Keras model fits for creating squares in Jupyter notebook edition

I am using Keras 2.0.2 with TensorFlow like:

I am running a simple model:

from keras.layers.core import Lambda, Flatten, Dense
from keras.models import Sequential
from keras.optimizers import Adam

model = Sequential([
    Lambda(norm_inp, input_shape=(1, 28, 28)),
    Flatten(),
    Dense(10, activation="softmax")
])

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

def run_fit(model, lr = 0.0001, epochs = 1):
    model.optimizer.lr = lr

    model.fit(x_train_processed, y_train_processed, epochs=epochs, verbose=1,
              validation_data=(x_test_processed, y_test_processed))

run_fit(model, 0.0001, 1)

      

        
        
        
      

    

But when I run this in Jupyter I get squares in the output.

I tried to find this, but I couldn't find anything suitable.