在 Keras 中声明已转换序列的 input_shape？

Question

I am trying to run a neural network on text inputs. This is a binary classification. Here is my working code so far:

df = pd.read_csv(pathname, encoding = "ISO-8859-1")
df = df[['content_cleaned', 'meaningful']] #Content cleaned: text, meaningful: label

X = df['content_cleaned']
y = df['meaningful']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=21) 

tokenizer = Tokenizer(num_words=100)
tokenizer.fit_on_texts(X_train)
X_train_encoded = tokenizer.texts_to_sequences(X_train)
X_test_encoded = tokenizer.texts_to_sequences(X_test)

max_len = 100
X_train = pad_sequences(X_train_encoded, maxlen=max_len)
X_test = pad_sequences(X_test_encoded, maxlen=max_len)


batch_size = 100
max_words = 100
input_dim = X_train.shape[1]  # Number of features
model = Sequential()
model.add(layers.Dense(10, activation='relu', input_shape=X_train.shape[1:]))




model.add(layers.Dense(1, activation='sigmoid'))

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

history = model.fit(X_train, X_test,
                batch_size=batch_size,
                epochs=5,
                verbose=1,
                validation_split=0.1)

My question is two parts. First is with the input_shape when creating the layers. I am confused as to the syntax of declaring this. When running this command:

print(X_train.shape)

I am getting this shape: (3609, 100) .

From my understanding, this is telling me that there are 3609 instances. From viewing other examples, my naive assumption was to use the 100 as there are 100 types (may be understanding this incorrectly) corresponding to the max_words that I initialized. I believe that I may have done the syntax incorrectly when initializing the input_shape .

The second question is with an error message when running all of this (most likely with the incorrect input_shape ). The error message highlights this line of code:

 validation_split=0.1)

The error message is:

ValueError: Error when checking target: expected dense_2 to have shape (None, 1) but got array with shape (1547, 1

Am I going about this problem incorrectly? I am very new to Deep Learning.

Answer 1

The input_shape argument specifies the shape of one training sample . Therefore, you need to set it to X_train.shape[1:] (ie ignore samples or batch axis):

model.add(layers.Dense(10, activation='relu', input_shape=X_train.shape[1:]))

Further, pass X_train and y_train to the fit_generator (instead of X_train_encoded and X_test_encoded ).

Answer 2

You missed two ending parenthesis ) at the line where you defined the input of your model. Also make sure that you provide your activation function .

Change your code as below:

model.add(layers.Dense(10, activation='relu', input_shape=(X_train.shape[0],)))

EDIT:

For your last error just change your input_shape to input_shape=(X_train.shape[0],) .