CNN(Convolutional Neural Network)-CIFAR 10_Functional API Modeling

CIFAR 10 - Functional API Modeling

Categorical Classification

1. CIFAR 10 Data_Set Load & Review

1-1. Load CIFAR 10 Data_Set

import tensorflow
from tensorflow.keras.datasets import cifar10

(X_train, y_train), (X_test, y_test) = cifar10.load_data()

print(len(X_train))
print(X_train.shape)

print(len(y_train))
print(y_train[0:5])

print(len(X_test))
print(X_test.shape)

print(len(y_test))
print(y_test[0:5])

---

2. Data Preprocessing

2-1. Normalization

X_train = X_train.astype(float) / 255
X_test = X_test.astype(float) / 255

print(X_train[0])

---

2-2. One Hot Encoding

from tensorflow.keras.utils import to_categorical

y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

print(y_train[:5])

---

3. Keras Functional API Modeling

3-1. Model Define

%%time

from tensorflow.keras import models
from tensorflow.keras import layers

input_img = layers.Input((32,32,3))

x = layers.Conv2D(filters=32, kernel_size=(3,3), strides=(1,1), padding='same')(input_img)
x = layers.BatchNormalization()(x)
x = layers.LeakyReLU()(x)


x = layers.Conv2D(filters=32, kernel_size=(3,3), strides=(2,2), padding='same')(x)
x = layers.BatchNormalization()(x)
x = layers.LeakyReLU()(x)


x = layers.Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='same')(x)
x = layers.BatchNormalization()(x)
x = layers.LeakyReLU()(x)


x = layers.Conv2D(filters=64, kernel_size=(3,3), strides=(2,2), padding='same')(x)
x = layers.BatchNormalization()(x)
x = layers.LeakyReLU()(x)


x = layers.Flatten()(x)

x = layers.Dense(128)(x)
x = layers.BatchNormalization()(x)
x = layers.LeakyReLU()(x)
x = layers.Dropout(0.5)(x)

x = layers.Dense(10)(x)
output_y_hat = layers.Activation('softmax')(x)

CIFAR = models.Model(input_img, output_y_hat)

CIFAR.summary()

---

2-2. Model Compile

CIFAR.compile(loss = 'categorical_crossentropy',
              optimizer = 'adam',
              metrics = ['accuracy'])

---

2-3. Model Fit

%%time

Hist_CIFAR = CIFAR.fit(X_train, y_train,
                       epochs = 100,
                       batch_size = 128,
                       validation_split = 0.2)

---

2-4. 학습 결과 시각화

import matplotlib.pyplot as plt

epochs = range(1, len(Hist_CIFAR.history['loss']) + 1)

plt.figure(figsize = (9, 6))
plt.plot(epochs, Hist_CIFAR.history['loss'])
plt.plot(epochs, Hist_CIFAR.history['val_loss'])
# plt.ylim(0, 0.25)
plt.title('Training & Validation Loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend(['Training Loss', 'Validation Loss'])
plt.grid()
plt.show()

---

2-5. Model Evaluate

loss, accuracy = CIFAR.evaluate(X_test, y_test)

print('Loss = {:.5f}'.format(loss))
print('Accuracy = {:.5f}'.format(accuracy))

---

3. 성능평가

3-1. Label Name 지정

import numpy as np

CLASSES = np.array(['Airplane', 'Automobile', 'Bird', 'Cat', 'Deer', 
                    'Dog', 'Frog', 'Horse', 'Ship', 'Truck'])

preds = CIFAR.predict(X_test)
preds_single = CLASSES[np.argmax(preds, axis = -1)]
actual_single = CLASSES[np.argmax(y_test, axis = -1)]

---

3-2. 비교 시각화

import matplotlib.pyplot as plt

n_to_show = 10
indices = np.random.choice(range(len(X_test)), n_to_show)

fig = plt.figure(figsize = (15, 3))
fig.subplots_adjust(hspace = 0.4, wspace = 0.4)

for i, idx in enumerate(indices):
    img = X_test[idx]
    ax = fig.add_subplot(1, n_to_show, i + 1)
    ax.axis('off')
    ax.text(0.5, -0.35, 
            'Pred = ' + str(preds_single[idx]), 
            fontsize = 10, 
            ha = 'center', 
            transform = ax.transAxes) 
    ax.text(0.5, -0.7, 
            'Act = ' + str(actual_single[idx]), 
            fontsize = 10, 
            ha = 'center', 
            transform = ax.transAxes)
    ax.imshow(img)