Cacher is the code snippet organizer for pro developers

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras.datasets import mnist

# 2. Load pre-shuffled MNIST data into train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# 3. Preprocess input data
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255

# 4. Preprocess class labels
Y_train = np_utils.to_categorical(y_train, 10)
Y_test = np_utils.to_categorical(y_test, 10)

# 5. Define model architecture
model = Sequential()
 
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(28,28,1)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2))) #tells what is the size of these grids?
model.add(Dropout(0.25))
 
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))

# 6. Compile model
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])
              
# 7. Fit model on training data
model.fit(X_train, Y_train, 
          batch_size=32, epochs=10, verbose=1)
          
# 8. Evaluate model on test data
score = model.evaluate(X_test, Y_test, verbose=0)