AERΒΆ

path: orion.primitives.aer.AER

description: this an autoencoder-based model capable of creating both prediction-based and reconstruction-based anomaly scores.

see json.

argument

type

description

parameters

X

numpy.ndarray

n-dimensional array containing the input sequences for the model

y

numpy.ndarray

n-dimensional array containing the target sequences we want to reconstruct. Typically y is a signal from a selected set of channels from X.

hyperparameters

epochs

int

number of epochs to train the model. An epoch is an iteration over the entire X data provided

input_shape

tuple

tuple denoting the shape of an input sample

optimizer

str

string (name of optimizer) or optimizer instance. Default is keras.optimizers.Adam

learning_rate

float

float denoting the learning rate of the optimizer. Default is 0.001

batch_size

int

number of samples per gradient update. Default is 64

layers_encoder

list

list containing layers of encoder

layers_generator

list

list containing layers of generator

output

ry_hat

numpy.ndarray

n-dimensional array containing the regression for each input sequence (reverse)

y_hat

numpy.ndarray

n-dimensional array containing the reconstructions for each input sequence

fy_hat

numpy.ndarray

n-dimensional array containing the regression for each input sequence (forward)

 
In [1]: import numpy as np

In [2]: from mlstars import load_primitive

In [3]: X = np.ones((64, 100, 1))

In [4]: y = X[:,:, [0]] # signal to reconstruct from X (channel 0)

In [5]: primitive = load_primitive('orion.primitives.aer.AER',
   ...:     arguments={"X": X, "y": y, "epochs": 1, "batch_size": 1})
   ...: 

In [6]: primitive.fit()

