パラメータチューニング
前回は全結合層の３層のパラメータ探索を行いました。
今回はその結果を用いて交差検証を行った結果、41.25% (+/- 35.04%)と今まで行ってきたモデルより精度が低い結果となってしまいました。
lossも十分に下がりきっておらず、これにより全結合層2層のモデルの方が良いということとなったため、
iphone等で撮影した画像を用いて、実用可能かを検証したいと思います。
ソースコードは以下に示します(VGG19_cross3.py)。
python:VGG19_cross3.py
import keras
import numpy as np
import matplotlib.pyplot as plt
import os
import re
import csv
import tensorflow as tf
from sklearn.model_selection import KFold
from keras.utils import np_utils
from keras.models import Sequential, Model
from keras.layers import Input, Conv2D, MaxPooling2D, Dense, Dropout, Activation, Flatten
from keras.preprocessing.image import array_to_img, img_to_array, load_img
from keras.applications import ResNet50, VGG19
from keras.callbacks import ModelCheckpoint, EarlyStopping
from keras import optimizers
from sklearn.model_selection import train_test_split
from keras.backend import tensorflow_backend
def list_pictures(directory, ext='jpg|jpeg|bmp|png|ppm'):
return [os.path.join(root, f)
for root, _, files in os.walk(directory) for f in files
if re.match(r'([\w]+\.(?:' + ext + '))', f.lower())]
X = []
Y = np.zeros((1000,3))
Y_pre = []
hidden_neurons1 = 3100
hidden_neurons2 = 4500
hidden_neurons3 = 1000
out_neurons = 3
batch_size = 8
nb_epochs = 200
fold_num = 5
es = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1, mode='auto')
picture_name = []
path = './test_dataset/'
for picture in list_pictures(path):
picture_name.append(float(picture[picture.find(path)+len(path):picture.find('_0_')]))
img = img_to_array(load_img(picture, target_size=(224,224)))
X.append(img)
with open('DB.csv',encoding="utf-8_sig") as f:
for row in csv.reader(f, quoting=csv.QUOTE_NONNUMERIC):
Y_pre.append(row)
Y_pre = np.array(Y_pre)
for i,name in enumerate(picture_name):
Y[i,:]=Y_pre[np.where(Y_pre==name)[0],1:4]
X = np.asarray(X)
X = X / 255.0
print(X.shape)
print(Y.shape)
x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=0, shuffle=False)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)
kf = KFold(n_splits=fold_num, random_state = 71, shuffle=False)
cvscores = []
count = 0
for train, test in kf.split(x_train):
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
session = tf.Session(config=config)
tensorflow_backend.set_session(session)
input_tensor = Input(shape=(224, 224, 3))
resnet50 = VGG19(include_top=False, weights='imagenet', input_tensor=input_tensor)
modelCheckpoint = ModelCheckpoint(filepath = 'Checkpoint_'+ str(count) +'.h5',
monitor='val_loss',
verbose=1,
save_best_only=True,
save_weights_only=False,
mode='min',
period=1)
top_model = Sequential()
top_model.add(Flatten(input_shape=resnet50.output_shape[1:]))
top_model.add(Dropout(0.2))
top_model.add(Dense(hidden_neurons1))
top_model.add(Activation("sigmoid"))
top_model.add(Dropout(0.2))
top_model.add(Dense(hidden_neurons2))
top_model.add(Activation("sigmoid"))
top_model.add(Dropout(0.2))
top_model.add(Dense(hidden_neurons3))
top_model.add(Activation("sigmoid"))
top_model.add(Dropout(0.2))
top_model.add(Dense(out_neurons))
top_model.add(Activation("linear"))
#top_model.summary()
model = Model(input=resnet50.input, output=top_model(resnet50.output))
model.compile(loss="mean_squared_error", metrics = ['accuracy'], optimizer=optimizers.SGD(lr=0.0001))
#model.summary()
