【TF 2.0-NN】データを所定の割合でランダムに訓練セット、検証セットに分割

【例】猫犬データセットを例に

import os
import zipfile
import random
from shutil import copyfile

'''
!wget --no-check-certificate \
    "https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip" \
    -O "/tmp/cats-and-dogs.zip"
'''

local_zip = '/tmp/cats-and-dogs.zip'
zip_ref   = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp')
zip_ref.close()


try:
    os.mkdir('/tmp/cats-v-dogs')
    os.mkdir('/tmp/cats-v-dogs/training')
    os.mkdir('/tmp/cats-v-dogs/testing')
    os.mkdir('/tmp/cats-v-dogs/training/cats')
    os.mkdir('/tmp/cats-v-dogs/training/dogs')
    os.mkdir('/tmp/cats-v-dogs/testing/cats')
    os.mkdir('/tmp/cats-v-dogs/testing/dogs')
except OSError:
    pass

def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):
    files = []
    for filename in os.listdir(SOURCE):
        file = SOURCE + filename
        if os.path.getsize(file) > 0:
            files.append(filename)
        else:
            print(filename + " is zero length, so ignoring.")

    training_length = int(len(files) * SPLIT_SIZE)
    testing_length = int(len(files) - training_length)
    shuffled_set = random.sample(files, len(files))
    training_set = shuffled_set[0:training_length]
    testing_set = shuffled_set[-testing_length:]

    for filename in training_set:
        this_file = SOURCE + filename
        destination = TRAINING + filename
        copyfile(this_file, destination)

    for filename in testing_set:
        this_file = SOURCE + filename
        destination = TESTING + filename
        copyfile(this_file, destination)


CAT_SOURCE_DIR = "/tmp/PetImages/Cat/"
TRAINING_CATS_DIR = "/tmp/cats-v-dogs/training/cats/"
TESTING_CATS_DIR = "/tmp/cats-v-dogs/testing/cats/"
DOG_SOURCE_DIR = "/tmp/PetImages/Dog/"
TRAINING_DOGS_DIR = "/tmp/cats-v-dogs/training/dogs/"
TESTING_DOGS_DIR = "/tmp/cats-v-dogs/testing/dogs/"

split_size = .9
split_data(CAT_SOURCE_DIR, TRAINING_CATS_DIR, TESTING_CATS_DIR, split_size)
split_data(DOG_SOURCE_DIR, TRAINING_DOGS_DIR, TESTING_DOGS_DIR, split_size)

【解析】
ポイントは関数split_data():

def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):
    files = []
    for filename in os.listdir(SOURCE):
        file = SOURCE + filename
        if os.path.getsize(file) > 0:
            files.append(filename)
        else:
            print(filename + " is zero length, so ignoring.")

    training_length = int(len(files) * SPLIT_SIZE)
    testing_length = int(len(files) - training_length)
    shuffled_set = random.sample(files, len(files))
    training_set = shuffled_set[0:training_length]
    testing_set = shuffled_set[-testing_length:]

    for filename in training_set:
        this_file = SOURCE + filename
        destination = TRAINING + filename
        copyfile(this_file, destination)

    for filename in testing_set:
        this_file = SOURCE + filename
        destination = TESTING + filename
        copyfile(this_file, destination)

いくつかの小さな関数の使用方法に注意してください.

from shutil import copyfile

os.listdir()

os.path.getsize

random.sample()

 
【モデル】

import tensorflow as tf
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.preprocessing.image import ImageDataGenerator


model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(16, (3, 3), activation='relu', input_shape=(150, 150, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

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


TRAINING_DIR = "/tmp/cats-v-dogs/training/"
train_datagen = ImageDataGenerator(rescale=1.0/255.)
train_generator = train_datagen.flow_from_directory(TRAINING_DIR,
                                                    batch_size=100,
                                                    class_mode='binary',
                                                    target_size=(150, 150))

VALIDATION_DIR = "/tmp/cats-v-dogs/testing/"
validation_datagen = ImageDataGenerator(rescale=1.0/255.)
validation_generator = validation_datagen.flow_from_directory(VALIDATION_DIR,
                                                              batch_size=100,
                                                              class_mode='binary',
                                                              target_size=(150, 150))

# Note that this may take some time.
history = model.fit_generator(train_generator,
                              epochs=50,
                              verbose=1,
                              validation_data=validation_generator)