Train an Anomaly Detector for Images
This example shows how to create an anomaly detector for a specific dataset of images.
Obtain a dataset of images.
In[1]:=1

✖
In[2]:=2

✖
Out[2]=2

Train an anomaly detector on the dataset.
In[3]:=3

✖
Out[3]=3

Obtain information about the anomaly detector.
In[4]:=4

✖
Out[4]=4

Use the detector on new images.
In[5]:=5

✖
Out[5]=5

Compare with the results obtained on corrupted images.
In[6]:=6

✖
Out[6]=6

Visualize the behavior of the probability to find a rarer image (RarerProbability) for various levels of corruption.
In[7]:=7

✖
Out[7]=7

In[8]:=8

✖
Out[8]=8
