TensorFlow 2.0 tutorial, this section depth study and practice begins
1. Obtain data set Fashion MNIST
This guide uses Fashion MNIST data set, the data set contains 70,000 grayscale image 10 categories. Low-resolution image display (28 x 28 pixels) of a single piece of clothing, as follows:
Fashion MNIST designed to replace the classic MNIST data sets, typically used as computer vision, machine learning program "Hello, World".
We will use the network to train 60,000 images and 10,000 images to evaluate the accuracy of image classification of learning.
(train_images, train_labels), (test_images, test_labels) = keras.datasets.fashion_mnist.load_data()
28x28 NumPy image is an array of pixel values between 0 and 255. Tag is an array of integers ranging from 0 to 9. The apparel category corresponding to the image represented by:
Label Class
0 T-shirt/top
1 Trouser
2 Pullover
3 Dress
4 Coat
5 Sandal
6 Shirt
7 Sneaker
8 Bag
9 Ankle boot
Each image is mapped to a label. Since the class name is not included in the data set, so they are stored for use in rendering images here:
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
2. Explore Data
Let's explore the format of the data set before training models. The following shows the training set has 60,000 images, each represented as a 28 x 28 pixel:
print(train_images.shape)
print(train_labels.shape)
print(test_images.shape)
print(test_labels.shape)
(60000, 28, 28)
(60000,)
(10000, 28, 28)
(10000,)
3. Data processing
image display
plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()
train_images = train_images / 255.0
test_images = test_images / 255.0
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()
4. Network configuration
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'])
5. Training and Validation
model.fit(train_images, train_labels, epochs=5)
Epoch 1/5
60000/60000 [==============================] - 3s 58us/sample - loss: 0.4970 - accuracy: 0.8264
Epoch 2/5
60000/60000 [==============================] - 3s 43us/sample - loss: 0.3766 - accuracy: 0.8651
Epoch 3/5
60000/60000 [==============================] - 3s 42us/sample - loss: 0.3370 - accuracy: 0.8777
Epoch 4/5
60000/60000 [==============================] - 3s 42us/sample - loss: 0.3122 - accuracy: 0.8859
Epoch 5/5
60000/60000 [==============================] - 3s 42us/sample - loss: 0.2949 - accuracy: 0.8921
model.evaluate(test_images, test_labels)
[0.3623474566936493, 0.8737]
6. forecast
predictions = model.predict(test_images)
print(predictions[0])
print(np.argmax(predictions[0]))
print(test_labels[0])
[2.1831402e-05 1.0357383e-06 1.0550731e-06 1.3231372e-06 8.0873624e-06
2.6805745e-02 1.2466960e-05 1.6174167e-01 1.4259206e-04 8.1126428e-01]
9
9
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: Wuxi abortion how much money http://www.xaytsgyy.com/
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)
(1, 28, 28)
[[2.1831380e-05 1.0357381e-06 1.0550700e-06 1.3231397e-06 8.0873460e-06
2.6805779e-02 1.2466959e-05 1.6174166e-01 1.4259205e-04 8.1126422e-01]]
