cellflow.networks.ConditionEncoder.__call__

ConditionEncoder.__call__(conditions, training=True)[source]

Apply the set encoder.

Parameters:
  • conditions (dict[str, jnp.ndarray]) – Dictionary of batch of conditions of shape (batch_size, set_size, condition_dim).

  • training (bool) – Whether the model is in training mode.

Return type:

tuple[Array, Array]

Returns:

: Mean and log-variance of conditions of shape (batch_size, output_dim).