result = model.fit(x_train[train],
y_train[train],
batch_size=batch_size,
epochs=nb_epochs,
verbose=1,
validation_data=(x_train[test], y_train[test]),
shuffle=True,
callbacks=[modelCheckpoint,es])
model.load_weights('Checkpoint_'+ str(count) +'.h5')
scores = model.evaluate(x_train[test], y_train[test], verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
cvscores.append(scores[1] * 100)
result.history.keys() # ヒストリデータのラベルを見てみる]
ep =len(result.history['acc'])
plt.figure()
plt.plot(range(1, ep+1), result.history['acc'], label="training")
plt.plot(range(1, ep+1), result.history['val_acc'], label="validation")
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.savefig('acc_'+str(count)+'.png')
plt.figure()
plt.plot(range(1, ep+1), result.history['loss'], label="training")
plt.plot(range(1, ep+1), result.history['val_loss'], label="validation")
plt.xlabel('Epochs')
plt.ylabel('loss')
plt.legend()
plt.savefig('loss_'+str(count)+'.png')
print("%.2f%% (+/- %.2f%%)" % (np.mean(cvscores), np.std(cvscores)))
可視化
model.summary()
evascores=[]
# モデル評価
for eva in range(1,6):
#print(eva)
model.load_weights('Checkpoint_'+ str(eva) +'.h5')
loss, accuracy = model.evaluate(x_test, y_test, verbose=0)
evascores.append(scores[1] * 100)
print("%.2f%% (+/- %.2f%%)" % (np.mean(evascores), np.std(evascores)))
print("end of script")
テスト用画像の収集
テスト用の画像として、家電をiPhone 7 Plusで撮影したものを7枚用意しました。
撮影した画像は以下の図1です。
それぞれ冷蔵庫、電子レンジ、空気清浄機、洗濯機です。
この寸法（幅x奥行x高さ） [mm]はそれぞれ685x633x1828、525x460x435、405x337x687、639x722x1021です。
それをプログラムで扱いやすいように、DB_test.csvに格納しています。
評価用モデルの作成
今までのデータセットをすべて学習して、新しい画像を用いて評価をするプログラムを作成しました。
これを使用すると、現在取得している画像から算出される値で大まかな精度評価が可能です。
学習速度やdropout、バッチサイズ等の細かな調整を行いながら学習を進めていった結果、未学習データに対してloss：0.05868486687541008、acc：1.0と非常に高いスコアを示しました。
loss及びaccカーブを以下に示します。
この結果から、まだ適応段階であると言えます。
今回は200epochsまでの設定だったため、このような結果となってしまいました。
次回はepoch数を1000に上げて再学習し、これに引き続き別の大型家電や別角度でトライして、このモデルのロバスト性を評価したいと思います。
ソースコードは以下に示します(VGG19_evaluation.py)。
python:VGG19_evaluation.py
import keras
import numpy as np
import matplotlib.pyplot as plt
import os
import re
import csv
import tensorflow as tf
from sklearn.model_selection import KFold
from keras.utils import np_utils
from keras.models import Sequential, Model
from keras.layers import Input, Conv2D, MaxPooling2D, Dense, Dropout, Activation, Flatten
from keras.preprocessing.image import array_to_img, img_to_array, load_img
from keras.applications import ResNet50, VGG19
from keras.callbacks import ModelCheckpoint, EarlyStopping
from keras import optimizers
from sklearn.model_selection import train_test_split
from keras.backend import tensorflow_backend
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
session = tf.Session(config=config)
tensorflow_backend.set_session(session)
def list_pictures(directory, ext='jpg|jpeg|bmp|png|ppm'):
return [os.path.join(root, f)
for root, _, files in os.walk(directory) for f in files
if re.match(r'([\w]+\.(?:' + ext + '))', f.lower())]
X = []
Y = np.zeros((1000,3))
Y_pre = []
hidden_neurons1 = 4000
hidden_neurons2 = 600
out_neurons = 3
batch_size = 8
nb_epochs = 200
picture_name = []
path = './test_dataset/'
for picture in list_pictures(path):
picture_name.append(float(picture[picture.find(path)+len(path):picture.find('_0_')]))
