텐서플로우 튜토리얼

import tensorflow as tf
from tensorflow import keras

import warnings
warnings.filterwarnings('ignore')

# Helper libraries
# numpy와 matplotlib을 사용한다.
import numpy as np
import matplotlib.pyplot as plt
# jupyter notebook에서 matplotlib을 사용하기 위한 매직커맨드
%matplotlib inline
print("사용되는 tensorflow의 버전:",tf.__version__)

사용되는 tensorflow의 버전: 2.9.1

import tensorflow.compat.v1 as tf

tf.disable_v2_behavior()

신버전 사용시 발생하는 오류 제어

fashion_mnist = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

train_labels

array([9, 0, 0, ..., 3, 0, 5], dtype=uint8)

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

train_images.shape

(60000, 28, 28)

test_images.shape

(10000, 28, 28)

# matplotlib을 통해 그림을 그린다.
plt.figure()
# train_images의 첫번째 요소를 그린다.
plt.imshow(train_images[0])
plt.colorbar()
# 점자선을 False로 둠으로써 없앤다.
plt.gca().grid(False)

train_images = train_images / 255.0
test_images = test_images / 255.0

# matplotlib을 통해 그림을 그린다.
plt.figure()
# train_images의 첫번째 요소를 그린다.
plt.imshow(train_images[0])
plt.colorbar()
# 점자선을 False로 둠으로써 없앤다.
plt.gca().grid(False)

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid('off')
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer=tf.train.AdamOptimizer(), 
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(train_images, train_labels, epochs=5)

Train on 60000 samples
Epoch 1/5
60000/60000 [==============================] - 2s 40us/sample - loss: 0.5039 - acc: 0.8234
Epoch 2/5
60000/60000 [==============================] - 3s 43us/sample - loss: 0.3801 - acc: 0.8628
Epoch 3/5
60000/60000 [==============================] - 2s 39us/sample - loss: 0.3401 - acc: 0.8767
Epoch 4/5
60000/60000 [==============================] - 2s 40us/sample - loss: 0.3163 - acc: 0.8842
Epoch 5/5
60000/60000 [==============================] - 2s 41us/sample - loss: 0.2975 - acc: 0.8910
<keras.callbacks.History at 0x1f8446a3b20>

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

print('Test accuracy:', test_acc)

Test accuracy: 0.8663

predictions = model.predict(test_images)

predictions[0]

array([1.6646754e-06, 4.6912991e-08, 1.9488364e-06, 2.4025017e-08,
6.5531931e-06, 5.9902354e-04, 1.7164682e-06, 1.0812764e-02,
2.1776802e-06, 9.8857415e-01], dtype=float32)

np.argmax(predictions[0])

9

test_labels[0]

9

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid('off')
    plt.imshow(test_images[i], cmap=plt.cm.binary)
    # predictions에서 가장 큰 값을 predicted_label 로 가져온다.
    predicted_label = np.argmax(predictions[i])
    true_label = test_labels[i]
    # 이때 실제 test_label과 일치하면 초록색 글씨로,
    if predicted_label == true_label:
      color = 'green'
    # 일치하지 않으면 빨간색 글씨로 출력한다.
    else:
      color = 'red'
    plt.xlabel("{} ({})".format(class_names[predicted_label], 
                                  class_names[true_label]),
                                  color=color)