keras_test.py

import rpyc
from rpyc.utils.zerodeploy import DeployedServer
from plumbum import SshMachine

mach = SshMachine("rodrigo@server")
server = DeployedServer(mach, python_executable='/home/rodrigo/venv/bin/python')
conn = server.classic_connect()

import sys
conn.modules.sys.stdout = sys.stdout

keras = conn.modules.keras
mnist = conn.modules['keras.datasets'].mnist
Sequential = conn.modules['keras.models'].Sequential
Dense = conn.modules['keras.layers'].Dense
Dropout = conn.modules['keras.layers'].Dropout
RMSprop = conn.modules['keras.optimizers'].RMSprop

batch_size = 128
num_classes = 10
epochs = 20

# the data, shuffled and 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, y_train), (x_test, y_test) = (x_train[:100], y_train[:100]), (x_test[:100], y_test[:100])

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)

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'])

history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_data=(x_test, y_test))

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