0

この tflearn DCNN サンプル (画像の前処理と拡張を使用) を keras に変換しようとしています:

Tflearn サンプル:

import tflearn
from tflearn.data_utils import shuffle, to_categorical
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.estimator import regression
from tflearn.data_preprocessing import ImagePreprocessing
from tflearn.data_augmentation import ImageAugmentation

# Data loading and preprocessing
from tflearn.datasets import cifar10
(X, Y), (X_test, Y_test) = cifar10.load_data()
X, Y = shuffle(X, Y)
Y = to_categorical(Y, 10)
Y_test = to_categorical(Y_test, 10)

# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()

# Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)

# Convolutional network building
network = input_data(shape=[None, 32, 32, 3],
                     data_preprocessing=img_prep,
                     data_augmentation=img_aug)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 10, activation='softmax')
network = regression(network, optimizer='adam',
                     loss='categorical_crossentropy',
                     learning_rate=0.001)

# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit(X, Y, n_epoch=50, shuffle=True, validation_set=(X_test, Y_test),
          show_metric=True, batch_size=96, run_id='cifar10_cnn')

これにより、50 エポック後に次の結果が得られました。

Training Step: 26050  | total loss: 0.35260 | time: 144.306s
| Adam | epoch: 050 | loss: 0.35260 - acc: 0.8785 | val_loss: 0.64622 - val_acc: 0.8212 -- iter: 50000/50000

次に、同じ DCNN レイヤー、パラメーター、および画像の前処理/増強を使用して、Keras に変換しようとしました。

import numpy as np
from keras.datasets import cifar10
from keras.callbacks import TensorBoard
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, AveragePooling2D, UpSampling2D, AtrousConvolution2D
from keras.layers.advanced_activations import LeakyReLU, PReLU
from keras.utils import np_utils
from keras.preprocessing.image import ImageDataGenerator
from keras import backend as K
import matplotlib
from matplotlib import pyplot as plt

np.random.seed(1337)

batch_size = 96 # how many images to process at once
nb_classes = 10 # how many types of objects we can detect in this set
nb_epoch = 50 # how long we train the system
img_rows, img_cols = 32, 32 # image dimensions
nb_filters = 32 # number of convolutional filters to use
pool_size = (2, 2) # size of pooling area for max pooling
kernel_size = (3, 3) # convolution kernel size

(X_train, Y_train), (X_test, Y_test) = cifar10.load_data()
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 3)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 3)
input_shape = (img_rows, img_cols, 3)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
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
Y_train = np_utils.to_categorical(Y_train, nb_classes)
Y_test = np_utils.to_categorical(Y_test, nb_classes)

datagen = ImageDataGenerator(featurewise_center=True,
                             featurewise_std_normalization=True,
                             horizontal_flip=True,
                             rotation_range=25)
datagen.fit(X_train)

model = Sequential()
model.add(Conv2D(nb_filters, kernel_size, padding='valid', input_shape=input_shape, activation='relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Conv2D(nb_filters*2, kernel_size, activation='relu'))
model.add(Conv2D(nb_filters*2, kernel_size, activation='relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes, activation='softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

# Set up TensorBoard
tb = TensorBoard(log_dir='./logs')

history = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size), epochs=nb_epoch, shuffle=True, verbose=1, validation_data=(X_test, Y_test), callbacks=[tb])
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print("Accuracy: %.2f%%" % (score[1]*100))

plt.plot(history.epoch,history.history['val_acc'],'-o',label='validation')
plt.plot(history.epoch,history.history['acc'],'-o',label='training')
plt.legend(loc=0)
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.grid(True)
plt.show()

これにより、検証精度が大幅に低下しました。

Epoch 50/50
521/521 [==============================] - 84s 162ms/step - loss: 0.4723 - acc: 0.8340 - val_loss: 3.2970 - val_acc: 0.2729
Test score: 3.2969648239135743
Accuracy: 27.29%

誰かが理由を理解するのを手伝ってくれますか? Keras での画像の前処理/増強を誤って適用/誤解しましたか?

4

1 に答える 1