機器學習入門 Machine Learning Tutorial I: 圖像 Images
1. 手寫數字識別 Handwritten Digits Recognition
附上對應英文，有助于日后更深層次的學習；若對內容有任何疑問，歡迎留言討論 : )
內容簡介
通過訓練簡單的CNN模型 （Convolutional Neural Networks 卷積神經網絡）來識別MNIST數據集中的手寫數字，精確度高于99%。
環境準備
Python 3.6
pandas 0.24.2
tensorflow 1.13.1 / keras 2.2.4
1. 導入模塊 (Import module)
import pandas as pd
from keras import datasets, layers, models # 或 from tensorflow.keras import datasets, layers, models
2. 下載及處理MNIST數據集 (Download and prepare the MNIST dataset)
數據來源：keras.datasets.minist
training data: 60000 images, 28x28 pixels for each image
testing data: 10000 images, 28x28 pixels for each image
圖像示例：
后附數據視覺化(Data visualization)代碼
image.png
下載數據集：
(train_images, train_labels), (test_images, test_labels) = datasets.mnist.load_data()
處理數據集：
train_images = train_images.reshape((60000, 28, 28, 1))
test_images = test_images.reshape((10000, 28, 28, 1))
train_images, test_images = train_images / 255.0, test_images / 255.0 # 將像素值標準化為至0-1區間 (原為0-255)
數據視覺化（如果你想看看圖片）：
def visualize(X, label):
# Convert train datset to (num_images, img_rows, img_cols) format
X = X.reshape(X.shape[0], 28, 28)
for i in range(0, 9):
plt.subplot(330+(i+1))
plt.imshow(X[i], cmap=plt.get_cmap('gray'))
plt.title(label[i])
plt.show()
visualize(train_images, train_labels)
3. 建立模型 (Build the model)
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28,28,1)))
model.add(layers.MaxPool2D(2, 2))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPool2D(2, 2))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
4. 編譯及訓練模型 (Compile and train the model)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5)
5. 評估模型 (Evaluate the model)
test_loss, test_acc = model.evaluate(test_images, test_labels)
print("Test Accuracy: ", test_acc)
準確率 Accuracy: 99.16%
image.png
6. 輸出預測結果 (Output the predictions)
predictions = model.predict_classes(test_images, verbose=0)
submissions=pd.DataFrame({"ImageId": list(range(1,len(predictions)+1)),
"Label": predictions})
submissions.to_csv("predictions_cnn.csv", index=False, header=True)
即可在當前文件夾中看到predictions_cnn.csv文件，內含預測結果。
學習自：https://www.tensorflow.org/beta/tutorials/images/intro_to_cnns
