import tensorflow as tf
import tensorflow_datasets as tfds
tfds.disable_progress_bar()
import math
import numpy as np
import matplotlib.pyplot as plt
import logging
logger = tf.get_logger()
logger.setLevel(logging.ERROR)
dataset, metadata = tfds.load('fashion_mnist', as_supervised=True, with_info=True)
train_dataset, test_dataset = dataset['train'], dataset['test']
print(metadata)
tfds.core.DatasetInfo(
name='fashion_mnist',
full_name='fashion_mnist/3.0.1',
description="""
Fashion-MNIST is a dataset of Zalando's article images consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes.
""",
homepage='https://github.com/zalandoresearch/fashion-mnist',
data_path='/root/tensorflow_datasets/fashion_mnist/3.0.1',
download_size=29.45 MiB,
dataset_size=36.42 MiB,
features=FeaturesDict({
'image': Image(shape=(28, 28, 1), dtype=tf.uint8),
'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=10),
}),
supervised_keys=('image', 'label'),
disable_shuffling=False,
splits={
'test': <SplitInfo num_examples=10000, num_shards=1>,
'train': <SplitInfo num_examples=60000, num_shards=1>,
},
citation="""@article{DBLP:journals/corr/abs-1708-07747,
author = {Han Xiao and
Kashif Rasul and
Roland Vollgraf},
title = {Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning
Algorithms},
journal = {CoRR},
volume = {abs/1708.07747},
year = {2017},
url = {http://arxiv.org/abs/1708.07747},
archivePrefix = {arXiv},
eprint = {1708.07747},
timestamp = {Mon, 13 Aug 2018 16:47:27 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/abs-1708-07747},
bibsource = {dblp computer science bibliography, https://dblp.org}
}""",
)
class_names = metadata.features['label'].names
print("Class names: {}".format(class_names))
Class names: ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
num_train_examples = metadata.splits['train'].num_examples
num_test_examples = metadata.splits['test'].num_examples
print("Number of training examples: {}".format(num_test_examples))
print("Number of test examples: {}".format(num_test_examples))
Number of training examples: 10000
Number of test examples: 10000
def normalize(images, labels):
images = tf.cast(images, tf.float32)
images /= 255
return images, labels
train_dataset = train_dataset.map(normalize)
test_dataset = test_dataset.map(normalize)
train_dataset = train_dataset.cache()
test_dataset = test_dataset.cache()
for image, label in test_dataset.take(1):
break
image = image.numpy().reshape((28, 28))
plt.figure()
plt.imshow(image, cmap=plt.cm.binary)
plt.colorbar()
plt.grid(False)
plt.show()
plt.figure(figsize=(10, 10))
for i, (image, label) in enumerate(train_dataset.take(25)):
image = image.numpy().reshape((28, 28))
plt.subplot(5, 5, i+1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(image, cmap=plt.cm.binary)
plt.xlabel(class_names[label])
plt.show()
model = tf.keras.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
tf.keras.layers.Dense(128, activation=tf.nn.relu),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(),
metrics=['accuracy'])
BATCH_SIZE = 32
train_dataset = train_dataset.cache().repeat().shuffle(num_train_examples).batch(BATCH_SIZE)
test_dataset = test_dataset.cache().batch(BATCH_SIZE)
model.fit(train_dataset, epochs=5, steps_per_epoch=math.ceil(num_train_examples/BATCH_SIZE))
Epoch 1/5
1875/1875 [==============================] - 13s 3ms/step - loss: 0.6291 - accuracy: 0.7770
Epoch 2/5
1875/1875 [==============================] - 5s 2ms/step - loss: 0.3831 - accuracy: 0.8607
Epoch 3/5
1875/1875 [==============================] - 5s 2ms/step - loss: 0.3359 - accuracy: 0.8764
Epoch 4/5
1875/1875 [==============================] - 5s 2ms/step - loss: 0.3110 - accuracy: 0.8873
Epoch 5/5
1875/1875 [==============================] - 5s 2ms/step - loss: 0.2914 - accuracy: 0.8939
test_loss, test_accuracy = model.evaluate(test_dataset, steps=math.ceil(num_test_examples/32))
print('Accuracy on test dataset:', test_accuracy)
313/313 [==============================] - 2s 6ms/step - loss: 0.3719 - accuracy: 0.8681
Accuracy on test dataset: 0.8680999875068665
for test_images, test_labels in test_dataset.take(1):
test_images = test_images.numpy()
test_labels = test_labels.numpy()
predictions = model.predict(test_images)
predictions.shape
predictions[0]
np.argmax(predictions[0])
test_labels[0]
def plot_image(i, predictions_array, true_labels, images):
predictions_array, true_label, img = predictions_array[i], true_labels[i], images[i]
plt.grid(False)
plt.xticks([])
plt.yticks([])
plt.imshow(img[...,0], cmap=plt.cm.binary)
predicted_label = np.argmax(predictions_array)
if predicted_label == true_label:
color = 'blue'
else:
color = 'red'
plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
100*np.max(predictions_array),
class_names[true_label]),
color=color)
def plot_value_array(i, predictions_array, true_label):
predictions_array, true_label = predictions_array[i], true_label[i]
plt.grid(False)
plt.xticks([])
plt.yticks([])
thisplot = plt.bar(range(10), predictions_array, color="#777777")
plt.ylim([0, 1])
predicted_label = np.argmax(predictions_array)
thisplot[predicted_label].set_color('red')
thisplot[true_label].set_color('blue')
i = 0
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions, test_labels)
i = 12
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(1,2,2)
plot_value_array(i, predictions, test_labels)
# Plot the first X test images, their predicted label, and the true label
# Color correct predictions in blue, incorrect predictions in red
num_rows = 5
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):
plt.subplot(num_rows, 2*num_cols, 2*i+1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(num_rows, 2*num_cols, 2*i+2)
plot_value_array(i, predictions, test_labels)
img = test_images[0]
print(img.shape)
(28, 28, 1)
img = np.array([img])
print(img.shape)
(1, 28, 28, 1)
predictions_single = model.predict(img)
print(predictions_single)
[[1.5874700e-04 1.4948106e-05 3.4735918e-02 4.7313256e-06 8.8238388e-01
2.5493446e-08 8.1383839e-02 2.9755012e-10 1.3179599e-03 1.8213705e-09]]
plot_value_array(0, predictions_single, test_labels)
_ = plt.xticks(range(10), class_names, rotation=45)