#（1）下載數據的壓縮檔
#1-1:訓練所需的數據
!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/rps.zip \
    -O /tmp/rps.zip
#1-2:測試與驗證所需的數據  
!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/rps-test-set.zip \
    -O /tmp/rps-test-set.zip

#（2）解壓缩下載的檔案
import os
import zipfile

local_zip = '/tmp/rps.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp/')
zip_ref.close()

local_zip = '/tmp/rps-test-set.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp/')
zip_ref.close()

#（3）解壓縮產生的目錄：images-Training-Rock, Paper, Scissors
rock_dir = os.path.join('/tmp/rps/rock')
paper_dir = os.path.join('/tmp/rps/paper')
scissors_dir = os.path.join('/tmp/rps/scissors')

print('total training rock images:', len(os.listdir(rock_dir)))
print('total training paper images:', len(os.listdir(paper_dir)))
print('total training scissors images:', len(os.listdir(scissors_dir)))

rock_files = os.listdir(rock_dir)
print(rock_files[:10])

paper_files = os.listdir(paper_dir)
print(paper_files[:10])

scissors_files = os.listdir(scissors_dir)
print(scissors_files[:10])

#（4）在上面這些資料夾裡面創建『學習用，預測用』的圖片與標註
#4-1.目的：把下載的檔案，用ImageDataGenerator()指令，重新創建出模型學習時，所需的圖片
import tensorflow as tf
import keras_preprocessing
from keras_preprocessing import image
from keras_preprocessing.image import ImageDataGenerator

TRAINING_DIR = "/tmp/rps/"
training_datagen = ImageDataGenerator(
      rescale = 1./255,
	    rotation_range=40,
      width_shift_range=0.2,
      height_shift_range=0.2,
      shear_range=0.2,
      zoom_range=0.2,
      horizontal_flip=True,
      fill_mode='nearest')

train_generator = training_datagen.flow_from_directory(
	TRAINING_DIR,
	target_size=(150,150),
	class_mode='categorical',
  batch_size=126
)

#4-2.目的：把下載的檔案，用ImageDataGenerator()指令，重新創建出模型『測試驗證』時，所需的圖片
VALIDATION_DIR = "/tmp/rps-test-set/"
validation_datagen = ImageDataGenerator(rescale = 1./255)

validation_generator = validation_datagen.flow_from_directory(
	VALIDATION_DIR,
	target_size=(150,150),
	class_mode='categorical',
  batch_size=126
)

#（5）建立卷積神經網絡模型
#為什麼要建立4層的卷積神經層：因為數據較複雜（圖片比較大(150x150)，顏色比較多（黑人，白人，黃種人））
model = tf.keras.models.Sequential([
    # Note the input shape is the desired size of the image 150x150 with 3 bytes color
    # This is the first convolution
    tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(150, 150, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    # The second convolution
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    # The third convolution
    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    # The fourth convolution
    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    # Flatten the results to feed into a DNN
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dropout(0.5),
    # 512 neuron hidden layer
    tf.keras.layers.Dense(512, activation='relu'),
    #最後輸出成：1層，三個神經元的網絡（輸出的答案有三種）
    tf.keras.layers.Dense(3, activation='softmax')    
])
model.summary()

#（6）編譯神經網絡模型（設定：loss，optimizer，metrics）
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

#（7）總共做25回，來從訓練數據test_generator，來訓練學習
history = model.fit(train_generator, epochs=25, steps_per_epoch=20, validation_data = validation_generator, verbose = 1, validation_steps=3)

model.save("rps.h5")

#（8）把訓練過程的準確率accuracy，畫成曲線圖
import matplotlib.pyplot as plt
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(len(acc))

plt.plot(epochs, acc, 'r', label='Training accuracy')
plt.plot(epochs, val_acc, 'b', label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.legend(loc=0)
plt.figure()

plt.show()

#（9）給一個測試x數據(validation_generator[0])，預測其石頭剪刀布的編號（pred_classifications[0]）
#編號的順序=（布，石頭，剪刀），例如：布=(1,0,0),石頭=（0，1，0),剪刀=（0，0，1)
pred_classifications = model.predict(validation_generator)
print('對第1個測試樣品的預測（石頭剪刀布？）=', pred_classifications[0])

#使用np.argmax()函數：傳回最大值索引號
import numpy as np
print("預測：第1個測試數據train_generator[0]的所預測的石頭剪刀布編號=", np.argmax(pred_classifications[0]))