Implementation of Deep learning model in Keras

Question

I am trying to implement the neural network model in Keras but I am getting a dimensionality issue. As per the Model architecture, I should get 1 as the output dimension from the last(Fully connected) layer but I am getting 2D data as output.

I am trying to implement the figure-4 from the paper.

Model proposed Architecture

My Implementation is as below:

import numpy as np
from tensorflow.keras import layers, Model
from tensorflow.keras.optimizers import Adam, RMSprop
from tensorflow.keras.utils import plot_model
from tensorflow.python.keras.regularizers import l2
from keras.datasets import imdb
from keras.preprocessing import sequence

def get_model(vocabulary_size, embedding_dim, input_length, summary=True):
  inputs = layers.Input(shape=(input_length))
  x = layers.Embedding(vocabulary_size, embedding_dim)(inputs)

  branch1 = layers.Conv1D(128, kernel_size=(3),padding='same',kernel_regularizer=l2(0.01), activation='relu')(x)
  branch1 = layers.MaxPool1D(pool_size=(2))(branch1)
  branch1 = layers.Dropout(0.5)(branch1)
  branch1 = layers.BatchNormalization()(branch1)
  branch1 = layers.LSTM(128, return_sequences=True)(branch1)

  branch2 = layers.Conv1D(128, kernel_size=(5),padding='same',kernel_regularizer=l2(0.01), activation='relu')(x)
  branch2 = layers.MaxPool1D(pool_size=(2))(branch2)
  branch2 = layers.Dropout(0.5)(branch2)
  branch2 = layers.BatchNormalization()(branch2)
  branch2 = layers.LSTM(128, return_sequences=True)(branch2)


  branch3 = layers.Conv1D(128, kernel_size=(7),padding='same',kernel_regularizer=l2(0.01), activation='relu')(x)
  branch3 = layers.MaxPool1D(pool_size=(2))(branch3)
  branch3 = layers.Dropout(0.5)(branch3)
  branch3 = layers.BatchNormalization()(branch3)
  branch3 = layers.LSTM(128, return_sequences=True)(branch3)

  branch4 = layers.Conv1D(128, kernel_size=(9),padding='same',kernel_regularizer=l2(0.01), activation='relu')(x)
  branch4 = layers.MaxPool1D(pool_size=(2))(branch4)
  branch4 = layers.Dropout(0.5)(branch4)
  branch4 = layers.BatchNormalization()(branch4)
  branch4 = layers.LSTM(128, return_sequences=True)(branch4)

  concat = layers.concatenate([branch1, branch2, branch3, branch4], name='Concatenate')

  outputs = layers.Dense(1, activation='sigmoid')(concat)


  model = Model(inputs, outputs)
  model.compile(loss='binary_crossentropy', optimizer=Adam(lr=1e-3), metrics='accuracy')
  
  print(model.summary())

  return model

EMBEDDING_DIM = 32
VOCABULARY_SIZE = 5000
seq_length = 500

my_model = get_model(VOCABULARY_SIZE, EMBEDDING_DIM, seq_length)

Hi, welcome to StackOverflow. Please refer to the guidelines https://stackoverflow.com/help/how-to-ask before asking a question. You would need to a minimal working example of your code that reproduces the issue. For that you would need to provide data and rest of your code as well. — Ananda, Jan 01 '21 at 12:52
@gaussian-prior answer will make it 1 as dimension as required. But still research paper will have details like what to do with LSTM & whether last hidden will suffice or not. I am not able to access that paper. — Alok Nayak, Jan 01 '21 at 14:16

score 1 · Answer 1 · answered Jan 01 '21 at 14:03

You need return_sequences = False in your last LSTM layer so it only returns last hidden state. That way it only returns a vector. So 4 branches return 4 vectors which are concatenated into one.

More details: How to use return_sequences option and TimeDistributed layer in Keras?

Implementation of Deep learning model in Keras

1 Answers1