Python tensorflow.keras.activations.get() Examples

def get(identifier: OptStrOrCallable = None) -> Callable[..., Any]:
    """
    Get activations by identifier

    Args:
        identifier (str or callable): the identifier of activations

    Returns:
        callable activation

    """
    try:
        return keras_get(identifier)
    except ValueError:
        if isinstance(identifier, str):
            return deserialize(identifier, custom_objects=globals())
        else:
            raise ValueError('Could not interpret:',  identifier) 

def __init__(self,
               exp_base: int,
               num_nodes: int,
               use_bias: Optional[bool] = True,
               activation: Optional[Text] = None,
               kernel_initializer: Optional[Text] = 'glorot_uniform',
               bias_initializer: Optional[Text] = 'zeros',
               **kwargs) -> None:

    if 'input_shape' not in kwargs and 'input_dim' in kwargs:
      kwargs['input_shape'] = (kwargs.pop('input_dim'),)

    super(DenseCondenser, self).__init__(**kwargs)

    self.exp_base = exp_base
    self.num_nodes = num_nodes
    self.nodes = []
    self.use_bias = use_bias
    self.activation = activations.get(activation)
    self.kernel_initializer = initializers.get(kernel_initializer)
    self.bias_initializer = initializers.get(bias_initializer) 

def __init__(self,
                 k,
                 channels=None,
                 return_mask=False,
                 activation=None,
                 kernel_initializer='glorot_uniform',
                 kernel_regularizer=None,
                 kernel_constraint=None,
                 **kwargs):

        super().__init__(**kwargs)
        self.k = k
        self.channels = channels
        self.return_mask = return_mask
        self.activation = activations.get(activation)
        self.kernel_initializer = initializers.get(kernel_initializer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.kernel_constraint = constraints.get(kernel_constraint) 

def __init__(self,
               output_dim: int,
               decomp_size: int,
               use_bias: Optional[bool] = True,
               activation: Optional[Text] = None,
               kernel_initializer: Optional[Text] = 'glorot_uniform',
               bias_initializer: Optional[Text] = 'zeros',
               **kwargs) -> None:

    # Allow specification of input_dim instead of input_shape,
    # for compatability with Keras layers that support this
    if 'input_shape' not in kwargs and 'input_dim' in kwargs:
      kwargs['input_shape'] = (kwargs.pop('input_dim'),)

    super(DenseDecomp, self).__init__(**kwargs)

    self.output_dim = output_dim
    self.decomp_size = decomp_size

    self.use_bias = use_bias
    self.activation = activations.get(activation)
    self.kernel_initializer = initializers.get(kernel_initializer)
    self.bias_initializer = initializers.get(bias_initializer) 

def convert_sequence_vocab(self, sequence, sequence_lengths):
        PFAM_TO_UNIREP_ENCODED = {encoding: UNIREP_VOCAB.get(aa, 23) for aa, encoding in PFAM_VOCAB.items()}

        def to_uniprot_unirep(seq, seqlens):
            new_seq = np.zeros_like(seq)

            for pfam_encoding, unirep_encoding in PFAM_TO_UNIREP_ENCODED.items():
                new_seq[seq == pfam_encoding] = unirep_encoding

            # add start/stop
            new_seq = np.pad(new_seq, [[0, 0], [1, 1]], mode='constant')
            new_seq[:, 0] = UNIREP_VOCAB['<START>']
            new_seq[np.arange(new_seq.shape[0]), seqlens + 1] = UNIREP_VOCAB['<STOP>']

            return new_seq

        new_sequence = tf.py_func(to_uniprot_unirep, [sequence, sequence_lengths], sequence.dtype)
        new_sequence.set_shape([sequence.shape[0], sequence.shape[1] + 2])

        return new_sequence 

def build(self, input_shape):
    self.W_list = []
    self.b_list = []
    init = initializers.get(self.init)
    prev_layer_size = self.n_embedding
    for i, layer_size in enumerate(self.layer_sizes):
      self.W_list.append(init([prev_layer_size, layer_size]))
      self.b_list.append(backend.zeros(shape=[
          layer_size,
      ]))
      prev_layer_size = layer_size
    self.W_list.append(init([prev_layer_size, self.n_outputs]))
    self.b_list.append(backend.zeros(shape=[
        self.n_outputs,
    ]))
    self.built = True 

