[INTRODUCTION TO TENSORFLOW FOR ARTIFICIAL INTELLIGENCE, MACHINE LEARNING, AND DEEP LEARNING] Handling Complex Images

코세라의   deeplearning.AI tensorflow developer 전문가 자격증 과정내에

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

과정의 4주차 Using Real-world Images

챕터의 코드 예제입니다.

 

Handling Complex Images

1) Happy or Sad image dataset를 받는다

2) myCallback함수에 traing accuracy가 99.9%이상이되면 훈련을 멈추도록 구현한다.

3) Conv2D를 이용한 네트워크를 구성한다.

4) preprocessing.image name space의  ImageDataGenerator를 이용해서, 밝기를 1/255로 정규화한다

5) flow_from_directory method를 이용해서, training data가 있는 디렉토리를 설정하고, target image size와 class mode, batch size를 설정한다.

6) fit_generator를 이용해서 모델을 훈련한다.

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

# Below is code with a link to a happy or sad dataset which contains 80 images, 40 happy and 40 sad. 
# Create a convolutional neural network that trains to 100% accuracy on these images,  which cancels training upon hitting training accuracy of >.999
# 
# Hint -- it will work best with 3 convolutional layers.

# In[ ]:


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

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

zip_ref = zipfile.ZipFile(path, 'r')
zip_ref.extractall("/tmp/h-or-s")
zip_ref.close()


# In[ ]:


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

    DESIRED_ACCURACY = 0.999


    class myCallback(tf.keras.callbacks.Callback):
      def on_epoch_end(self, epoch, logs={}):
        if(logs.get('acc')>DESIRED_ACCURACY):
          print("\nReached 99.9% accuracy so cancelling training!")
          self.model.stop_training = True

    callbacks = myCallback()
    
    # This Code Block should Define and Compile the Model. Please assume the images are 150 X 150 in your implementation.
    model = tf.keras.models.Sequential([
        # Your Code Here
        tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(150, 150, 3)),
        tf.keras.layers.MaxPooling2D(2, 2),
        # The second convolution
        tf.keras.layers.Conv2D(32, (3,3), activation='relu'),
        tf.keras.layers.MaxPooling2D(2,2),
        # The third convolution
        tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
        tf.keras.layers.MaxPooling2D(2,2),
        # Flatten the results to feed into a DNN
        tf.keras.layers.Flatten(),
        # 512 neuron hidden layer
        tf.keras.layers.Dense(512, activation='relu'),
        # Only 1 output neuron. It will contain a value from 0-1 where 0 for 1 class ('horses') and 1 for the other ('humans')
        tf.keras.layers.Dense(1, activation='sigmoid')
    ])

    from tensorflow.keras.optimizers import RMSprop

    model.compile(loss='binary_crossentropy',
              optimizer=RMSprop(lr=0.001),
              metrics=['accuracy'])
        

    # This code block should create an instance of an ImageDataGenerator called train_datagen 
    # And a train_generator by calling train_datagen.flow_from_directory

    from tensorflow.keras.preprocessing.image import ImageDataGenerator

    train_datagen = ImageDataGenerator(rescale=1/255)

    # Please use a target_size of 150 X 150.
    train_generator = train_datagen.flow_from_directory(
        '/tmp/h-or-s/',  # This is the source directory for training images
        target_size=(150, 150),  # All images will be resized to 300x300
        batch_size=128,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')
    # Expected output: 'Found 80 images belonging to 2 classes'

    # This code block should call model.fit_generator and train for
    # a number of epochs.
    # model fitting
    history = model.fit_generator(train_generator,steps_per_epoch=8,epochs=15,verbose=1,callbacks=[callbacks])
    # model fitting
    return history.history['acc'][-1]


# In[ ]:


# The Expected output: "Reached 99.9% accuracy so cancelling training!""
train_happy_sad_model()