img = img_to_array(load_img(picture, target_size=(224,224)))
X.append(img)
with open('DB.csv',encoding="utf-8_sig") as f:
for row in csv.reader(f, quoting=csv.QUOTE_NONNUMERIC):
Y_pre.append(row)
Y_pre = np.array(Y_pre)
for i,name in enumerate(picture_name):
Y[i,:]=Y_pre[np.where(Y_pre==name)[0],1:4]
X = np.asarray(X)
X = X / 255.0
print(X.shape)
print(Y.shape)
x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=71, shuffle=True)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)
es = EarlyStopping(monitor='val_loss', min_delta=0, patience=20, verbose=1, mode='auto')
modelCheckpoint = ModelCheckpoint(filepath = 'Checkpoint.h5',
monitor='val_loss',
verbose=1,
save_best_only=True,
save_weights_only=False,
mode='min',
period=1)
input_tensor = Input(shape=(224, 224, 3))
resnet50 = VGG19(include_top=False, weights='imagenet', input_tensor=input_tensor)
top_model = Sequential()
top_model.add(Flatten(input_shape=resnet50.output_shape[1:]))
top_model.add(Dropout(0.5))
top_model.add(Dense(hidden_neurons1))
top_model.add(Activation("sigmoid"))
top_model.add(Dropout(0.5))
top_model.add(Dense(hidden_neurons2))
top_model.add(Activation("sigmoid"))
top_model.add(Dropout(0.5))
top_model.add(Dense(out_neurons))
top_model.add(Activation("linear"))
#top_model.summary()
model = Model(input=resnet50.input, output=top_model(resnet50.output))
model.compile(loss="mean_squared_error", metrics = ['accuracy'], optimizer=optimizers.SGD(lr=0.0001))
#model.summary()
result = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=nb_epochs,
verbose=1,
validation_data=(x_test, y_test),
shuffle=True,
callbacks=[modelCheckpoint,es])
model.load_weights('Checkpoint.h5')
scores = model.evaluate(X, Y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
result.history.keys() # ヒストリデータのラベルを見てみる]
ep =len(result.history['acc'])
plt.figure()
plt.plot(range(1, ep+1), result.history['acc'], label="training")
plt.plot(range(1, ep+1), result.history['val_acc'], label="validation")
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.savefig('acc_test.png')
plt.figure()
plt.plot(range(1, ep+1), result.history['loss'], label="training")
plt.plot(range(1, ep+1), result.history['val_loss'], label="validation")
plt.xlabel('Epochs')
plt.ylabel('loss')
plt.legend()
plt.savefig('loss_test.png')
#可視化
model.summary()
# モデル評価
print("Load test dataset")
X_test = []
Y_test = np.zeros((7,3))
Y_pre_test = []
picture_name_test = []
path = './test_dataset_test/'
for picture in list_pictures(path):
picture_name_test.append(float(picture[picture.find(path)+len(path):picture.find('.jpg')]))
img = img_to_array(load_img(picture, target_size=(224,224)))
X_test.append(img)
with open('DB_test.csv',encoding="utf-8_sig") as f:
for row in csv.reader(f, quoting=csv.QUOTE_NONNUMERIC):
Y_pre_test.append(row)
Y_pre_test = np.array(Y_pre_test)
for i,name in enumerate(picture_name_test):
Y_test[i,:]=Y_pre_test[np.where(Y_pre_test==name)[0],1:4]
X_test = np.asarray(X_test)
X_test = X_test / 255.0
model.load_weights('Checkpoint.h5')
loss, accuracy = model.evaluate(X_test, Y_test, verbose=0)
print('loss: '+str(loss)+' , acc: '+str(accuracy))
for i in range(7):
input = np.squeeze(X_test[i,:,:,:])
print(input.shape)
pred = model.predict(input, batch_size=1, verbose=0)
print(pred)
print("end of script")
