#!/usr/bin/env python
# coding: utf-8

# # 케라스로 중간 깊이 신경망 만들기

# 이 노트북에서 지금까지 다룬 이론을 적용해 [얕은 신경망](https://github.com/the-deep-learners/deep-learning-illustrated/blob/master/notebooks/5-1.shallow_net_in_keras.ipynb)을 발전시켜 보겠습니다.

# [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/rickiepark/dl-illustrated/blob/master/notebooks/8-4.intermediate_net_in_keras.ipynb)

# #### 라이브러리를 적재합니다.

# In[1]:


from tensorflow import keras
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import SGD


# #### 데이터를 적재합니다.

# In[2]:


(X_train, y_train), (X_valid, y_valid) = mnist.load_data()


# #### 데이터를 전처리합니다.

# In[3]:


X_train = X_train.reshape(60000, 784).astype('float32')
X_valid = X_valid.reshape(10000, 784).astype('float32')


# In[4]:


X_train /= 255
X_valid /= 255


# In[5]:


n_classes = 10
y_train = keras.utils.to_categorical(y_train, n_classes)
y_valid = keras.utils.to_categorical(y_valid, n_classes)


# #### 신경망을 만듭니다.

# In[6]:


model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,)))
model.add(Dense(64, activation='relu'))
model.add(Dense(10, activation='softmax'))


# In[7]:


model.summary()


# #### 모델을 컴파일합니다.

# In[8]:


model.compile(loss='categorical_crossentropy', optimizer=SGD(learning_rate=0.1), metrics=['accuracy'])


# #### 훈련!

# In[9]:


model.fit(X_train, y_train, batch_size=128, epochs=20, verbose=1, validation_data=(X_valid, y_valid))