Fully connected layer output ValueError

Question

I am working on a glaucoma detection CNN and I'm getting the following error ValueError: Error when checking target: expected activation_1 to have shape (2,) but got array with shape (1,) for any other number at the final Dense layer except 1. Since the number of classifications is 2, I need to give Dense(2) before the activation function. But whenever I run the code with Dense(1), I get a good accuracy but during testing, everything is predicted to be from the same class. How do I solve this error without changing my Dense layer back to Dense(1)

This is the code:

img_width, img_height = 256, 256
input_shape = (img_width, img_height, 3)

train_data_dir = "data/train"
validation_data_dir = "data/validation"
nb_train_samples = 500
nb_validation_samples = 50
batch_size = 10
epochs = 10

model = Sequential()

model.add(Conv2D(3, (11, 11), activation='relu', input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))

model.add(Conv2D(96, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
model.add(Dropout(0.5))
model.add(Conv2D(192, (3, 3)))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
model.add(Dropout(0.5))
model.add(Conv2D(192, (3, 3)))

model.add(Flatten())
model.add(Dense(2))
model.add(Activation('softmax'))

model.summary()
model.compile(loss="binary_crossentropy", optimizer=optimizers.Adam(lr=0.001, beta_1=0.9,
                                                                    beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False), metrics=["accuracy"])


# Initiate the train and test generators with data Augumentation
train_datagen = ImageDataGenerator(
    rescale=1./255,
    horizontal_flip=True,
    rotation_range=30)

test_datagen = ImageDataGenerator(
    rescale=1./255,
    horizontal_flip=True,
    rotation_range=30)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode="binary")

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_height, img_width),
    class_mode="binary")


model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size

)

model.save('f1.h5')

Any help will be much appreciated.

Answer 1

That is because you specify class_mode='binary' in your image generators which means two classes will be encoded as 0 or 1 rather than [1,0] or [0,1]. You can easily solve this by changing your final layer to:

model.add(Dense(1, activation='sigmoid'))
# No need for softmax activation
model.compile(loss='binary_crossentropy', ...)

Binary cross-entropy on 0-1 is mathematically equivalent to 2 class softmax with cross-entropy so you achieve the same thing.