Completed Demo code

Fall_Demo/Demo_mnist.py

+from __future__ import absolute_import, division, print_function
+import tensorflow as tf
+from tensorflow import keras
+import numpy as np
+import matplotlib.pyplot as plt
+import serial
+import time
+
+ser = serial.Serial( # Setup the serial port
+    port='/dev/ttyACM0',
+    baudrate=19200,
+    parity=serial.PARITY_ODD,
+    stopbits=serial.STOPBITS_TWO,
+    bytesize=serial.SEVENBITS
+)
+
+mnist = keras.datasets.mnist
+(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
+train_images = train_images / 255.0
+test_images = test_images / 255.0
+plt.rcParams['interactive'] == True
+class_names = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
+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()
+
+
+new_model = keras.models.load_model('MNIST_model.h5') # Load in the trained model.
+print(new_model.summary())
+new_model.compile(optimizer=tf.train.AdamOptimizer(), 
+    	          loss='sparse_categorical_crossentropy',
+        	      metrics=['accuracy'])
+
+loss, acc = new_model.evaluate(test_images, test_labels)
+print("Restored model, accuracy: {:5.2f}%".format(100*acc))
+
+predictions = new_model.predict(test_images)
+
+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()
+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)
+# Single image testing
+img = test_images[0]
+print(img.shape)
+img = (np.expand_dims(img,0))
+print(img.shape)
+predictions_single = new_model.predict(img)
+print(predictions_single)
+print(np.argmax(predictions_single[0]))
+for i in range(0,len(test_images)):
+  img = test_images[i]
+  img = (np.expand_dims(img,0))
+  predictions_single = new_model.predict(img)
+  predict = int(np.argmax(predictions_single[0]))
+  time.sleep(2)
+  print(predict)
+  ser.write(b'%d' % predict)
\ No newline at end of file

Fall_Demo/Demo_training_mnist.py

+from __future__ import absolute_import, division, print_function
+import tensorflow as tf
+from tensorflow import keras
+import numpy as np
+import os
+mnist = keras.datasets.mnist
+(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
+train_images = train_images / 255.0
+test_images = test_images / 255.0
+
+def create_model():
+	model = keras.Sequential([
+    	keras.layers.Flatten(input_shape=(28, 28)), #Transforms the format of the images from a 2d-array (of 28 by 28 pixels), to a 1d-array of 28 * 28 = 784 pixels
+    	keras.layers.Dense(128, activation=tf.nn.relu), #This is the fully connected layers
+    	keras.layers.Dense(10, activation=tf.nn.softmax) #Output layer
+	])
+	model.compile(optimizer=tf.train.AdamOptimizer(), 
+    	          loss='sparse_categorical_crossentropy',
+        	      metrics=['accuracy'])
+	return model
+
+
+model = create_model()
+
+
+model.fit(train_images, train_labels,  epochs = 5)
+model.save('MNIST_model.h5')
+
+new_model = keras.models.load_model('MNIST_model.h5')
+print("Original model summary:")
+print(model.summary())
+print("New model summary:")
+print(new_model.summary())
+new_model.compile(optimizer=tf.train.AdamOptimizer(), 
+    	          loss='sparse_categorical_crossentropy',
+        	      metrics=['accuracy'])
+
+loss, acc = model.evaluate(test_images, test_labels)
+print("Restored model, accuracy: {:5.2f}%".format(100*acc))
+
+loss, acc = new_model.evaluate(test_images, test_labels)
+print("Restored model, accuracy: {:5.2f}%".format(100*acc))
\ No newline at end of file