Я тренирую данные Fashion MNIST, используя CNN.Dut to overfit Я попытался добавить слой Dropout.Но он не работает
До того, как я добавил Dropout, модель работала нормально.
def fashion_model()
batch_size = 64
epochs = 20
num_classes = 10
fashion_drop_model = Sequential()
fashion_drop_model.add(Conv2D(32, kernel_size=(3, 3),activation='linear',padding='same',input_shape=(28,28,1)))
fashion_drop_model.add(LeakyReLU(alpha=0.1))
fashion_drop_model.add(MaxPooling2D((2, 2),padding='same'))
fashion_drop_model.add(Dropout(0.25))
fashion_drop_model.add(Conv2D(64, (3, 3), activation='linear',padding='same'))
fashion_drop_model.add(LeakyReLU(alpha=0.1))
fashion_drop_model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
fashion_drop_model.add(Dropout(0.25))
fashion_drop_model.add(Conv2D(128, (3, 3), activation='linear',padding='same'))
fashion_drop_model.add(LeakyReLU(alpha=0.1))
fashion_drop_model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
fashion_drop_model.add(Dropout(0.4))
fashion_drop_model.add(Flatten())
fashion_drop_model.add(Dense(128, activation='linear'))
fashion_drop_model.add(LeakyReLU(alpha=0.1))
fashion_drop_model.add(Dropout(0.3))
fashion_drop_model.add(Dense(num_classes, activation='softmax'))
return fashion_drop_model.summary()
fashion_model()
Я получаю ошибку: UnboundLocalError: local variable 'a' referenced before assignment
PS: послекороткое пошаговое описание кода, я понял, что ошибка в строке 8 (fashion_drop_model.add(Dropout(0.25))
)