 1/51 [..............................] - ETA: 3:25 - loss: 0.8501 - tf.__operators__.getitem_loss: 0.8987 - tf.__operators__.getitem_1_loss: 0.8078 - tf.__operators__.getitem_2_loss: 0.8861
 4/51 [=>............................] - ETA: 1s - loss: 0.5814 - tf.__operators__.getitem_loss: 0.6524 - tf.__operators__.getitem_1_loss: 0.4937 - tf.__operators__.getitem_2_loss: 0.6858  
 7/51 [===>..........................] - ETA: 0s - loss: 0.3997 - tf.__operators__.getitem_loss: 0.4641 - tf.__operators__.getitem_1_loss: 0.3049 - tf.__operators__.getitem_2_loss: 0.5248
10/51 [====>.........................] - ETA: 0s - loss: 0.3018 - tf.__operators__.getitem_loss: 0.3357 - tf.__operators__.getitem_1_loss: 0.2368 - tf.__operators__.getitem_2_loss: 0.3979
13/51 [======>.......................] - ETA: 0s - loss: 0.2604 - tf.__operators__.getitem_loss: 0.2586 - tf.__operators__.getitem_1_loss: 0.2352 - tf.__operators__.getitem_2_loss: 0.3128
16/51 [========>.....................] - ETA: 0s - loss: 0.2310 - tf.__operators__.getitem_loss: 0.2109 - tf.__operators__.getitem_1_loss: 0.2258 - tf.__operators__.getitem_2_loss: 0.2614
19/51 [==========>...................] - ETA: 0s - loss: 0.2049 - tf.__operators__.getitem_loss: 0.1814 - tf.__operators__.getitem_1_loss: 0.2027 - tf.__operators__.getitem_2_loss: 0.2330
22/51 [===========>..................] - ETA: 0s - loss: 0.1849 - tf.__operators__.getitem_loss: 0.1644 - tf.__operators__.getitem_1_loss: 0.1782 - tf.__operators__.getitem_2_loss: 0.2190
25/51 [=============>................] - ETA: 0s - loss: 0.1705 - tf.__operators__.getitem_loss: 0.1549 - tf.__operators__.getitem_1_loss: 0.1577 - tf.__operators__.getitem_2_loss: 0.2118
28/51 [===============>..............] - ETA: 0s - loss: 0.1594 - tf.__operators__.getitem_loss: 0.1485 - tf.__operators__.getitem_1_loss: 0.1414 - tf.__operators__.getitem_2_loss: 0.2062
31/51 [=================>............] - ETA: 0s - loss: 0.1498 - tf.__operators__.getitem_loss: 0.1426 - tf.__operators__.getitem_1_loss: 0.1286 - tf.__operators__.getitem_2_loss: 0.1996
34/51 [===================>..........] - ETA: 0s - loss: 0.1413 - tf.__operators__.getitem_loss: 0.1362 - tf.__operators__.getitem_1_loss: 0.1188 - tf.__operators__.getitem_2_loss: 0.1915
37/51 [====================>.........] - ETA: 0s - loss: 0.1339 - tf.__operators__.getitem_loss: 0.1296 - tf.__operators__.getitem_1_loss: 0.1119 - tf.__operators__.getitem_2_loss: 0.1823
40/51 [======================>.......] - ETA: 0s - loss: 0.1277 - tf.__operators__.getitem_loss: 0.1233 - tf.__operators__.getitem_1_loss: 0.1073 - tf.__operators__.getitem_2_loss: 0.1731
43/51 [========================>.....] - ETA: 0s - loss: 0.1224 - tf.__operators__.getitem_loss: 0.1178 - tf.__operators__.getitem_1_loss: 0.1035 - tf.__operators__.getitem_2_loss: 0.1647
46/51 [==========================>...] - ETA: 0s - loss: 0.1176 - tf.__operators__.getitem_loss: 0.1133 - tf.__operators__.getitem_1_loss: 0.0998 - tf.__operators__.getitem_2_loss: 0.1575
49/51 [===========================>..] - ETA: 0s - loss: 0.1133 - tf.__operators__.getitem_loss: 0.1100 - tf.__operators__.getitem_1_loss: 0.0957 - tf.__operators__.getitem_2_loss: 0.1516
51/51 [==============================] - 6s 42ms/step - loss: 0.1106 - tf.__operators__.getitem_loss: 0.1083 - tf.__operators__.getitem_1_loss: 0.0929 - tf.__operators__.getitem_2_loss: 0.1483 - val_loss: 0.0455 - val_tf.__operators__.getitem_loss: 0.0705 - val_tf.__operators__.getitem_1_loss: 0.0213 - val_tf.__operators__.getitem_2_loss: 0.0691

In [7]: ry, y, fy = primitive.produce(X=X)

1/2 [==============>...............] - ETA: 0s
2/2 [==============================] - 0s 10ms/step

1/2 [==============>...............] - ETA: 0s
2/2 [==============================] - 0s 11ms/step

In [8]: print("Reverse Prediction: {}\nReconstructed Values: {}, Forward Prediction: {}".format(ry, y, fy))
Reverse Prediction: [[0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]
 [0.73445056]]
Reconstructed Values: [[[0.84596941]
  [0.92662006]
  [0.98547457]
  ...
  [0.9669104 ]
  [0.91257842]
  [0.83867568]]

 [[0.84596941]
  [0.92662006]
  [0.98547457]
  ...
  [0.9669104 ]
  [0.91257842]
  [0.83867568]]

 [[0.84596941]
  [0.92662006]
  [0.98547457]
  ...
  [0.9669104 ]
  [0.91257842]
  [0.83867568]]

 ...

 [[0.84596941]
  [0.92662006]
  [0.98547457]
  ...
  [0.9669104 ]
  [0.91257842]
  [0.83867568]]

 [[0.84596941]
  [0.92662006]
  [0.98547457]
  ...
  [0.9669104 ]
  [0.91257842]
  [0.83867568]]

 [[0.84596941]
  [0.92662006]
  [0.98547457]
  ...
  [0.9669104 ]
  [0.91257842]
  [0.83867568]]], Forward Prediction: [[0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]
 [0.73718563]]
TadGAN VAE