add_weight() got multiple values for argument 'name' while using a custom Attention(Layer) in Keras

Question

(I think this is because of the version conflict as the authors have used keras.engine.topology.Layer)

With tensorflow==2.2.0 and keras==2.4.3, I am trying to learn the Attention Mechanism and have imported the code from somewhere as:

from keras import backend as K
from keras.engine.topology import Layer
from keras import initializers, regularizers, constraints

from keras.layers import Dense, Input, LSTM, Bidirectional, Activation, Conv1D, GRU, TimeDistributed
from keras.layers import Dropout, Embedding, GlobalMaxPooling1D, MaxPooling1D, Add, Flatten, SpatialDropout1D
from keras.layers import GlobalAveragePooling1D, BatchNormalization, concatenate
from keras.layers import Reshape, merge, Concatenate, Lambda, Average
from keras.models import Sequential, Model
from keras.initializers import Constant
from keras.layers.merge import add


class Attention(Layer):
    def __init__(self, step_dim,
                 W_regularizer=None, b_regularizer=None,
                 W_constraint=None, b_constraint=None,
                 bias=True, **kwargs):
        self.supports_masking = True
        self.init = initializers.get('glorot_uniform')
        self.W_regularizer = regularizers.get(W_regularizer)
        self.b_regularizer = regularizers.get(b_regularizer)
        self.W_constraint = constraints.get(W_constraint)
        self.b_constraint = constraints.get(b_constraint)
        self.bias = bias
        self.step_dim = step_dim
        self.features_dim = 0
        super(Attention, self).__init__(**kwargs)

    def build(self, input_shape):
        assert len(input_shape) == 3
        self.W = self.add_weight((input_shape[-1],),
                                 initializer=self.init,
                                 name='{}_W'.format(self.name),
                                 regularizer=self.W_regularizer,
                                 constraint=self.W_constraint)
        self.features_dim = input_shape[-1]
        if self.bias:
            self.b = self.add_weight((input_shape[1],),
                                     initializer='zero',
                                     name='{}_b'.format(self.name),
                                     regularizer=self.b_regularizer,
                                     constraint=self.b_constraint)
        else:
            self.b = None
        self.built = True

    def compute_mask(self, input, input_mask=None):
        return None

    def call(self, x, mask=None):
        features_dim = self.features_dim
        step_dim = self.step_dim
        eij = K.reshape(K.dot(K.reshape(x, (-1, features_dim)), K.reshape(self.W, (features_dim, 1))), (-1, step_dim))
        if self.bias:
            eij += self.b
        eij = K.tanh(eij)
        a = K.exp(eij)
        if mask is not None:
            a *= K.cast(mask, K.floatx())
        a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())
        a = K.expand_dims(a)
        weighted_input = x * a
        return K.sum(weighted_input, axis=1)

    def compute_output_shape(self, input_shape):
        return input_shape[0],  self.features_dim

The Problem is when I try to use,

lstm_layer = LSTM(300, dropout=0.25, recurrent_dropout=0.25, return_sequences=True)

inp = Input(shape=(maxlen,), dtype='int32')
embedding= embedding_layer(inp)
x = lstm_layer(embedding)
x = Dropout(0.25)(x)
merged = Attention(maxlen)(x)
merged = Dense(256, activation='relu')(merged)
merged = Dropout(0.25)(merged)
merged = BatchNormalization()(merged)
outp = Dense(len(int_category), activation='softmax')(merged)

AttentionLSTM = Model(inputs=inp, outputs=outp)
AttentionLSTM.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['acc'])

AttentionLSTM.summary()

it throws an error as TypeError: add_weight() got multiple values for argument 'name'

Full traceback of the error is:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-25-1ab1f1ef1ed7> in <module>
      5 x = lstm_layer(embedding)
      6 x = Dropout(0.25)(x)
----> 7 merged = Attention(maxlen)(x)
      8 merged = Dense(256, activation='relu')(merged)
      9 merged = Dropout(0.25)(merged)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    895           # Build layer if applicable (if the `build` method has been
    896           # overridden).
--> 897           self._maybe_build(inputs)
    898           cast_inputs = self._maybe_cast_inputs(inputs)
    899 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
   2414         # operations.
   2415         with tf_utils.maybe_init_scope(self):
-> 2416           self.build(input_shapes)  # pylint:disable=not-callable
   2417       # We must set also ensure that the layer is marked as built, and the build
   2418       # shape is stored since user defined build functions may not be calling

<ipython-input-20-86a01469b2e5> in build(self, input_shape)
     23                                  name='{}_W'.format(self.name),
     24                                  regularizer=self.W_regularizer,
---> 25                                  constraint=self.W_constraint)
     26         self.features_dim = input_shape[-1]
     27         if self.bias:

TypeError: add_weight() got multiple values for argument 'name'

Answer 1

The issue is coming because the add_weight function is taking value from the shape tuples. Try writing "shape = shape(YOUR INPUT)" . This should resolve the issue.