assertion failed: [Condition x == y did not hold element-wise:]

Question

I have built a BiLSTM model with an attention layer for sentence classification task but I am getting an error that my assertion has failed due to mismatch in number of parameters. The attention layer code is here and the error is below the code.

class attention(Layer):
    
    def __init__(self, return_sequences=True):
        self.return_sequences = return_sequences
        super(attention,self).__init__()
        
    def build(self, input_shape):
        
        self.W=self.add_weight(name="att_weight", shape=(input_shape[-1],1),
                               initializer="normal")
        self.b=self.add_weight(name="att_bias", shape=(input_shape[1],1),
                               initializer="zeros")
        
        super(attention,self).build(input_shape)
        
    def call(self, x):
        
        e = K.tanh(K.dot(x,self.W)+self.b)
        a = K.softmax(e, axis=1)
        output = x*a
        
        if self.return_sequences:
            return output
        
        return K.sum(output, axis=1)

When i am training the model with attention layer included, it is giving an error that assertion failed.

Epoch 1/10
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-45-ac310033130c> in <module>()
      1 #Early stopping, Adam, dropout = 0.3, 0.5, 0.5
      2 #history = model.fit(sequences_matrix, Y_train, batch_size=256, epochs=5, validation_split=0.1,  callbacks=[EarlyStopping(monitor='val_loss', min_delta=0.0001)])
----> 3 history = model.fit(sequences_matrix, Y_train, batch_size=32, epochs=10, validation_split=0.1)

8 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     58     ctx.ensure_initialized()
     59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:
     62     if name is not None:

InvalidArgumentError:  assertion failed: [Condition x == y did not hold element-wise:] [x (sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/Shape_1:0) = ] [32 1] [y (sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/strided_slice:0) = ] [32 758]
     [[node sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/assert_equal_1/Assert/Assert (defined at <ipython-input-45-ac310033130c>:3) ]] [Op:__inference_train_function_19854]

Function call stack:
train_function

My model is

model = Sequential()
model.add(Embedding(max_words, 768, input_length=max_len, weights=[embedding]))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(SpatialDropout1D(0.1))
model.add(Conv1D(16, kernel_size=11, activation='relu'))
model.add(Bidirectional(LSTM(16, return_sequences=True)))
model.add(attention(return_sequences=True))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(Dropout(0.2))
model.add(Dense(2, activation='softmax', use_bias=True, kernel_regularizer=regularizers.l1_l2(l1=1e-5, l2=1e-4), bias_regularizer=regularizers.l2(1e-4),
    activity_regularizer=regularizers.l2(1e-5)))
model.summary()

Shape of Y_train is

max_words = 48369
max_len = 768
tok = Tokenizer(num_words = max_words)
tok.fit_on_texts(X_train)
sequences = tok.texts_to_sequences(X_train)
sequences_matrix = sequence.pad_sequences(sequences, maxlen = max_len)
Y_train = np.array(Y_train)
Y_test = np.array(Y_test)

print(Y_train.shape)

(43532, 1)

Answer 1

your target is in 2D so you need to set return_sequences=False in the last attention layer in order to return output in 2D format

Answer 2

Add flatten layer before Dropout and then execute.

model.add(Flatten())