def build(self, input_shape):
    self.W_list = []
    self.b_list = []
    self.dropouts = []
    init = initializers.get(self.init)
    prev_layer_size = self.n_graph_feat
    for layer_size in self.layer_sizes:
      self.W_list.append(init([prev_layer_size, layer_size]))
      self.b_list.append(backend.zeros(shape=[
          layer_size,
      ]))
      if self.dropout is not None and self.dropout > 0.0:
        self.dropouts.append(Dropout(rate=self.dropout))
      else:
        self.dropouts.append(None)
      prev_layer_size = layer_size
    self.W_list.append(init([prev_layer_size, self.n_outputs]))
    self.b_list.append(backend.zeros(shape=[
        self.n_outputs,
    ]))
    if self.dropout is not None and self.dropout > 0.0:
      self.dropouts.append(Dropout(rate=self.dropout))
    else:
      self.dropouts.append(None)
    self.built = True 

def __init__(self,
                 channels,
                 epsilon=None,
                 mlp_hidden=None,
                 mlp_activation='relu',
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):
        super().__init__(aggregate='sum',
                         activation=activation,
                         use_bias=use_bias,
                         kernel_initializer=kernel_initializer,
                         bias_initializer=bias_initializer,
                         kernel_regularizer=kernel_regularizer,
                         bias_regularizer=bias_regularizer,
                         activity_regularizer=activity_regularizer,
                         kernel_constraint=kernel_constraint,
                         bias_constraint=bias_constraint,
                         **kwargs)
        self.channels = self.output_dim = channels
        self.epsilon = epsilon
        self.mlp_hidden = mlp_hidden if mlp_hidden else []
        self.mlp_activation = activations.get(mlp_activation) 

def __init__(self,
                 input_dim_1=None,
                 activation=None,
                 **kwargs):

        super(MinkowskiProduct, self).__init__(**kwargs)
        self.input_dim_1 = input_dim_1
        self.activation = activations.get(activation) 

def __init__(self,
                 k,
                 mlp_hidden=None,
                 mlp_activation='relu',
                 return_mask=False,
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):

        super().__init__(**kwargs)
        self.k = k
        self.mlp_hidden = mlp_hidden if mlp_hidden else []
        self.mlp_activation = mlp_activation
        self.return_mask = return_mask
        self.activation = activations.get(activation)
        self.use_bias = use_bias
        self.kernel_initializer = initializers.get(kernel_initializer)
        self.bias_initializer = initializers.get(bias_initializer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.bias_regularizer = regularizers.get(bias_regularizer)
        self.kernel_constraint = constraints.get(kernel_constraint)
        self.bias_constraint = constraints.get(bias_constraint) 

def __init__(self,
                 channels,
                 mlp_hidden=None,
                 mlp_activation='relu',
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):
        super().__init__(aggregate='sum',
                         activation=activation,
                         use_bias=use_bias,
                         kernel_initializer=kernel_initializer,
                         bias_initializer=bias_initializer,
                         kernel_regularizer=kernel_regularizer,
                         bias_regularizer=bias_regularizer,
                         activity_regularizer=activity_regularizer,
                         kernel_constraint=kernel_constraint,
                         bias_constraint=bias_constraint,
                         **kwargs)
        self.channels = self.output_dim = channels
        self.mlp_hidden = mlp_hidden if mlp_hidden else []
        self.mlp_activation = activations.get(mlp_activation) 

def __init__(self,
                 channels,
                 order=1,
                 iterations=1,
                 share_weights=False,
                 gcn_activation='relu',
                 dropout_rate=0.0,
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):
        super().__init__(channels,
                         activation=activation,
                         use_bias=use_bias,
                         kernel_initializer=kernel_initializer,
                         bias_initializer=bias_initializer,
                         kernel_regularizer=kernel_regularizer,
                         bias_regularizer=bias_regularizer,
                         activity_regularizer=activity_regularizer,
                         kernel_constraint=kernel_constraint,
                         bias_constraint=bias_constraint,
                         **kwargs)
        self.iterations = iterations
        self.order = order
        self.share_weights = share_weights
        self.gcn_activation = activations.get(gcn_activation)
        self.dropout_rate = dropout_rate 

def __init__(self,
                 channels,
                 alpha=0.2,
                 propagations=1,
                 mlp_hidden=None,
                 mlp_activation='relu',
                 dropout_rate=0.0,
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):
        super().__init__(channels,
                         activation=activation,
                         use_bias=use_bias,
                         kernel_initializer=kernel_initializer,
                         bias_initializer=bias_initializer,
                         kernel_regularizer=kernel_regularizer,
                         bias_regularizer=bias_regularizer,
                         activity_regularizer=activity_regularizer,
                         kernel_constraint=kernel_constraint,
                         bias_constraint=bias_constraint,
                         **kwargs)
        self.mlp_hidden = mlp_hidden if mlp_hidden else []
        self.alpha = alpha
        self.propagations = propagations
        self.mlp_activation = activations.get(mlp_activation)
        self.dropout_rate = dropout_rate 

