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: 3:20 - loss: 0.7771 - tf.__operators__.getitem_loss: 0.8326 - tf.__operators__.getitem_1_loss: 0.7290 - tf.__operators__.getitem_2_loss: 0.8178
 4/51 [=>............................] - ETA: 1s - loss: 0.5265 - tf.__operators__.getitem_loss: 0.6545 - tf.__operators__.getitem_1_loss: 0.4375 - tf.__operators__.getitem_2_loss: 0.5765  
 7/51 [===>..........................] - ETA: 0s - loss: 0.3532 - tf.__operators__.getitem_loss: 0.4960 - tf.__operators__.getitem_1_loss: 0.2644 - tf.__operators__.getitem_2_loss: 0.3881
10/51 [====>.........................] - ETA: 0s - loss: 0.2780 - tf.__operators__.getitem_loss: 0.3720 - tf.__operators__.getitem_1_loss: 0.2334 - tf.__operators__.getitem_2_loss: 0.2731
13/51 [======>.......................] - ETA: 0s - loss: 0.2451 - tf.__operators__.getitem_loss: 0.2949 - tf.__operators__.getitem_1_loss: 0.2376 - tf.__operators__.getitem_2_loss: 0.2104
16/51 [========>.....................] - ETA: 0s - loss: 0.2138 - tf.__operators__.getitem_loss: 0.2521 - tf.__operators__.getitem_1_loss: 0.2151 - tf.__operators__.getitem_2_loss: 0.1730
19/51 [==========>...................] - ETA: 0s - loss: 0.1889 - tf.__operators__.getitem_loss: 0.2303 - tf.__operators__.getitem_1_loss: 0.1853 - tf.__operators__.getitem_2_loss: 0.1545
22/51 [===========>..................] - ETA: 0s - loss: 0.1720 - tf.__operators__.getitem_loss: 0.2188 - tf.__operators__.getitem_1_loss: 0.1607 - tf.__operators__.getitem_2_loss: 0.1476
25/51 [=============>................] - ETA: 0s - loss: 0.1596 - tf.__operators__.getitem_loss: 0.2102 - tf.__operators__.getitem_1_loss: 0.1419 - tf.__operators__.getitem_2_loss: 0.1443
28/51 [===============>..............] - ETA: 0s - loss: 0.1489 - tf.__operators__.getitem_loss: 0.2007 - tf.__operators__.getitem_1_loss: 0.1272 - tf.__operators__.getitem_2_loss: 0.1406
31/51 [=================>............] - ETA: 0s - loss: 0.1395 - tf.__operators__.getitem_loss: 0.1898 - tf.__operators__.getitem_1_loss: 0.1165 - tf.__operators__.getitem_2_loss: 0.1350
34/51 [===================>..........] - ETA: 0s - loss: 0.1315 - tf.__operators__.getitem_loss: 0.1782 - tf.__operators__.getitem_1_loss: 0.1096 - tf.__operators__.getitem_2_loss: 0.1284
37/51 [====================>.........] - ETA: 0s - loss: 0.1249 - tf.__operators__.getitem_loss: 0.1673 - tf.__operators__.getitem_1_loss: 0.1053 - tf.__operators__.getitem_2_loss: 0.1218
40/51 [======================>.......] - ETA: 0s - loss: 0.1194 - tf.__operators__.getitem_loss: 0.1579 - tf.__operators__.getitem_1_loss: 0.1017 - tf.__operators__.getitem_2_loss: 0.1162
43/51 [========================>.....] - ETA: 0s - loss: 0.1143 - tf.__operators__.getitem_loss: 0.1503 - tf.__operators__.getitem_1_loss: 0.0976 - tf.__operators__.getitem_2_loss: 0.1119
46/51 [==========================>...] - ETA: 0s - loss: 0.1098 - tf.__operators__.getitem_loss: 0.1445 - tf.__operators__.getitem_1_loss: 0.0930 - tf.__operators__.getitem_2_loss: 0.1089
49/51 [===========================>..] - ETA: 0s - loss: 0.1059 - tf.__operators__.getitem_loss: 0.1399 - tf.__operators__.getitem_1_loss: 0.0884 - tf.__operators__.getitem_2_loss: 0.1067
51/51 [==============================] - 6s 43ms/step - loss: 0.1035 - tf.__operators__.getitem_loss: 0.1372 - tf.__operators__.getitem_1_loss: 0.0856 - tf.__operators__.getitem_2_loss: 0.1055 - val_loss: 0.0445 - val_tf.__operators__.getitem_loss: 0.0713 - val_tf.__operators__.getitem_1_loss: 0.0163 - val_tf.__operators__.getitem_2_loss: 0.0741

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: [[0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]
 [0.73301312]]
Reconstructed Values: [[[0.85093788]
  [0.93476129]
  [0.99410671]
  ...
  [0.9771176 ]
  [0.91771306]
  [0.83665791]]

 [[0.85093788]
  [0.93476129]
  [0.99410671]
  ...
  [0.9771176 ]
  [0.91771306]
  [0.83665791]]

 [[0.85093788]
  [0.93476129]
  [0.99410671]
  ...
  [0.9771176 ]
  [0.91771306]
  [0.83665791]]

 ...

 [[0.85093788]
  [0.93476129]
  [0.99410671]
  ...
  [0.9771176 ]
  [0.91771306]
  [0.83665791]]

 [[0.85093788]
  [0.93476129]
  [0.99410671]
  ...
  [0.9771176 ]
  [0.91771306]
  [0.83665791]]

 [[0.85093788]
  [0.93476129]
  [0.99410671]
  ...
  [0.9771176 ]
  [0.91771306]
  [0.83665791]]], Forward Prediction: [[0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]
 [0.72778667]]
TadGAN VAE