CNN – Images – Tensorflow/Keras – Conv2D

---

# -*- coding: utf-8 -*-
"""
Created on Wed Oct 19 09:45:05 2022

@author: profa
"""
## Image Processing Python
## https://note.nkmk.me/en/python-numpy-image-processing/

import tensorflow as tf

from tensorflow.keras import datasets, layers, models
import matplotlib.pyplot as plt

(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()

print(type(train_images))
print(train_images.shape)   ## 50000 rows, 32 by 32, depth 3
plt.imshow(train_images[2])
plt.show()

print(train_images[0,:,:,0])
print(train_images[0,:,:,0].shape)

# Normalize pixel values to be between 0 and 1
train_images, test_images = train_images / 255.0, test_images / 255.0
class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',
               'dog', 'frog', 'horse', 'ship', 'truck']

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])
    # The CIFAR labels happen to be arrays, 
    # which is why you need the extra index
    plt.xlabel(class_names[train_labels[i][0]])
plt.show()

model = models.Sequential()
## https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
#https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool2D
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))

model.summary()

model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))

model.summary()


model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              ## Using True above means you do not use one-hot-encoding
              metrics=['accuracy'])

##Increase epochs to improve accuracy/training
history = model.fit(train_images, train_labels, epochs=10, 
                    validation_data=(test_images, test_labels))


plt.plot(history.history['accuracy'], label='accuracy')
plt.plot(history.history['val_accuracy'], label = 'val_accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.ylim([0.5, 1])
plt.legend(loc='lower right')

test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)

print(test_acc)