Home > Net >  ValueError: Dimensions must be equal, but are 2 and 64 for '{{node binary_crossentropy/mul}} wi
ValueError: Dimensions must be equal, but are 2 and 64 for '{{node binary_crossentropy/mul}} wi

Time:03-30

I'm trying binary classification of text with bi-lstm model but getting this error: ValueError: Dimensions must be equal, but are 2 and 64 for '{{node binary_crossentropy/mul}} = Mul[T=DT_FLOAT](binary_crossentropy/Cast, binary_crossentropy/Log)' with input shapes: [?,2], [?,64]. I am a beginner please provide some valuable solutions.

text=df['text']
label=df['label']

X = pad_sequences(X, maxlen=max_len,padding=pad_type,truncating=trunc_type)
Y = pd.get_dummies(label).values    
X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.20)
print(X_train.shape,Y_train.shape)
print(X_test.shape,Y_test.shape)

#model creation
model=tf.keras.Sequential([
 # add an embedding layer
 tf.keras.layers.Embedding(word_count, 16, input_length=max_len),
 tf.keras.layers.Dropout(0.2),
 # add another bi-lstm layer
 tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(2,return_sequences=True)),
 # add a dense layer
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.softmax),
 # add the prediction layer
 tf.keras.layers.Dense(1, activation=tf.keras.activations.sigmoid),
])
model.compile(loss=tf.keras.losses.BinaryCrossentropy(), optimizer=tf.keras.optimizers.Adam(), metrics=['accuracy'])
model.summary()
history = model.fit(X_train,  Y_train, validation_data=(X_test,  Y_test), epochs = 10, batch_size=batch_size, callbacks = [callback_func], verbose=1)

CodePudding user response:

The output dimension of the prediction layer of the binary classification should be 2:

# add the prediction layer
tf.keras.layers.Dense(2, activation=tf.keras.activations.sigmoid)

Flatten:

#model creation
model=tf.keras.Sequential([
 # add an embedding layer
 tf.keras.layers.Embedding(word_count, 16, input_length=max_len),
 tf.keras.layers.Dropout(0.2),
 # add another bi-lstm layer
 tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(2,return_sequences=True)),
 # add flatten
 tf.keras.layers.Flatten(),  #<========================
 # add a dense layer
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.softmax),
 # add the prediction layer
 tf.keras.layers.Dense(2, activation=tf.keras.activations.sigmoid),
])
  • Related