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: 3:10 - loss: 0.9381 - tf.__operators__.getitem_loss: 0.7652 - tf.__operators__.getitem_1_loss: 0.9073 - tf.__operators__.getitem_2_loss: 1.1725
 4/51 [=>............................] - ETA: 1s - loss: 0.6283 - tf.__operators__.getitem_loss: 0.5270 - tf.__operators__.getitem_1_loss: 0.5386 - tf.__operators__.getitem_2_loss: 0.9090  
 7/51 [===>..........................] - ETA: 1s - loss: 0.4229 - tf.__operators__.getitem_loss: 0.3458 - tf.__operators__.getitem_1_loss: 0.3257 - tf.__operators__.getitem_2_loss: 0.6945
10/51 [====>.........................] - ETA: 0s - loss: 0.3320 - tf.__operators__.getitem_loss: 0.2432 - tf.__operators__.getitem_1_loss: 0.2762 - tf.__operators__.getitem_2_loss: 0.5325
13/51 [======>.......................] - ETA: 0s - loss: 0.2911 - tf.__operators__.getitem_loss: 0.1882 - tf.__operators__.getitem_1_loss: 0.2743 - tf.__operators__.getitem_2_loss: 0.4275
16/51 [========>.....................] - ETA: 0s - loss: 0.2551 - tf.__operators__.getitem_loss: 0.1539 - tf.__operators__.getitem_1_loss: 0.2510 - tf.__operators__.getitem_2_loss: 0.3645
19/51 [==========>...................] - ETA: 0s - loss: 0.2253 - tf.__operators__.getitem_loss: 0.1365 - tf.__operators__.getitem_1_loss: 0.2185 - tf.__operators__.getitem_2_loss: 0.3278
22/51 [===========>..................] - ETA: 0s - loss: 0.2042 - tf.__operators__.getitem_loss: 0.1311 - tf.__operators__.getitem_1_loss: 0.1902 - tf.__operators__.getitem_2_loss: 0.3055
25/51 [=============>................] - ETA: 0s - loss: 0.1889 - tf.__operators__.getitem_loss: 0.1306 - tf.__operators__.getitem_1_loss: 0.1681 - tf.__operators__.getitem_2_loss: 0.2888
28/51 [===============>..............] - ETA: 0s - loss: 0.1762 - tf.__operators__.getitem_loss: 0.1302 - tf.__operators__.getitem_1_loss: 0.1509 - tf.__operators__.getitem_2_loss: 0.2730
31/51 [=================>............] - ETA: 0s - loss: 0.1651 - tf.__operators__.getitem_loss: 0.1279 - tf.__operators__.getitem_1_loss: 0.1379 - tf.__operators__.getitem_2_loss: 0.2566
34/51 [===================>..........] - ETA: 0s - loss: 0.1556 - tf.__operators__.getitem_loss: 0.1240 - tf.__operators__.getitem_1_loss: 0.1291 - tf.__operators__.getitem_2_loss: 0.2402
37/51 [====================>.........] - ETA: 0s - loss: 0.1478 - tf.__operators__.getitem_loss: 0.1195 - tf.__operators__.getitem_1_loss: 0.1233 - tf.__operators__.getitem_2_loss: 0.2248
40/51 [======================>.......] - ETA: 0s - loss: 0.1411 - tf.__operators__.getitem_loss: 0.1153 - tf.__operators__.getitem_1_loss: 0.1188 - tf.__operators__.getitem_2_loss: 0.2114
43/51 [========================>.....] - ETA: 0s - loss: 0.1352 - tf.__operators__.getitem_loss: 0.1120 - tf.__operators__.getitem_1_loss: 0.1141 - tf.__operators__.getitem_2_loss: 0.2004
46/51 [==========================>...] - ETA: 0s - loss: 0.1299 - tf.__operators__.getitem_loss: 0.1097 - tf.__operators__.getitem_1_loss: 0.1090 - tf.__operators__.getitem_2_loss: 0.1916
49/51 [===========================>..] - ETA: 0s - loss: 0.1251 - tf.__operators__.getitem_loss: 0.1082 - tf.__operators__.getitem_1_loss: 0.1039 - tf.__operators__.getitem_2_loss: 0.1846
51/51 [==============================] - 6s 51ms/step - loss: 0.1223 - tf.__operators__.getitem_loss: 0.1073 - tf.__operators__.getitem_1_loss: 0.1006 - tf.__operators__.getitem_2_loss: 0.1807 - val_loss: 0.0521 - val_tf.__operators__.getitem_loss: 0.0842 - val_tf.__operators__.getitem_1_loss: 0.0198 - val_tf.__operators__.getitem_2_loss: 0.0847

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

1/2 [==============>...............] - ETA: 0s
2/2 [==============================] - 0s 9ms/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: [[0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]
 [0.70987779]]
Reconstructed Values: [[[0.80058991]
  [0.87140675]
  [0.9268512 ]
  ...
  [0.95519217]
  [0.89325505]
  [0.81269645]]

 [[0.80058991]
  [0.87140675]
  [0.9268512 ]
  ...
  [0.95519217]
  [0.89325505]
  [0.81269645]]

 [[0.80058991]
  [0.87140675]
  [0.9268512 ]
  ...
  [0.95519217]
  [0.89325505]
  [0.81269645]]

 ...

 [[0.80058991]
  [0.87140675]
  [0.9268512 ]
  ...
  [0.95519217]
  [0.89325505]
  [0.81269645]]

 [[0.80058991]
  [0.87140675]
  [0.9268512 ]
  ...
  [0.95519217]
  [0.89325505]
  [0.81269645]]

 [[0.80058991]
  [0.87140675]
  [0.9268512 ]
  ...
  [0.95519217]
  [0.89325505]
  [0.81269645]]], Forward Prediction: [[0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]
 [0.70891031]]
TadGAN VAE