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: 3:08 - loss: 1.1714 - tf.__operators__.getitem_loss: 0.9719 - tf.__operators__.getitem_1_loss: 1.1957 - tf.__operators__.getitem_2_loss: 1.3223
 4/51 [=>............................] - ETA: 1s - loss: 0.8341 - tf.__operators__.getitem_loss: 0.7416 - tf.__operators__.getitem_1_loss: 0.7871 - tf.__operators__.getitem_2_loss: 1.0207  
 7/51 [===>..........................] - ETA: 0s - loss: 0.5849 - tf.__operators__.getitem_loss: 0.5448 - tf.__operators__.getitem_1_loss: 0.5070 - tf.__operators__.getitem_2_loss: 0.7810
10/51 [====>.........................] - ETA: 0s - loss: 0.4333 - tf.__operators__.getitem_loss: 0.3946 - tf.__operators__.getitem_1_loss: 0.3724 - tf.__operators__.getitem_2_loss: 0.5936
13/51 [======>.......................] - ETA: 0s - loss: 0.3666 - tf.__operators__.getitem_loss: 0.3037 - tf.__operators__.getitem_1_loss: 0.3491 - tf.__operators__.getitem_2_loss: 0.4646
16/51 [========>.....................] - ETA: 0s - loss: 0.3201 - tf.__operators__.getitem_loss: 0.2473 - tf.__operators__.getitem_1_loss: 0.3249 - tf.__operators__.getitem_2_loss: 0.3833
19/51 [==========>...................] - ETA: 0s - loss: 0.2798 - tf.__operators__.getitem_loss: 0.2139 - tf.__operators__.getitem_1_loss: 0.2862 - tf.__operators__.getitem_2_loss: 0.3329
22/51 [===========>..................] - ETA: 0s - loss: 0.2494 - tf.__operators__.getitem_loss: 0.1973 - tf.__operators__.getitem_1_loss: 0.2494 - tf.__operators__.getitem_2_loss: 0.3016
25/51 [=============>................] - ETA: 0s - loss: 0.2276 - tf.__operators__.getitem_loss: 0.1897 - tf.__operators__.getitem_1_loss: 0.2200 - tf.__operators__.getitem_2_loss: 0.2806
28/51 [===============>..............] - ETA: 0s - loss: 0.2106 - tf.__operators__.getitem_loss: 0.1848 - tf.__operators__.getitem_1_loss: 0.1968 - tf.__operators__.getitem_2_loss: 0.2640
31/51 [=================>............] - ETA: 0s - loss: 0.1962 - tf.__operators__.getitem_loss: 0.1793 - tf.__operators__.getitem_1_loss: 0.1783 - tf.__operators__.getitem_2_loss: 0.2489
34/51 [===================>..........] - ETA: 0s - loss: 0.1836 - tf.__operators__.getitem_loss: 0.1725 - tf.__operators__.getitem_1_loss: 0.1638 - tf.__operators__.getitem_2_loss: 0.2341
37/51 [====================>.........] - ETA: 0s - loss: 0.1727 - tf.__operators__.getitem_loss: 0.1646 - tf.__operators__.getitem_1_loss: 0.1532 - tf.__operators__.getitem_2_loss: 0.2199
40/51 [======================>.......] - ETA: 0s - loss: 0.1636 - tf.__operators__.getitem_loss: 0.1566 - tf.__operators__.getitem_1_loss: 0.1456 - tf.__operators__.getitem_2_loss: 0.2067
43/51 [========================>.....] - ETA: 0s - loss: 0.1558 - tf.__operators__.getitem_loss: 0.1494 - tf.__operators__.getitem_1_loss: 0.1394 - tf.__operators__.getitem_2_loss: 0.1951
46/51 [==========================>...] - ETA: 0s - loss: 0.1489 - tf.__operators__.getitem_loss: 0.1433 - tf.__operators__.getitem_1_loss: 0.1335 - tf.__operators__.getitem_2_loss: 0.1853
49/51 [===========================>..] - ETA: 0s - loss: 0.1427 - tf.__operators__.getitem_loss: 0.1385 - tf.__operators__.getitem_1_loss: 0.1275 - tf.__operators__.getitem_2_loss: 0.1772
51/51 [==============================] - 6s 49ms/step - loss: 0.1389 - tf.__operators__.getitem_loss: 0.1359 - tf.__operators__.getitem_1_loss: 0.1234 - tf.__operators__.getitem_2_loss: 0.1727 - val_loss: 0.0461 - val_tf.__operators__.getitem_loss: 0.0756 - val_tf.__operators__.getitem_1_loss: 0.0211 - val_tf.__operators__.getitem_2_loss: 0.0665

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 12ms/step

In [8]: print("Reverse Prediction: {}\nReconstructed Values: {}, Forward Prediction: {}".format(ry, y, fy))
Reverse Prediction: [[0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]
 [0.72499681]]
Reconstructed Values: [[[0.83495353]
  [0.91743553]
  [0.97877403]
  ...
  [1.00492918]
  [0.94143304]
  [0.8560517 ]]

 [[0.83495353]
  [0.91743553]
  [0.97877403]
  ...
  [1.00492918]
  [0.94143304]
  [0.8560517 ]]

 [[0.83495353]
  [0.91743553]
  [0.97877403]
  ...
  [1.00492918]
  [0.94143304]
  [0.8560517 ]]

 ...

 [[0.83495353]
  [0.91743553]
  [0.97877403]
  ...
  [1.00492918]
  [0.94143304]
  [0.8560517 ]]

 [[0.83495353]
  [0.91743553]
  [0.97877403]
  ...
  [1.00492918]
  [0.94143304]
  [0.8560517 ]]

 [[0.83495353]
  [0.91743553]
  [0.97877403]
  ...
  [1.00492918]
  [0.94143304]
  [0.8560517 ]]], Forward Prediction: [[0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]
 [0.74208537]]
TadGAN VAE