fashion-mnist classifier to build tensorflow version

1. Daily import

from __future__ import absolute_import, division, print_function
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

import numpy as np
import matplotlib.pyplot as plt
import os
#调用GPU加速训练
os.environ['CUDA_VISIBLE_DEVICES'] = '/gpu:1'

2. Dataset loading

#查看tf版本
print(tf.__version__)
#加载数据集
(train_images, train_labels), (test_images, test_labels) = keras.datasets.fashion_mnist.load_data()

3. Dataset labeling and dataset visualization

#data label
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
#print label
print(train_images.shape)
print(train_labels.shape)
print(test_images.shape)
print(test_labels.shape)

#显示数据
plt.figure()
plt.imshow(train_images[1])
plt.colorbar()
plt.grid(False)
plt.show()

#data per
train_images = train_images / 255.0

test_images = test_images / 255.0
#display part data
plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])
plt.show()

The results are as follows


4. Model building and training test

# setup model
model = keras.Sequential(
[
    layers.Flatten(input_shape=[28, 28]),
    layers.Dense(128, activation='relu'),
    layers.Dense(10, activation='softmax')
])

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

model.fit(train_images, train_labels, epochs=5)

model.evaluate(test_images, test_labels)

predictions = model.predict(test_images)
print(predictions[0])
print(np.argmax(predictions[0]))
print(test_labels[0])


def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array[i], true_label[i], img[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, 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)
plt.show()

# 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)
plt.show()

img = test_images[0]

img = (np.expand_dims(img,0))

print(img.shape)
predictions_single = model.predict(img)

print(predictions_single)
plot_value_array(0, predictions_single, test_labels)
_ = plt.xticks(range(10), class_names, rotation=45)

The test results are as follows


5. Complete code

from __future__ import absolute_import, division, print_function
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

import numpy as np
import matplotlib.pyplot as plt
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '/gpu:1'


print(tf.__version__)

(train_images, train_labels), (test_images, test_labels) = keras.datasets.fashion_mnist.load_data()

#data label
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
#print label
print(train_images.shape)
print(train_labels.shape)
print(test_images.shape)
print(test_labels.shape)

#显示数据
plt.figure()
plt.imshow(train_images[1])
plt.colorbar()
plt.grid(False)
plt.show()

#data per
train_images = train_images / 255.0

test_images = test_images / 255.0
#display part data
plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])
plt.show()

# setup model
model = keras.Sequential(
[
    layers.Flatten(input_shape=[28, 28]),
    layers.Dense(128, activation='relu'),
    layers.Dense(10, activation='softmax')
])

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

model.fit(train_images, train_labels, epochs=5)

model.evaluate(test_images, test_labels)

predictions = model.predict(test_images)
print(predictions[0])
print(np.argmax(predictions[0]))
print(test_labels[0])


def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array[i], true_label[i], img[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, 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)
plt.show()

# 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)
plt.show()

img = test_images[0]

img = (np.expand_dims(img,0))

print(img.shape)
predictions_single = model.predict(img)

print(predictions_single)
plot_value_array(0, predictions_single, test_labels)
_ = plt.xticks(range(10), class_names, rotation=45)