[INTRODUCTION TO TENSORFLOW FOR ARTIFICIAL INTELLIGENCE, MACHINE LEARNING, AND DEEP LEARNING] Implement a Deep Neural Network to recognize handwritten digits

코세라의   deeplearning.AI tensorflow developer 전문가 자격증 과정내에

Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning

과정의 2주차  Introduction to Computer Vision챕터의 코드 예제입니다.

 

Implement a Deep Neural Network to recognize handwritten digits

Handwriting Recognition예제

1) MNIST dataset을 이용해서 모델 학습

2) 각 픽셀의 밝기값을 225로 나눠서 정규화

3) 28x28의 2차원 픽셀 데이터를 1차원으로 flatten하여 모델에 입력되도록 함

4) dense 512개 unit뉴럴네트워크 hidden layer 구성

5) output layer class의 종류인 10개 output unit으로 구성

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

# ## Exercise 2
# In the course you learned how to do classificaiton using Fashion MNIST, a data set containing items of clothing. There's another, similar dataset called MNIST which has items of handwriting -- the digits 0 through 9.
# 
# Write an MNIST classifier that trains to 99% accuracy or above, and does it without a fixed number of epochs -- i.e. you should stop training once you reach that level of accuracy.
# 
# Some notes:
# 1. It should succeed in less than 10 epochs, so it is okay to change epochs= to 10, but nothing larger
# 2. When it reaches 99% or greater it should print out the string "Reached 99% accuracy so cancelling training!"
# 3. If you add any additional variables, make sure you use the same names as the ones used in the class
# 
# I've started the code for you below -- how would you finish it? 

# In[1]:


import tensorflow as tf
from os import path, getcwd, chdir

# DO NOT CHANGE THE LINE BELOW. If you are developing in a local
# environment, then grab mnist.npz from the Coursera Jupyter Notebook
# and place it inside a local folder and edit the path to that location
path = f"{getcwd()}/../tmp2/mnist.npz"


# In[12]:


# GRADED FUNCTION: train_mnist
def train_mnist():
    # Please write your code only where you are indicated.
    # please do not remove # model fitting inline comments.

    # YOUR CODE SHOULD START HERE
    class myCallback(tf.keras.callbacks.Callback):
      def on_epoch_end(self, epoch, logs={}):
        if((logs.get('acc')) > 0.99):
          print("\nReached 99% accuracy so cancelling training!")
          self.model.stop_training = True
    # YOUR CODE SHOULD END HERE

    mnist = tf.keras.datasets.mnist

    (x_train, y_train),(x_test, y_test) = mnist.load_data(path=path)
    # YOUR CODE SHOULD START HERE
    x_train, x_test = x_train / 255.0, x_test / 255.0
    callbacks = myCallback()
    # YOUR CODE SHOULD END HERE
    model = tf.keras.models.Sequential([
        # YOUR CODE SHOULD START HERE       
      tf.keras.layers.Flatten(input_shape=(28, 28)),
      tf.keras.layers.Dense(512, activation=tf.nn.relu),
      tf.keras.layers.Dense(10, activation=tf.nn.softmax)
        # YOUR CODE SHOULD END HERE
    ])

    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])
    
    # model fitting
    history = model.fit(x_train, y_train, epochs=10, callbacks=[callbacks])
    # model fitting
    return history.epoch, history.history['acc'][-1]


# In[13]:


train_mnist()