eye_blink_detector/train.py at main · devNmin/eye_blink_detector · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
import datetime
import numpy as np
import matplotlib.pyplot as plt
from keras.layers import Input, Activation, Conv2D, Flatten, Dense, MaxPooling2D
from keras.models import Model, load_model
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
plt.style.use('dark_background')

# load dataset
x_train = np.load('dataset/x_train.npy').astype(np.float32)
y_train = np.load('dataset/y_train.npy').astype(np.float32)
x_val = np.load('dataset/x_val.npy').astype(np.float32)
y_val = np.load('dataset/y_val.npy').astype(np.float32)

print(x_train.shape, y_train.shape)
print(x_val.shape, y_val.shape)

#Preview
plt.subplot(2, 1, 1)
plt.title(str(y_train[0]))
plt.imshow(x_train[0].reshape((26, 34)), cmap='gray')
plt.subplot(2, 1, 2)
plt.title(str(y_val[4]))
plt.imshow(x_val[4].reshape((26, 34)), cmap='gray')

#data augmetation

train_datagen = ImageDataGenerator(
    rescale=1./255,
    rotation_range=10,
    width_shift_range=0.2,
    height_shift_range=0.2,
    shear_range=0.2
)

val_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow(
    x=x_train, y=y_train,
    batch_size=32,
    shuffle=True
)

val_generator = val_datagen.flow(
    x=x_val, y=y_val,
    batch_size=32,
    shuffle=False
)

#build model
inputs = Input(shape=(26, 34, 1))

net = Conv2D(32, kernel_size=3, strides=1, padding='same', activation='relu')(inputs)
net = MaxPooling2D(pool_size=2)(net)

net = Conv2D(64, kernel_size=3, strides=1, padding='same', activation='relu')(net)
net = MaxPooling2D(pool_size=2)(net)

net = Conv2D(128, kernel_size=3, strides=1, padding='same', activation='relu')(net)
net = MaxPooling2D(pool_size=2)(net)

net = Flatten()(net)

net = Dense(512)(net)
net = Activation('relu')(net)
net = Dense(1)(net)
outputs = Activation('sigmoid')(net)

model = Model(inputs=inputs, outputs=outputs)

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])

model.summary()

#train

start_time = datetime.datetime.now().strftime('%Y_%m_%d_%H_%M_%S')

model.fit_generator(
    train_generator, epochs=50, validation_data=val_generator,
    callbacks=[
        ModelCheckpoint('models/%s.h5' % (start_time), monitor='val_acc', save_best_only=True, mode='max', verbose=1),
        ReduceLROnPlateau(monitor='val_acc', factor=0.2, patience=10, verbose=1, mode='auto', min_lr=1e-05)
    ]
)

# Confusion Matrix

from sklearn.metrics import accuracy_score, confusion_matrix
import seaborn as sns

model = load_model('models/%s.h5' % (start_time))

y_pred = model.predict(x_val/255.)
y_pred_logical = (y_pred > 0.5).astype(np.int)

print ('test acc: %s' % accuracy_score(y_val, y_pred_logical))

cm = confusion_matrix(y_val, y_pred_logical)
sns.heatmap(cm, annot=True)

# Distribution of Prediction
ax = sns.distplot(y_pred, kde=False)