mirror of
https://github.com/Azure/MachineLearningNotebooks.git
synced 2025-12-19 17:17:04 -05:00
122 lines
3.7 KiB
Python
122 lines
3.7 KiB
Python
# Copyright (c) Microsoft Corporation. All rights reserved.
|
|
# Licensed under the MIT License.
|
|
|
|
import numpy as np
|
|
import argparse
|
|
import os
|
|
|
|
import matplotlib.pyplot as plt
|
|
|
|
import keras
|
|
from keras.models import Sequential, model_from_json
|
|
from keras.layers import Dense
|
|
from keras.optimizers import RMSprop
|
|
from keras.callbacks import Callback
|
|
|
|
import tensorflow as tf
|
|
|
|
from azureml.core import Run
|
|
from utils import load_data, one_hot_encode
|
|
|
|
print("Keras version:", keras.__version__)
|
|
print("Tensorflow version:", tf.__version__)
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--data-folder', type=str, dest='data_folder', help='data folder mounting point')
|
|
parser.add_argument('--batch-size', type=int, dest='batch_size', default=50, help='mini batch size for training')
|
|
parser.add_argument('--first-layer-neurons', type=int, dest='n_hidden_1', default=100,
|
|
help='# of neurons in the first layer')
|
|
parser.add_argument('--second-layer-neurons', type=int, dest='n_hidden_2', default=100,
|
|
help='# of neurons in the second layer')
|
|
args = parser.parse_args()
|
|
|
|
data_folder = args.data_folder
|
|
|
|
print('training dataset is stored here:', data_folder)
|
|
|
|
X_train = load_data(os.path.join(data_folder, 'train-images.gz'), False) / 255.0
|
|
X_test = load_data(os.path.join(data_folder, 'test-images.gz'), False) / 255.0
|
|
|
|
y_train = load_data(os.path.join(data_folder, 'train-labels.gz'), True).reshape(-1)
|
|
y_test = load_data(os.path.join(data_folder, 'test-labels.gz'), True).reshape(-1)
|
|
|
|
training_set_size = X_train.shape[0]
|
|
|
|
n_inputs = 28 * 28
|
|
n_h1 = args.n_hidden_1
|
|
n_h2 = args.n_hidden_2
|
|
n_outputs = 10
|
|
|
|
n_epochs = 20
|
|
batch_size = args.batch_size
|
|
|
|
y_train = one_hot_encode(y_train, n_outputs)
|
|
y_test = one_hot_encode(y_test, n_outputs)
|
|
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape, sep='\n')
|
|
|
|
# Build a simple MLP model
|
|
model = Sequential()
|
|
# input layer
|
|
model.add(Dense(n_h1, activation='relu', input_shape=(n_inputs,)))
|
|
# hidden layer
|
|
model.add(Dense(n_h2, activation='relu'))
|
|
# output layer
|
|
model.add(Dense(n_outputs, activation='softmax'))
|
|
|
|
model.summary()
|
|
|
|
model.compile(loss='categorical_crossentropy',
|
|
optimizer=RMSprop(),
|
|
metrics=['accuracy'])
|
|
|
|
# start an Azure ML run
|
|
run = Run.get_context()
|
|
|
|
|
|
class LogRunMetrics(Callback):
|
|
# callback at the end of every epoch
|
|
def on_epoch_end(self, epoch, log):
|
|
# log a value repeated which creates a list
|
|
run.log('Loss', log['loss'])
|
|
run.log('Accuracy', log['acc'])
|
|
|
|
|
|
history = model.fit(X_train, y_train,
|
|
batch_size=batch_size,
|
|
epochs=n_epochs,
|
|
verbose=2,
|
|
validation_data=(X_test, y_test),
|
|
callbacks=[LogRunMetrics()])
|
|
|
|
score = model.evaluate(X_test, y_test, verbose=0)
|
|
|
|
# log a single value
|
|
run.log("Final test loss", score[0])
|
|
print('Test loss:', score[0])
|
|
|
|
run.log('Final test accuracy', score[1])
|
|
print('Test accuracy:', score[1])
|
|
|
|
plt.figure(figsize=(6, 3))
|
|
plt.title('MNIST with Keras MLP ({} epochs)'.format(n_epochs), fontsize=14)
|
|
plt.plot(history.history['acc'], 'b-', label='Accuracy', lw=4, alpha=0.5)
|
|
plt.plot(history.history['loss'], 'r--', label='Loss', lw=4, alpha=0.5)
|
|
plt.legend(fontsize=12)
|
|
plt.grid(True)
|
|
|
|
# log an image
|
|
run.log_image('Accuracy vs Loss', plot=plt)
|
|
|
|
# create a ./outputs/model folder in the compute target
|
|
# files saved in the "./outputs" folder are automatically uploaded into run history
|
|
os.makedirs('./outputs/model', exist_ok=True)
|
|
|
|
# serialize NN architecture to JSON
|
|
model_json = model.to_json()
|
|
# save model JSON
|
|
with open('./outputs/model/model.json', 'w') as f:
|
|
f.write(model_json)
|
|
# save model weights
|
|
model.save_weights('./outputs/model/model.h5')
|
|
print("model saved in ./outputs/model folder")
|