained on ImageNet Competition Data

Identify the main object in an image

Released in 2017, ShuffleNet is designed specially for mobile devices with very limited computing power. Its architecture utilizes two new operations: pointwise group convolutions and channel shuffling, greatly reducing computational cost while maintaining accuracy.

Number of layers: 203 | Parameter count: 1,420,152 | Trained size: 7 MB |

Training Set Information

Performance

Examples

Resource retrieval

Get the pre-trained net:

In[1]:=
NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"]
Out[1]=

Basic usage

Classify an image:

In[2]:=
pred = NetModel[
   "ShuffleNet-V1 Trained on ImageNet Competition Data"][\!\(\*
GraphicsBox[
TagBox[RasterBox[CompressedData["
1:eJwcu2V0XGe2rV22Y4oZZIEFFjMzl5hZqioxs1RiZmYGy7bMMsZMsRMndhIn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"], {{0, 102.}, {88., 0}}, {0, 255},
ColorFunction->RGBColor],
BoxForm`ImageTag["Byte", ColorSpace -> "RGB", Interleaving -> True],
Selectable->False],
DefaultBaseStyle->"ImageGraphics",
ImageSizeRaw->{88., 102.},
PlotRange->{{0, 88.}, {0, 102.}}]\)]
Out[2]=

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

In[3]:=
pred["Definition"]
Out[3]=

Get a list of available properties of the predicted Entity:

In[4]:=
pred["Properties"]
Out[4]=

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

In[5]:=
NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"][\!\(\*
GraphicsBox[
TagBox[RasterBox[CompressedData["
1:eJwcu2V0XGe2rV22Y4oZZIEFFjMzl5hZqioxs1RiZmYGy7bMMsZMsRMndhIn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"], {{0, 102.}, {88., 0}}, {0, 255},
ColorFunction->RGBColor],
BoxForm`ImageTag["Byte", ColorSpace -> "RGB", Interleaving -> True],
Selectable->False],
DefaultBaseStyle->"ImageGraphics",
ImageSizeRaw->{88., 102.},
PlotRange->{{0, 88.}, {0, 102.}}]\), {"TopProbabilities", 10}]
Out[5]=

An object outside the list of the ImageNet classes will be misidentified:

In[6]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/0b6dfbfa-2ea7-421a-a095-a4cae272d0a4"]
Out[6]=

Obtain the list of names of all available classes:

In[7]:=
EntityValue[
 NetExtract[
   NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"], "Output"][["Labels"]], "Name"]
Out[7]=

Feature extraction

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

In[8]:=
extractor = NetDrop[NetModel[
   "ShuffleNet-V1 Trained on ImageNet Competition Data"], -3]
Out[8]=

Get a set of images:

In[9]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/616cbb6c-ab92-4253-a390-774c9adc28c1"]

Visualize the features of a set of images:

In[10]:=
FeatureSpacePlot[imgs, FeatureExtractor -> extractor, LabelingSize -> 100, ImageSize -> 600]
Out[10]=

Visualize convolutional weights

Extract the weights of the first convolutional layer in the trained net:

In[11]:=
weights = NetExtract[
   NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"], {1,
     "Weights"}];

Show the dimensions of the weights:

In[12]:=
Dimensions[weights]
Out[12]=

Visualize the weights as a list of 24 images of size 3⨯3:

In[13]:=
ImageAdjust[Image[#, Interleaving -> False]] & /@ Normal[weights]
Out[13]=

Transfer learning

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

In[14]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/7ee7cada-dfe3-4d8d-86eb-c96999132bcb"]
In[15]:=
(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/506a3dc5-42c1-4bf7-b0aa-feb75c822a5f"]

Remove the last layers from the pre-trained net:

In[16]:=
tempNet = NetDrop[NetModel[
   "ShuffleNet-V1 Trained on ImageNet Competition Data"], -2]
Out[16]=

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

In[17]:=
newNet = NetChain[<|"pretrainedNet" -> tempNet, "linearNew" -> LinearLayer[], "softmax" -> SoftmaxLayer[]|>, "Output" -> NetDecoder[{"Class", {"sunflower", "rose"}}]]
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]:=
trainedNet = NetTrain[newNet, trainSet, LearningRateMultipliers -> {"linearNew" -> 1, _ -> 0}]
Out[18]=

Accuracy obtained on the test set:

In[19]:=
ClassifierMeasurements[trainedNet, testSet, "Accuracy"]
Out[19]=

Net information

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

In[20]:=
Information[
 NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"], \
"ArraysElementCounts"]
Out[20]=

Obtain the total number of parameters:

In[21]:=
Information[
 NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"], \
"ArraysTotalElementCount"]
Out[21]=

Obtain the layer type counts:

In[22]:=
Information[
 NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"], \
"LayerTypeCounts"]
Out[22]=

Display the summary graphic:

In[23]:=
Information[
 NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"], \
"SummaryGraphic"]
Out[23]=

Export to ONNX

Export the net to the ONNX format:

In[24]:=
onnxFile = Export[FileNameJoin[{$TemporaryDirectory, "net.onnx"}], NetModel["ShuffleNet-V1 Trained on ImageNet Competition Data"]]
Out[24]=

Get the size of the ONNX file:

In[25]:=
FileByteCount[onnxFile]
Out[25]=

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

In[26]:=
ResourceObject[
  "ShuffleNet-V1 Trained on ImageNet Competition Data"]["ByteCount"]
Out[26]=

Check some metadata of the ONNX model:

In[27]:=
{OpsetVersion, IRVersion} = {Import[onnxFile, "OperatorSetVersion"], Import[onnxFile, "IRVersion"]}
Out[27]=

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

In[28]:=
Import[onnxFile]
Out[28]=

Resource History

Reference