def __init__(self,
                 trainable_kernel=False,
                 activation=None,
                 kernel_initializer='glorot_uniform',
                 kernel_regularizer=None,
                 kernel_constraint=None,
                 **kwargs):

        super().__init__(**kwargs)
        self.trainable_kernel = trainable_kernel
        self.activation = activations.get(activation)
        self.kernel_initializer = initializers.get(kernel_initializer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.kernel_constraint = constraints.get(kernel_constraint) 

def __init__(self,
               output_dim: int,
               num_legs: int,
               num_levels: int,
               use_bias: Optional[bool] = True,
               activation: Optional[Text] = None,
               kernel_initializer: Optional[Text] = 'glorot_uniform',
               bias_initializer: Optional[Text] = 'zeros',
               **kwargs) -> None:

    if 'input_shape' not in kwargs and 'input_dim' in kwargs:
      kwargs['input_shape'] = (kwargs.pop('input_dim'),)

    assert (
        num_legs >=
        2), f'Need at least 2 legs to create Entangler but got {num_legs} legs'
    assert (
        num_levels >= 1
    ), f'Need at least 1 level to create Entangler but got {num_levels} levels'

    super(DenseEntangler, self).__init__(**kwargs)

    self.output_dim = output_dim
    self.num_legs = num_legs
    self.num_levels = num_levels
    self.nodes = []
    self.use_bias = use_bias
    self.activation = activations.get(activation)
    self.kernel_initializer = initializers.get(kernel_initializer)
    self.bias_initializer = initializers.get(bias_initializer) 

def __init__(self,
               output_dim: int,
               num_nodes: int,
               bond_dim: int,
               use_bias: Optional[bool] = True,
               activation: Optional[Text] = None,
               kernel_initializer: Optional[Text] = 'glorot_uniform',
               bias_initializer: Optional[Text] = 'zeros',
               **kwargs) -> None:

    # Allow specification of input_dim instead of input_shape,
    # for compatability with Keras layers that support this
    if 'input_shape' not in kwargs and 'input_dim' in kwargs:
      kwargs['input_shape'] = (kwargs.pop('input_dim'),)

    assert num_nodes > 2, 'Need at least 3 nodes to create MPO.'

    super(DenseMPO, self).__init__(**kwargs)

    self.output_dim = output_dim
    self.num_nodes = num_nodes
    self.bond_dim = bond_dim
    self.nodes = []
    self.use_bias = use_bias
    self.activation = activations.get(activation)
    self.kernel_initializer = initializers.get(kernel_initializer)
    self.bias_initializer = initializers.get(bias_initializer) 

def __init__(self,
                 T=3,
                 n_hidden=512,
                 activation=None,
                 activation_lstm='tanh',
                 recurrent_activation='hard_sigmoid',
                 kernel_initializer='glorot_uniform',
                 recurrent_initializer='orthogonal',
                 bias_initializer='zeros',
                 use_bias=True,
                 unit_forget_bias=True,
                 kernel_regularizer=None,
                 recurrent_regularizer=None,
                 bias_regularizer=None,
                 kernel_constraint=None,
                 recurrent_constraint=None,
                 bias_constraint=None,
                 **kwargs):

        super().__init__(**kwargs)
        self.activation = activations.get(activation)
        self.use_bias = use_bias
        self.kernel_initializer = initializers.get(kernel_initializer)
        self.bias_initializer = initializers.get(bias_initializer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.bias_regularizer = regularizers.get(bias_regularizer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.kernel_constraint = constraints.get(kernel_constraint)
        self.bias_constraint = constraints.get(bias_constraint)

        self.activation_lstm = activations.get(activation_lstm)
        self.recurrent_activation = activations.get(recurrent_activation)
        self.recurrent_initializer = initializers.get(recurrent_initializer)
        self.unit_forget_bias = unit_forget_bias
        self.recurrent_regularizer = regularizers.get(recurrent_regularizer)
        self.recurrent_constraint = constraints.get(recurrent_constraint)
        self.T = T
        self.n_hidden = n_hidden 

