ValueError: Error when checking target: expected dense_3 to have shape (3,) but got array with shape (1,) 

I read multiple similar issues but none helped me so far. The error is on the last layer, where I've put 3 because this is the number of classes I'm trying right now.

The code is the following:

import keras from keras.datasets
import cifar10 from keras.preprocessing.image 
import ImageDataGenerator from keras.models 
import Sequential 
from keras.layers import Dense, Dropout, Activation, Flatten from keras.layers import Conv2D, MaxPooling2D 
from keras import backend as K import os


# Constants used  
img_width, img_height = 224, 224  
train_data_dir='places\\train'  
validation_data_dir='places\\validation'  
save_filename = 'vgg_trained_model.h5'  
training_samples = 15  
validation_samples = 5  
batch_size = 5  
epochs = 5


if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height) else:
    input_shape = (img_width, img_height, 3)

model = Sequential([
    # Block 1
    Conv2D(64, (3, 3), activation='relu', input_shape=input_shape, padding='same'),
    Conv2D(64, (3, 3), activation='relu', padding='same'),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    # Block 2
    Conv2D(128, (3, 3), activation='relu', padding='same'),
    Conv2D(128, (3, 3), activation='relu', padding='same'),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    # Block 3
    Conv2D(256, (3, 3), activation='relu', padding='same'),
    Conv2D(256, (3, 3), activation='relu', padding='same'),
    Conv2D(256, (3, 3), activation='relu', padding='same'),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    # Block 4
    Conv2D(512, (3, 3), activation='relu', padding='same'),
    Conv2D(512, (3, 3), activation='relu', padding='same'),
    Conv2D(512, (3, 3), activation='relu', padding='same'),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    # Block 5
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    # Top
    Flatten(),
    Dense(4096, activation='relu'),
    Dense(4096, activation='relu'),
    Dense(3, activation='softmax') ])

model.summary()

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# no augmentation config train_datagen = ImageDataGenerator() validation_datagen = ImageDataGenerator()
     train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = validation_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=training_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=validation_samples // batch_size)

model.save_weights(save_filename)​

The problem is with your label-data shape. In a multiclass problem you are predicting the probabibility of every possible class, so must provide label data in (N, m) shape, where N is the number of training examples, and m is the number of possible classes (3 in your case).

Keras expects y-data in (N, 3) shape, not (N,) as you've problably provided, that's why it raises an error.

Use e.g. OneHotEncoder to convert your label data to one-hot encoded form.

Problem : expected dense_3 to have shape (3,) but got array with shape (1,)

If you are using it for classification then the number of variables should be correct in the parameter for adding a dense layer.

variables_for_classification=5 #change it as per your number of categories
model.add(Dense(variables_for_classification, activation='softmax'))

model.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size,validation_split=0.1,callbacks=[EarlyStopping(monitor='val_loss', patience=3, min_delta=0.0001)])

To make it more clear. As I was using the LSTM to predict the category of the news and the categories were 5- business, tech, politics, sports, entertainment

In that dense function when I put 5 it worked correctly.

The problem is with the shape of the labels of the data "Y".
The shape you have for the labels are (m,) and this will not work with the:

loss = "binary_crossentropy"

I believe if you don't want to play with the shape of the labels, then use:

loss = "sparse_categorical_crossentropy"