Using conv1d Layer in Tensorflow Sequential Model

Question

i am very new to Tensorflow and just cannot figure out the problem. I am trying to build a CNN, but I keep having issues with the conv1d layer (specifically the input): expected min_ndim=3, found ndim=2 tensorflow sequential

I already tried: ValueError when using Conv1D layer, but this does not change anything.

Here is the code of the model:

#create feature_colums
from tensorflow import feature_column
feature_columns = []

for header in list(train_df.drop(columns=["LABEL"])):
  feature_columns.append(feature_column.numeric_column(header))

feature_layer = tf.keras.layers.DenseFeatures(feature_columns)

model = tf.keras.Sequential([
    feature_layer,
    #tf.keras.layers.InputLayer(input_shape=(len(feature_columns), 1)),
    tf.keras.layers.Dense(1024, activation="relu"),
    tf.keras.layers.Conv1D(32, 3, activation="relu"),
    #tf.keras.layers.MaxPool1D(pool_size=5),
    #tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Dense(512, activation="relu"),
    tf.keras.layers.Dense(256, activation="relu"),
    tf.keras.layers.Dense(256, activation="relu"),
    tf.keras.layers.Dense(128, activation="relu"),
    tf.keras.layers.Dense(128, activation="relu"),
    tf.keras.layers.Dense(64, activation="relu"),
    tf.keras.layers.Dense(32, activation="relu"),
    tf.keras.layers.Dense(12, activation="softmax")
])

model.compile(optimizer="adam",
            loss="sparse_categorical_crossentropy",
            metrics=['accuracy'])

model.fit(train_ds,
        validation_data=val_ds,
        epochs=25,
        #steps_per_epoch=20,
        callbacks=[tensorboard_callback]
            )

EDIT: This is how train_ds is created (I followed this tutorial: https://www.tensorflow.org/tutorials/structured_data/feature_columns#create_compile_and_train_the_model):

def df_to_dataset(dataframe, shuffle=True, batch_size=256):
  dataframe = dataframe.copy()
  labels = dataframe.pop("FAMILY")
  ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels))
  print(labels)
  if shuffle:
    ds = ds.shuffle(buffer_size=len(dataframe))
  ds = ds.batch(batch_size)
  return ds, labels, dataframe.values.tolist()

Thank you in advance!

score 0 · Answer 1 · answered Aug 29 '22 at 19:54

0

You have to keep x_train and y_train data separated. See the docs for keras fit function:

Model.fit(
    x=None,
    y=None,
    batch_size=None,
    epochs=1,
    verbose="auto",
    callbacks=None,
    validation_split=0.0,
    validation_data=None,
    shuffle=True,
    class_weight=None,
    sample_weight=None,
    initial_epoch=0,
    steps_per_epoch=None,
    validation_steps=None,
    validation_batch_size=None,
    validation_freq=1,
    max_queue_size=10,
    workers=1,
    use_multiprocessing=False,
)

The argument x represents your data to train, and y your labels. You have to reshape your train_ds data.

answered Aug 29 '22 at 19:54

ClaudiaR

3,108
2
13
27

I actually did seperate samples and labels when trying the solution from https://stackoverflow.com/questions/66124514/valueerror-when-using-conv1d-layer. A command that disappeared by now, told me to add tf.keras.layers.RepeatVector(N_TIMESTEPS) and that helped me! – Max Aug 29 '22 at 20:05
Ah, I see now. If the input is a tf.Dataset that's ok. Well... the problem is related to having a mismatch in your input shapes. Your feature_layer, which is your first layer, is expecting three dimensions. But the data with which you created the dataset, must have only two. You should print some shapes and try to understand which of the two is wrong. Your input should have two or three dimensions? After you've cleared that up, you can fix the inputs or the layer shape – ClaudiaR Aug 29 '22 at 21:25

score 0 · Answer 2 · answered Aug 30 '22 at 04:48

i think it would just cause of the input layer shape, the model is fed with dataset which is in shape (rows, features) into model, so based on that the will feed in this shape (batch_size, features) and as you know the term None means batch size and not needed to define for input shape, so in here:

tf.keras.layers.InputLayer(input_shape=(len(feature_columns), 1))

should be changed into

tf.keras.layers.InputLayer(input_shape=(len(feature_columns),))

or this one

tf.keras.layers.InputLayer(input_shape=(None, len(feature_columns)))

cause of tensorflow will assume term None in the input shape as batch size.

and basically, as i noticed this type of model (Conv1D) is for sequences but you are trying to implement model for a typical one, which takes features and then lead into output feature, which in this case is as label.

So if i got it correctly, change your model arch into a model without Conv1d layer and even change input_shape based on what i said above. hopefully, it would work.

Using conv1d Layer in Tensorflow Sequential Model

2 Answers2