def __init__(self,
               output_dim,
               input_dim,
               init_fn='glorot_uniform',
               inner_init_fn='orthogonal',
               activation_fn='tanh',
               inner_activation_fn='hard_sigmoid',
               **kwargs):
    """
    Parameters
    ----------
    output_dim: int
      Dimensionality of output vectors.
    input_dim: int
      Dimensionality of input vectors.
    init_fn: str
      TensorFlow nitialization to use for W.
    inner_init_fn: str
      TensorFlow initialization to use for U.
    activation_fn: str
      TensorFlow activation to use for output.
    inner_activation_fn: str
      TensorFlow activation to use for inner steps.
    """

    super(LSTMStep, self).__init__(**kwargs)
    self.init = init_fn
    self.inner_init = inner_init_fn
    self.output_dim = output_dim
    # No other forget biases supported right now.
    self.activation = activation_fn
    self.inner_activation = inner_activation_fn
    self.activation_fn = activations.get(activation_fn)
    self.inner_activation_fn = activations.get(inner_activation_fn)
    self.input_dim = input_dim 

def deserialize_kwarg(key, attr):
    if key.endswith('_initializer'):
        return initializers.get(attr)
    if key.endswith('_regularizer'):
        return regularizers.get(attr)
    if key.endswith('_constraint'):
        return constraints.get(attr)
    if key == 'activation':
        return activations.get(attr) 

def build(self, input_shape):
    n_hidden = self.n_hidden
    init = initializers.get(self.init)
    self.Wz = init([n_hidden, n_hidden])
    self.Wr = init([n_hidden, n_hidden])
    self.Wh = init([n_hidden, n_hidden])
    self.Uz = init([n_hidden, n_hidden])
    self.Ur = init([n_hidden, n_hidden])
    self.Uh = init([n_hidden, n_hidden])
    self.bz = backend.zeros(shape=(n_hidden,))
    self.br = backend.zeros(shape=(n_hidden,))
    self.bh = backend.zeros(shape=(n_hidden,))
    self.built = True 

def build(self, input_shape):
    n_pair_features = self.n_pair_features
    n_hidden = self.n_hidden
    init = initializers.get(self.init)
    self.W = init([n_pair_features, n_hidden * n_hidden])
    self.b = backend.zeros(shape=(n_hidden * n_hidden,))
    self.built = True 

def __init__(self,
               n_graph_feat=30,
               n_outputs=30,
               max_atoms=50,
               layer_sizes=[100],
               init='glorot_uniform',
               activation='relu',
               dropout=None,
               **kwargs):
    """DAG vector gathering layer

    Parameters
    ----------
    n_graph_feat: int, optional
      Number of features for each atom.
    n_outputs: int, optional
      Number of features for each molecule.
    max_atoms: int, optional
      Maximum number of atoms in molecules.
    layer_sizes: list of int, optional
      List of hidden layer size(s):
      length of this list represents the number of hidden layers,
      and each element is the width of corresponding hidden layer.
    init: str, optional
      Weight initialization for filters.
    activation: str, optional
      Activation function applied.
    dropout: float, optional
      Dropout probability in the hidden layer(s).
    """
    super(DAGGather, self).__init__(**kwargs)
    self.init = init  # Set weight initialization
    self.activation = activation  # Get activations
    self.activation_fn = activations.get(activation)
    self.layer_sizes = layer_sizes
    self.dropout = dropout
    self.max_atoms = max_atoms
    self.n_graph_feat = n_graph_feat
    self.n_outputs = n_outputs 

def build(self, input_shape):
    """"Construct internal trainable weights."""
    self.W_list = []
    self.b_list = []
    self.dropouts = []
    init = initializers.get(self.init)
    prev_layer_size = self.n_inputs
    for layer_size in self.layer_sizes:
      self.W_list.append(init([prev_layer_size, layer_size]))
      self.b_list.append(backend.zeros(shape=[
          layer_size,
      ]))
      if self.dropout is not None and self.dropout > 0.0:
        self.dropouts.append(Dropout(rate=self.dropout))
      else:
        self.dropouts.append(None)
      prev_layer_size = layer_size
    self.W_list.append(init([prev_layer_size, self.n_outputs]))
    self.b_list.append(backend.zeros(shape=[
        self.n_outputs,
    ]))
    if self.dropout is not None and self.dropout > 0.0:
      self.dropouts.append(Dropout(rate=self.dropout))
    else:
      self.dropouts.append(None)
    self.built = True 

