In [1]:

    

HOST = "app.verta.ai"

PROJECT_NAME = "MNIST Multiclassification"
EXPERIMENT_NAME = "FC-NN"


    

In [2]:

    

# import os
# os.environ['VERTA_EMAIL'] = 
# os.environ['VERTA_DEV_KEY'] =


    

In [3]:

    

from verta import Client

client = Client(HOST)
proj = client.set_project(PROJECT_NAME)
expt = client.set_experiment(EXPERIMENT_NAME)


    

In [4]:

    

from __future__ import print_function

from tensorflow import keras
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.optimizers import RMSprop


    

In [5]:

    

batch_size = 128
num_classes = 10
epochs = 5


    

In [6]:

    

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)


    

In [7]:

    

model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(num_classes, activation='softmax'))

model.summary()

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


    

In [8]:

    

run = client.set_experiment_run()


    

In [9]:

    

from verta.integrations.keras import VertaCallback


history = model.fit(
    x_train, y_train,
    batch_size=batch_size,
    epochs=epochs,
    verbose=1,
    validation_data=(x_test, y_test),
    callbacks=[VertaCallback(run)],
)

score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])


    

In [10]:

    

run