텐서플로우 - 꽃 이미지 맞추기

from shutil import ExecError
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf

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

# 데이터세트 다운로드 및 탐색하기
import pathlib
dataset_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz"
data_dir = tf.keras.utils.get_file('flower_photos', origin=dataset_url, untar=True)
data_dir = pathlib.Path(data_dir)

print(data_dir)

image_count = len(list(data_dir.glob('*/*.jpg')))
print(image_count)


# 데이터세트 만들기

batch_size = 32
img_height = 180
img_width = 180

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)


val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)
  


# 모델 만들기

class_names = train_ds.class_names
print(class_names)

num_classes = 5

model = Sequential([
  layers.experimental.preprocessing.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])


# 모델 컴파일하기

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


# 모델 훈련하기

epochs=10
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)



# 데이터 증강

data_augmentation = keras.Sequential(
  [
    layers.experimental.preprocessing.RandomFlip("horizontal", 
                                                 input_shape=(img_height, 
                                                              img_width,
                                                              3)),
    layers.experimental.preprocessing.RandomRotation(0.1),
    layers.experimental.preprocessing.RandomZoom(0.1),
  ]
)


# 새로운 데이터로 예측하기

while True:

    try:
        flower_url = input('이미지 URL 입력: ') # "https://storage.googleapis.com/download.tensorflow.org/example_images/592px-Red_sunflower.jpg"
        flower_path = tf.keras.utils.get_file('flower', origin=flower_url)

        img = keras.preprocessing.image.load_img(
            flower_path, target_size=(img_height, img_width)
        )
        img_array = keras.preprocessing.image.img_to_array(img)
        img_array = tf.expand_dims(img_array, 0) # Create a batch

        predictions = model.predict(img_array)
        score = tf.nn.softmax(predictions[0])

        print(
            "This image most likely belongs to {} with a {:.2f} percent confidence."
            .format(class_names[np.argmax(score)], 100 * np.max(score))
        )

        os.system('del ' + flower_path)

    except Exception as e:
        print('예외 오류: ', e)

 

문서: 

https://www.tensorflow.org/tutorials/images/classification?hl=ko#%EA%B3%BC%EB%8C%80%EC%A0%81%ED%95%A9 

이미지 분류  |  TensorFlow Core