Wolfram Research

CIFAR-100

CIFAR-100 computer-vision training dataset

The CIFAR-100 dataset contains 50,000 training and 10,000 test images of 20 object classes, along with 100 object subclasses. It is traditional to train on the 100 object subclasses. Each image is an RGB image of size 32x32.

Examples

Basic Examples

Retrieve the resource:

In[1]:=
ResourceObject["CIFAR-100"]
Out[1]=

View the data:

In[2]:=
ResourceData["CIFAR-100"]
Out[2]=

Analysis

View the list of classes in the dataset:

In[3]:=
classes = DeleteDuplicates[Values[ResourceData["CIFAR-100"]]]
Out[3]=

Obtain one example of each class:

In[4]:=
sample = Cases[ResourceData["CIFAR-100"], 
     HoldPattern[_ -> #]][[-1]] & /@ classes
Out[4]=

Test the ImageIdentify function on an example image:

In[5]:=
example = \!\(\*
GraphicsBox[
TagBox[RasterBox[CompressedData["
1:eJw10/lTWlmiB/Cueb+8H6dqfngzbaKx85LpnkxcEjV2Eo24sLkg+y4g6xWE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"], {{0, 32}, {32, 0}}, {0, 255},
ColorFunction->RGBColor],
BoxForm`ImageTag["Byte", ColorSpace -> "RGB", Interleaving -> True],
Selectable->False],
DefaultBaseStyle->"ImageGraphics",
ImageSizeRaw->{32, 32},
PlotRange->{{0, 32}, {0, 32}}]\) -> "castle"
Out[5]=
In[6]:=
ImageIdentify[Keys[example]]
Out[6]=

Wolfram Research, "CIFAR-100" from the Wolfram Data Repository (2018) https://doi.org/10.24097/wolfram.36758.data

Data Resource History

Source Metadata

Publisher Information