Correct Conv1D layers shape for 2d classification data

Question

My dataset( Network traffic dataset where we do binary classification)-

The shape of X_train and y_train are (45447, 25) (45447,)

The model I am working on-

# fit and evaluate a model
import tensorflow as tf
def evaluate_model(X_train, y_train,X_test,y_test):

  X_train = X_train.reshape(45447,25,1)
  y_train=y_train.reshape(45447,1)
  verbose=0
  epochs=10
  batch_size = 32
  n_timesteps = X_train.shape[0]
  n_features= X_train.shape[1]
  print(n_timesteps,n_features)
  n_outputs = 1
  model = Sequential()
  model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
  model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
  model.add(Dropout(0.5))
  model.add(MaxPooling1D(pool_size=2))
  model.add(Flatten())
  model.add(Dense(100, activation='relu'))
  model.add(Dense(n_outputs, activation='softmax'))
  model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
  # fit network
  #train_data = tf.data.Dataset.from_tensor_slices((X_train, y_train))
  #valid_data = tf.data.Dataset.from_tensor_slices((X_test, y_test))

  model.fit(X_train, y_train,epochs=10, batch_size=32, verbose=0)
      # evaluate model
  #_, accuracy = model.evaluate(X_test, y_test, batch_size=batch_size, verbose=0)
  

# summarize scores
def summarize_results(scores):
    print(scores)
    m, s = mean(scores), std(scores)
    print('Accuracy: %.3f%% (+/-%.3f)' % (m, s))

# run an experiment
def run_experiment(repeats=10):
    # load data
    
    # repeat experiment
    scores = list()
    for r in range(repeats):
        score = evaluate_model(X_train, y_train,X_test,y_test)
        score = score * 100.0
        print('>#%d: %.3f' % (r+1, score))
        scores.append(score)
    # summarize results
    summarize_results(scores)

# run the experiment
run_experiment()

What I have tried-

1)I tried making the pandas data into numpy

2)Reshaped the 2d array to 3d -

X_train = X_train.reshape(45447,25,1)
y_train=y_train.reshape(45447,1,1)

3. Made the data into tf objects-

   train_data = tf.data.Dataset.from_tensor_slices((X_train, y_train)) valid_data = tf.data.Dataset.from_tensor_slices((X_test, y_test))

Still Im unable to run my model..it keeps giving shape errors. Please help me understand the shape to give to model.

Answer 1

I think you have to remove batch from the input_shape and add 1 as length or the feature:

model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_features , 1)))

For the output layer, there is no sense to use one unit dense cell with softmax activation, change the number of output units to :

 n_outputs = your_number_of_categories

Answer 2

input_shape should be X_train.shape[1:]. The loss function should be sparse_categorical_accuracy as labels are provided as integers.

def evaluate_model(X_train, y_train,X_test,y_test):

  X_train = X_train.reshape(45447,25,1)
  y_train=y_train.reshape(45447,1)
  verbose=0
  epochs=10
  batch_size = 32
  n_outputs = 2
  model = Sequential()
  model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=X_train.shape[1:]))
  model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
  model.add(Dropout(0.5))
  model.add(MaxPooling1D(pool_size=2))
  model.add(Flatten())
  model.add(Dense(100, activation='relu'))
  model.add(Dense(n_outputs, activation='softmax'))
  model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
  # fit network
  model.fit(X_train, y_train,epochs=10, batch_size=32, verbose=0)
  # evaluate model
  _, accuracy = model.evaluate(X_test, y_test, batch_size=batch_size, verbose=0)