# ML CNN
## Tips for deep learning
before starting CNN...
- relu
- adam
- early stopping, overfit, validation
- regularization
- dropout
- ensemble

## CNN
### Model
- VGG16/VGG19
- AlexNet

### Data
- [dog and cat on kaggle](https://www.kaggle.com/c/dogs-vs-cats/data)
- or keras dataset

import keras
from keras.datasets import cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()

### Start Coding

#!/usr/bin/env python3
import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
import os
import numpy as np

batch_size = 32
num_classes = 10
epochs = 10
data_augmentation = True
num_predictions = 20
save_dir = os.path.join(os.getcwd(), 'saved_models')
model_name = 'keras_cifar10_trained_model.h5'


# The data, split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# Convert class vectors to binary class matrices.
# To one hot encoding
print('One hot encoding')
print(y_train.shape)
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print(y_train.shape)

# Build model
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
                 input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])
print(model.summary())

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          validation_data=(x_test, y_test),
          shuffle=True)

# Save model and weights
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

# load
# from keras.models import load_model
# model = load_model('my_model.h5')

# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])

y = model.predict(x_test)
np.save('y.npy', y)

# show image
import matplotlib.pyplot as plt
plt.imshow(x_train[1])
fig = plt.gcf()
fig.savefig('out.png')
plt.show()

## Reference
[Hung-yi Lee](http://speech.ee.ntu.edu.tw/~tlkagk/courses_ML17_2.html)
[Keras Documentation](https://keras.io/)
[devdocs](https://devdocs.io/)
[Building powerful image classification models using very little data](https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html)
[cifar10_cnn.py](https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py)