def __init__(self,
               n_embedding=30,
               n_outputs=100,
               layer_sizes=[100],
               output_activation=True,
               init='glorot_uniform',
               activation='tanh',
               **kwargs):
    """
    Parameters
    ----------
    n_embedding: int, optional
      Number of features for each atom
    n_outputs: int, optional
      Number of features for each molecule(output)
    layer_sizes: list of int, optional(default=[1000])
      Structure of hidden layer(s)
    init: str, optional
      Weight initialization for filters.
    activation: str, optional
      Activation function applied
    """
    super(DTNNGather, self).__init__(**kwargs)
    self.n_embedding = n_embedding
    self.n_outputs = n_outputs
    self.layer_sizes = layer_sizes
    self.output_activation = output_activation
    self.init = init  # Set weight initialization
    self.activation = activation  # Get activations
    self.activation_fn = activations.get(activation) 

def build(self, input_shape):
    init = initializers.get(self.init)
    self.W_cf = init([self.n_embedding, self.n_hidden])
    self.W_df = init([self.n_distance, self.n_hidden])
    self.W_fc = init([self.n_hidden, self.n_embedding])
    self.b_cf = backend.zeros(shape=[
        self.n_hidden,
    ])
    self.b_df = backend.zeros(shape=[
        self.n_hidden,
    ])
    self.built = True 

def __init__(self,
               n_embedding=30,
               n_distance=100,
               n_hidden=60,
               init='glorot_uniform',
               activation='tanh',
               **kwargs):
    """
    Parameters
    ----------
    n_embedding: int, optional
      Number of features for each atom
    n_distance: int, optional
      granularity of distance matrix
    n_hidden: int, optional
      Number of nodes in hidden layer
    init: str, optional
      Weight initialization for filters.
    activation: str, optional
      Activation function applied
    """
    super(DTNNStep, self).__init__(**kwargs)
    self.n_embedding = n_embedding
    self.n_distance = n_distance
    self.n_hidden = n_hidden
    self.init = init  # Set weight initialization
    self.activation = activation  # Get activations
    self.activation_fn = activations.get(activation) 

def build(self, input_shape):
    init = initializers.get(self.init)
    self.embedding_list = init([self.periodic_table_length, self.n_embedding])
    self.built = True 

def __init__(self,
               batch_size,
               n_input=128,
               gaussian_expand=False,
               init='glorot_uniform',
               activation='tanh',
               epsilon=1e-3,
               momentum=0.99,
               **kwargs):
    """
    Parameters
    ----------
    batch_size: int
      number of molecules in a batch
    n_input: int, optional
      number of features for each input molecule
    gaussian_expand: boolean. optional
      Whether to expand each dimension of atomic features by gaussian histogram
    init: str, optional
      Weight initialization for filters.
    activation: str, optional
      Activation function applied
    """
    super(WeaveGather, self).__init__(**kwargs)
    self.n_input = n_input
    self.batch_size = batch_size
    self.gaussian_expand = gaussian_expand
    self.init = init  # Set weight initialization
    self.activation = activation  # Get activations
    self.activation_fn = activations.get(activation)
    self.epsilon = epsilon
    self.momentum = momentum 

def build(self, input_shape):
    """ Construct internal trainable weights."""
    init = initializers.get(self.init)  # Set weight initialization

    self.W_AA = init([self.n_atom_input_feat, self.n_hidden_AA])
    self.b_AA = backend.zeros(shape=[
        self.n_hidden_AA,
    ])

    self.W_PA = init([self.n_pair_input_feat, self.n_hidden_PA])
    self.b_PA = backend.zeros(shape=[
        self.n_hidden_PA,
    ])

    self.W_A = init([self.n_hidden_A, self.n_atom_output_feat])
    self.b_A = backend.zeros(shape=[
        self.n_atom_output_feat,
    ])

    if self.update_pair:
      self.W_AP = init([self.n_atom_input_feat * 2, self.n_hidden_AP])
      self.b_AP = backend.zeros(shape=[
          self.n_hidden_AP,
      ])

      self.W_PP = init([self.n_pair_input_feat, self.n_hidden_PP])
      self.b_PP = backend.zeros(shape=[
          self.n_hidden_PP,
      ])

      self.W_P = init([self.n_hidden_P, self.n_pair_output_feat])
      self.b_P = backend.zeros(shape=[
          self.n_pair_output_feat,
      ])
    self.built = True 

def build(self, input_shape):
    """Constructs learnable weights for this layer."""
    init = initializers.get(self.init)
    inner_init = initializers.get(self.inner_init)
    self.W = init((self.input_dim, 4 * self.output_dim))
    self.U = inner_init((self.output_dim, 4 * self.output_dim))

    self.b = tf.Variable(
        np.hstack((np.zeros(self.output_dim), np.ones(self.output_dim),
                   np.zeros(self.output_dim), np.zeros(self.output_dim))),
        dtype=tf.float32)
    self.built = True