satishgunjal

probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)
# 'predictions' will contain the prediction for each image in the training set. Lets check the first prediction
predictions[0]

satishgunjal

test_loss, test_acc = model.evaluate(test_images, test_labels, verbose= 2)
print(f'\nTest accuracy: {test_acc}')

satishgunjal

%%timeit -n1 -r1 # time required toexecute this cell once

# To view in TensorBoard
logdir = os.path.join("logs/adam", datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)

model.fit(train_images, train_labels, epochs= 10, callbacks = [tensorboard_callback])

satishgunjal

# The from_logits=True attribute inform the loss function that the output values generated by the model are not normalized, a.k.a. logits.
# Since softmax layer is not being added at the last layer, hence we need to have the from_logits=True to indicate the probabilities are not normalized.

model.compile(optimizer= 'adam', 
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics = ['accuracy'])

satishgunjal

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

satishgunjal

train_images = train_images / 255.0
test_images = test_images / 255.0

satishgunjal

# Display the first 25 images from the training set and display the class name below each image.
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()

satishgunjal

# Images labels(classes) possible values from 0 to 9
train_labels

satishgunjal

plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()

satishgunjal

# The images are 28x28 NumPy arrays, with pixel values ranging from 0 to 255
train_images