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: 3:19 - loss: 0.8546 - tf.__operators__.getitem_loss: 0.9104 - tf.__operators__.getitem_1_loss: 0.8131 - tf.__operators__.getitem_2_loss: 0.8817
 4/51 [=>............................] - ETA: 0s - loss: 0.6269 - tf.__operators__.getitem_loss: 0.7159 - tf.__operators__.getitem_1_loss: 0.5464 - tf.__operators__.getitem_2_loss: 0.6989  
 7/51 [===>..........................] - ETA: 0s - loss: 0.4527 - tf.__operators__.getitem_loss: 0.5511 - tf.__operators__.getitem_1_loss: 0.3584 - tf.__operators__.getitem_2_loss: 0.5431
10/51 [====>.........................] - ETA: 0s - loss: 0.3376 - tf.__operators__.getitem_loss: 0.4167 - tf.__operators__.getitem_1_loss: 0.2595 - tf.__operators__.getitem_2_loss: 0.4145
13/51 [======>.......................] - ETA: 0s - loss: 0.2838 - tf.__operators__.getitem_loss: 0.3232 - tf.__operators__.getitem_1_loss: 0.2445 - tf.__operators__.getitem_2_loss: 0.3230
16/51 [========>.....................] - ETA: 0s - loss: 0.2511 - tf.__operators__.getitem_loss: 0.2642 - tf.__operators__.getitem_1_loss: 0.2378 - tf.__operators__.getitem_2_loss: 0.2647
19/51 [==========>...................] - ETA: 0s - loss: 0.2219 - tf.__operators__.getitem_loss: 0.2278 - tf.__operators__.getitem_1_loss: 0.2154 - tf.__operators__.getitem_2_loss: 0.2289
22/51 [===========>..................] - ETA: 0s - loss: 0.1987 - tf.__operators__.getitem_loss: 0.2073 - tf.__operators__.getitem_1_loss: 0.1895 - tf.__operators__.getitem_2_loss: 0.2084
25/51 [=============>................] - ETA: 0s - loss: 0.1819 - tf.__operators__.getitem_loss: 0.1959 - tf.__operators__.getitem_1_loss: 0.1675 - tf.__operators__.getitem_2_loss: 0.1966
28/51 [===============>..............] - ETA: 0s - loss: 0.1690 - tf.__operators__.getitem_loss: 0.1880 - tf.__operators__.getitem_1_loss: 0.1499 - tf.__operators__.getitem_2_loss: 0.1883
31/51 [=================>............] - ETA: 0s - loss: 0.1582 - tf.__operators__.getitem_loss: 0.1803 - tf.__operators__.getitem_1_loss: 0.1360 - tf.__operators__.getitem_2_loss: 0.1805
34/51 [===================>..........] - ETA: 0s - loss: 0.1485 - tf.__operators__.getitem_loss: 0.1719 - tf.__operators__.getitem_1_loss: 0.1252 - tf.__operators__.getitem_2_loss: 0.1720
37/51 [====================>.........] - ETA: 0s - loss: 0.1402 - tf.__operators__.getitem_loss: 0.1629 - tf.__operators__.getitem_1_loss: 0.1174 - tf.__operators__.getitem_2_loss: 0.1631
40/51 [======================>.......] - ETA: 0s - loss: 0.1332 - tf.__operators__.getitem_loss: 0.1542 - tf.__operators__.getitem_1_loss: 0.1120 - tf.__operators__.getitem_2_loss: 0.1545
43/51 [========================>.....] - ETA: 0s - loss: 0.1272 - tf.__operators__.getitem_loss: 0.1463 - tf.__operators__.getitem_1_loss: 0.1078 - tf.__operators__.getitem_2_loss: 0.1468
46/51 [==========================>...] - ETA: 0s - loss: 0.1218 - tf.__operators__.getitem_loss: 0.1397 - tf.__operators__.getitem_1_loss: 0.1037 - tf.__operators__.getitem_2_loss: 0.1402
49/51 [===========================>..] - ETA: 0s - loss: 0.1169 - tf.__operators__.getitem_loss: 0.1343 - tf.__operators__.getitem_1_loss: 0.0993 - tf.__operators__.getitem_2_loss: 0.1349
51/51 [==============================] - 6s 41ms/step - loss: 0.1140 - tf.__operators__.getitem_loss: 0.1313 - tf.__operators__.getitem_1_loss: 0.0963 - tf.__operators__.getitem_2_loss: 0.1319 - val_loss: 0.0411 - val_tf.__operators__.getitem_loss: 0.0616 - val_tf.__operators__.getitem_1_loss: 0.0200 - val_tf.__operators__.getitem_2_loss: 0.0630

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: [[0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]
 [0.75185597]]
Reconstructed Values: [[[0.85202879]
  [0.92947942]
  [0.98824289]
  ...
  [1.03146749]
  [0.9733126 ]
  [0.88472319]]

 [[0.85202879]
  [0.92947942]
  [0.98824289]
  ...
  [1.03146749]
  [0.9733126 ]
  [0.88472319]]

 [[0.85202879]
  [0.92947942]
  [0.98824289]
  ...
  [1.03146749]
  [0.9733126 ]
  [0.88472319]]

 ...

 [[0.85202879]
  [0.92947942]
  [0.98824289]
  ...
  [1.03146749]
  [0.9733126 ]
  [0.88472319]]

 [[0.85202879]
  [0.92947942]
  [0.98824289]
  ...
  [1.03146749]
  [0.9733126 ]
  [0.88472319]]

 [[0.85202879]
  [0.92947942]
  [0.98824289]
  ...
  [1.03146749]
  [0.9733126 ]
  [0.88472319]]], Forward Prediction: [[0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]
 [0.74904007]]
TadGAN VAE