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: 3:06 - loss: 0.9387 - tf.__operators__.getitem_loss: 1.0812 - tf.__operators__.getitem_1_loss: 0.9278 - tf.__operators__.getitem_2_loss: 0.8181
 4/51 [=>............................] - ETA: 1s - loss: 0.6234 - tf.__operators__.getitem_loss: 0.8419 - tf.__operators__.getitem_1_loss: 0.5516 - tf.__operators__.getitem_2_loss: 0.5486  
 7/51 [===>..........................] - ETA: 0s - loss: 0.4156 - tf.__operators__.getitem_loss: 0.6432 - tf.__operators__.getitem_1_loss: 0.3328 - tf.__operators__.getitem_2_loss: 0.3537
10/51 [====>.........................] - ETA: 0s - loss: 0.3250 - tf.__operators__.getitem_loss: 0.4905 - tf.__operators__.getitem_1_loss: 0.2797 - tf.__operators__.getitem_2_loss: 0.2501
13/51 [======>.......................] - ETA: 0s - loss: 0.2843 - tf.__operators__.getitem_loss: 0.3926 - tf.__operators__.getitem_1_loss: 0.2741 - tf.__operators__.getitem_2_loss: 0.1963
16/51 [========>.....................] - ETA: 0s - loss: 0.2472 - tf.__operators__.getitem_loss: 0.3354 - tf.__operators__.getitem_1_loss: 0.2468 - tf.__operators__.getitem_2_loss: 0.1599
19/51 [==========>...................] - ETA: 0s - loss: 0.2170 - tf.__operators__.getitem_loss: 0.3034 - tf.__operators__.getitem_1_loss: 0.2125 - tf.__operators__.getitem_2_loss: 0.1395
22/51 [===========>..................] - ETA: 0s - loss: 0.1959 - tf.__operators__.getitem_loss: 0.2842 - tf.__operators__.getitem_1_loss: 0.1842 - tf.__operators__.getitem_2_loss: 0.1311
25/51 [=============>................] - ETA: 0s - loss: 0.1804 - tf.__operators__.getitem_loss: 0.2693 - tf.__operators__.getitem_1_loss: 0.1624 - tf.__operators__.getitem_2_loss: 0.1276
28/51 [===============>..............] - ETA: 0s - loss: 0.1674 - tf.__operators__.getitem_loss: 0.2543 - tf.__operators__.getitem_1_loss: 0.1455 - tf.__operators__.getitem_2_loss: 0.1242
31/51 [=================>............] - ETA: 0s - loss: 0.1558 - tf.__operators__.getitem_loss: 0.2383 - tf.__operators__.getitem_1_loss: 0.1328 - tf.__operators__.getitem_2_loss: 0.1193
34/51 [===================>..........] - ETA: 0s - loss: 0.1461 - tf.__operators__.getitem_loss: 0.2222 - tf.__operators__.getitem_1_loss: 0.1243 - tf.__operators__.getitem_2_loss: 0.1134
37/51 [====================>.........] - ETA: 0s - loss: 0.1381 - tf.__operators__.getitem_loss: 0.2073 - tf.__operators__.getitem_1_loss: 0.1188 - tf.__operators__.getitem_2_loss: 0.1075
40/51 [======================>.......] - ETA: 0s - loss: 0.1313 - tf.__operators__.getitem_loss: 0.1944 - tf.__operators__.getitem_1_loss: 0.1140 - tf.__operators__.getitem_2_loss: 0.1025
43/51 [========================>.....] - ETA: 0s - loss: 0.1251 - tf.__operators__.getitem_loss: 0.1839 - tf.__operators__.getitem_1_loss: 0.1089 - tf.__operators__.getitem_2_loss: 0.0989
46/51 [==========================>...] - ETA: 0s - loss: 0.1197 - tf.__operators__.getitem_loss: 0.1755 - tf.__operators__.getitem_1_loss: 0.1033 - tf.__operators__.getitem_2_loss: 0.0965
49/51 [===========================>..] - ETA: 0s - loss: 0.1149 - tf.__operators__.getitem_loss: 0.1687 - tf.__operators__.getitem_1_loss: 0.0979 - tf.__operators__.getitem_2_loss: 0.0949
51/51 [==============================] - 6s 49ms/step - loss: 0.1120 - tf.__operators__.getitem_loss: 0.1646 - tf.__operators__.getitem_1_loss: 0.0946 - tf.__operators__.getitem_2_loss: 0.0940 - val_loss: 0.0402 - val_tf.__operators__.getitem_loss: 0.0636 - val_tf.__operators__.getitem_1_loss: 0.0139 - val_tf.__operators__.getitem_2_loss: 0.0693

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: [[0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]
 [0.74781653]]
Reconstructed Values: [[[0.87945034]
  [0.96653411]
  [1.02361853]
  ...
  [0.9798506 ]
  [0.923733  ]
  [0.84530444]]

 [[0.87945034]
  [0.96653411]
  [1.02361853]
  ...
  [0.9798506 ]
  [0.923733  ]
  [0.84530444]]

 [[0.87945034]
  [0.96653411]
  [1.02361853]
  ...
  [0.9798506 ]
  [0.923733  ]
  [0.84530444]]

 ...

 [[0.87945034]
  [0.96653411]
  [1.02361853]
  ...
  [0.9798506 ]
  [0.923733  ]
  [0.84530444]]

 [[0.87945034]
  [0.96653411]
  [1.02361853]
  ...
  [0.9798506 ]
  [0.923733  ]
  [0.84530444]]

 [[0.87945034]
  [0.96653411]
  [1.02361853]
  ...
  [0.9798506 ]
  [0.923733  ]
  [0.84530444]]], Forward Prediction: [[0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]
 [0.7366958]]
TadGAN VAE