MLflow_Keras.py

#!/usr/bin/env python
# coding: utf-8

'''Trains and evaluate a simple MLP
on the Reuters newswire topic classification task.
'''
from __future__ import print_function

import numpy as np
import keras
from keras.datasets import reuters
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.preprocessing.text import Tokenizer

import mlflow
import mlflow.keras


# # Setup Experiment Tracker

tracking_uri='file:///root/mlflow'
mlflow.set_tracking_uri(tracking_uri)

experiment_name = 'reuters'
mlflow.set_experiment(experiment_name)  

mlflow.keras.autolog()


# # Load the Training Data

max_words = 1000
batch_size = 32
epochs = 1

(x_train, y_train), (x_test, y_test) = reuters.load_data(num_words=max_words,
                                                         test_split=0.2)

print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')

num_classes = np.max(y_train) + 1
print(num_classes, 'classes')

print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

print('Convert class vector to binary class matrix '
      '(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)

print('Building model...')
model = Sequential()
model.add(Dense(512, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

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


# # Start Training Run

with mlflow.start_run():
    history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_split=0.1)
    score = model.evaluate(x_test, y_test,
                       batch_size=batch_size, verbose=1)
    print('Test score:', score[0])
    print('Test accuracy:', score[1])