SYMBOL INDEX (49 symbols across 6 files)

FILE: dataset.py
  function rand_dataset (line 6) | def rand_dataset(num_rows=60_000, num_columns=100) -> Dataset:
  function mnist_dataset (line 10) | def mnist_dataset(train=True) -> Dataset:

FILE: model/VAE.py
  class VAEAnomalyDetection (line 10) | class VAEAnomalyDetection(pl.LightningModule, ABC):
    method __init__ (line 22) | def __init__(self, input_size: int, latent_size: int, L: int = 10, lr:...
    method make_encoder (line 44) | def make_encoder(self, input_size: int, latent_size: int) -> nn.Module:
    method make_decoder (line 58) | def make_decoder(self, latent_size: int, output_size: int) -> nn.Module:
    method forward (line 71) | def forward(self, x: torch.Tensor) -> dict:
    method predict (line 100) | def predict(self, x) -> dict:
    method is_anomaly (line 131) | def is_anomaly(self, x: torch.Tensor, alpha: float = 0.05) -> torch.Te...
    method reconstructed_probability (line 146) | def reconstructed_probability(self, x: torch.Tensor) -> torch.Tensor:
    method generate (line 165) | def generate(self, batch_size: int = 1) -> torch.Tensor:
    method training_step (line 182) | def training_step(self, batch, batch_idx):
    method validation_step (line 194) | def validation_step(self, batch, batch_idx):
    method configure_optimizers (line 203) | def configure_optimizers(self):
    method _log_norm (line 207) | def _log_norm(self):
  class VAEAnomalyTabular (line 213) | class VAEAnomalyTabular(VAEAnomalyDetection):
    method make_encoder (line 215) | def make_encoder(self, input_size, latent_size):
    method make_decoder (line 232) | def make_decoder(self, latent_size, output_size):

FILE: model/VAE_tf1.py
  function tf_namespace (line 11) | def tf_namespace(namespace):
  class VAE (line 22) | class VAE:
    method __init__ (line 24) | def __init__(self, input_shape, encode_sizes, latent_size, decode_size...
    method _build_graph (line 37) | def _build_graph(self, input_shape, latent_size):
    method k_init (line 53) | def k_init(self):
    method elbo (line 56) | def elbo(self, X_true, X_pred, mu, log_sigma, sigma, mu_prior, sigma_p...
    method _create_placeholders (line 67) | def _create_placeholders(self, input_shape):
    method _create_encoder (line 71) | def _create_encoder(self, X):
    method _create_latent_distribution (line 81) | def _create_latent_distribution(self, encoder, latent_dim):
    method _create_decoder (line 89) | def _create_decoder(self, z):
    method layers (line 109) | def layers(self):
    method fit (line 114) | def fit(self, X, epochs, batch_size, print_every=50, save_every_epochs...
    method generate (line 139) | def generate(self, n=1, mu_prior=None, sigma_prior=None):
    method reconstruct (line 154) | def reconstruct(self, X):
    method reconstructed_probability (line 157) | def reconstructed_probability(self, X, L=100):
    method is_outlier (line 169) | def is_outlier(self, X, L=100, alpha=0.05):
    method open (line 173) | def open(self):
    method close (line 180) | def close(self):
    method __exit__ (line 185) | def __exit__(self, exc_type, exc_val, exc_tb):
    method __delete__ (line 188) | def __delete__(self, instance):
    method __setattr__ (line 191) | def __setattr__(self, key, value):
    method __delattr__ (line 199) | def __delattr__(self, item):
    method __enter__ (line 206) | def __enter__(self):

FILE: model/encoder_decoder.py
  function tabular_encoder (line 9) | def tabular_encoder(input_size: int, latent_size: int):
  function tabular_decoder (line 35) | def tabular_decoder(latent_size: int, output_size: int):

FILE: tests/test_pytorch_model.py
  function test_pytorch_anomaly_detection (line 5) | def test_pytorch_anomaly_detection():
  function test_pytorch_prediction (line 16) | def test_pytorch_prediction():
  function test_training_step (line 29) | def test_training_step():

FILE: train.py
  function make_folder_run (line 18) | def make_folder_run() -> Path:
  function get_args (line 31) | def get_args() -> argparse.Namespace:
  function main (line 55) | def main():