def load_tf_aegmm(filepath: str, state_dict: Dict) -> tf.keras.Model:
"""
Load AEGMM.
Parameters
----------
filepath
Save directory.
state_dict
Dictionary containing the `n_gmm` and `recon_features` parameters.
Returns
-------
Loaded AEGMM.
"""
model_dir = os.path.join(filepath, 'model')
if not [f for f in os.listdir(model_dir) if not f.startswith('.')]:
logger.warning(
'No encoder, decoder, gmm density net or aegmm found in {}.'.
format(model_dir))
return None
encoder_net = tf.keras.models.load_model(
os.path.join(model_dir, 'encoder_net.h5'))
decoder_net = tf.keras.models.load_model(
os.path.join(model_dir, 'decoder_net.h5'))
gmm_density_net = tf.keras.models.load_model(
os.path.join(model_dir, 'gmm_density_net.h5'))
aegmm = AEGMM(encoder_net, decoder_net, gmm_density_net,
state_dict['n_gmm'], state_dict['recon_features'])
aegmm.load_weights(os.path.join(model_dir, 'aegmm.ckpt'))
return aegmm
def __init__(self,
threshold: float = None,
aegmm: tf.keras.Model = None,
encoder_net: tf.keras.Sequential = None,
decoder_net: tf.keras.Sequential = None,
gmm_density_net: tf.keras.Sequential = None,
n_gmm: int = None,
recon_features: Callable = eucl_cosim_features,
data_type: str = None) -> None:
"""
AEGMM-based outlier detector.
Parameters
----------
threshold
Threshold used for outlier score to determine outliers.
aegmm
A trained tf.keras model if available.
encoder_net
Layers for the encoder wrapped in a tf.keras.Sequential class if no 'aegmm' is specified.
decoder_net
Layers for the decoder wrapped in a tf.keras.Sequential class if no 'aegmm' is specified.
gmm_density_net
Layers for the GMM network wrapped in a tf.keras.Sequential class.
n_gmm
Number of components in GMM.
recon_features
Function to extract features from the reconstructed instance by the decoder.
data_type
Optionally specifiy the data type (tabular, image or time-series). Added to metadata.
"""
super().__init__()
if threshold is None:
logger.warning(
'No threshold level set. Need to infer threshold using `infer_threshold`.'
)
self.threshold = threshold
# check if model can be loaded, otherwise initialize AEGMM model
if isinstance(aegmm, tf.keras.Model):
self.aegmm = aegmm
elif (isinstance(encoder_net, tf.keras.Sequential)
and isinstance(decoder_net, tf.keras.Sequential)
and isinstance(gmm_density_net, tf.keras.Sequential)):
self.aegmm = AEGMM(encoder_net, decoder_net, gmm_density_net,
n_gmm, recon_features)
else:
raise TypeError(
'No valid format detected for `aegmm` (tf.keras.Model) '
'or `encoder_net`, `decoder_net` and `gmm_density_net` (tf.keras.Sequential).'
)
# set metadata
self.meta['detector_type'] = 'offline'
self.meta['data_type'] = data_type
self.phi, self.mu, self.cov, self.L, self.log_det_cov = None, None, None, None, None
assert np.sum((X - X_recon_untrained)**2) > np.sum((X - X_recon)**2)
@pytest.mark.parametrize('tf_v_ae_mnist', tests, indirect=True)
def test_ae_vae(tf_v_ae_mnist):
pass
n_gmm = 1
gmm_density_net = tf.keras.Sequential([
InputLayer(input_shape=(latent_dim + 2, )),
Dense(10, activation=tf.nn.relu),
Dense(n_gmm, activation=tf.nn.softmax)
])
aegmm = AEGMM(encoder_net, decoder_net, gmm_density_net, n_gmm)
vaegmm = VAEGMM(encoder_net, decoder_net, gmm_density_net, n_gmm, latent_dim)
tests = [(aegmm, loss_aegmm), (vaegmm, loss_vaegmm)]
n_tests = len(tests)
@pytest.fixture
def tf_v_aegmm_mnist(request):
# load and preprocess MNIST data
(X_train, _), (X_test, _) = tf.keras.datasets.mnist.load_data()
X = X_train.reshape(60000,
input_dim)[:1000] # only train on 1000 instances
X = X.astype(np.float32)
X /= 255
# init model, predict with untrained model, train and predict with trained model