-
Notifications
You must be signed in to change notification settings - Fork 0
/
transfer_learning_vgg16_custom_data.py
168 lines (133 loc) · 5.13 KB
/
transfer_learning_vgg16_custom_data.py
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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
import numpy as np
import os
import time
from vgg16 import VGG16
from keras.preprocessing import image
from keras.applications.imagenet_utils import preprocess_input
from imagenet_utils import decode_predictions
from keras.layers import Dense, Activation, Flatten
from keras.layers import merge, Input
from keras.models import Model
from keras.utils import np_utils
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
print (x.shape)
x = np.expand_dims(x, axis=0)
print (x.shape)
x = preprocess_input(x)
print('Input image shape:', x.shape)
# Loading the training data
PATH = os.getcwd()
# Define data path
data_path = PATH + '/data'
data_dir_list = os.listdir(data_path)
img_data_list=[]
for dataset in data_dir_list:
img_list=os.listdir(data_path+'/'+ dataset)
print ('Loaded the images of dataset-'+'{}\n'.format(dataset))
for img in img_list:
img_path = data_path + '/'+ dataset + '/'+ img
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
# x = x/255
print('Input image shape:', x.shape)
img_data_list.append(x)
img_data = np.array(img_data_list)
#img_data = img_data.astype('float32')
print (img_data.shape)
img_data=np.rollaxis(img_data,1,0)
print (img_data.shape)
img_data=img_data[0]
print (img_data.shape)
# Define the number of classes
num_classes = 4
num_of_samples = img_data.shape[0]
labels = np.ones((num_of_samples,),dtype='int64')
labels[0:202]=0
labels[202:404]=1
labels[404:606]=2
labels[606:]=3
names = ['cats','dogs','horses','humans']
# convert class labels to on-hot encoding
Y = np_utils.to_categorical(labels, num_classes)
#Shuffle the dataset
x,y = shuffle(img_data,Y, random_state=2)
# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=2)
#########################################################################################
# Custom_vgg_model_1
#Training the classifier alone
image_input = Input(shape=(224, 224, 3))
model = VGG16(input_tensor=image_input, include_top=True,weights='imagenet')
model.summary()
last_layer = model.get_layer('fc2').output
#x= Flatten(name='flatten')(last_layer)
out = Dense(num_classes, activation='softmax', name='output')(last_layer)
custom_vgg_model = Model(image_input, out)
custom_vgg_model.summary()
for layer in custom_vgg_model.layers[:-1]:
layer.trainable = False
custom_vgg_model.layers[3].trainable
custom_vgg_model.compile(loss='categorical_crossentropy',optimizer='rmsprop',metrics=['accuracy'])
t=time.time()
# t = now()
hist = custom_vgg_model.fit(X_train, y_train, batch_size=32, epochs=12, verbose=1, validation_data=(X_test, y_test))
print('Training time: %s' % (t - time.time()))
(loss, accuracy) = custom_vgg_model.evaluate(X_test, y_test, batch_size=10, verbose=1)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))
####################################################################################################################
#Training the feature extraction also
image_input = Input(shape=(224, 224, 3))
model = VGG16(input_tensor=image_input, include_top=True,weights='imagenet')
model.summary()
last_layer = model.get_layer('block5_pool').output
x= Flatten(name='flatten')(last_layer)
x = Dense(128, activation='relu', name='fc1')(x)
x = Dense(128, activation='relu', name='fc2')(x)
out = Dense(num_classes, activation='softmax', name='output')(x)
custom_vgg_model2 = Model(image_input, out)
custom_vgg_model2.summary()
# freeze all the layers except the dense layers
for layer in custom_vgg_model2.layers[:-3]:
layer.trainable = False
custom_vgg_model2.summary()
custom_vgg_model2.compile(loss='categorical_crossentropy',optimizer='adadelta',metrics=['accuracy'])
t=time.time()
# t = now()
hist = custom_vgg_model2.fit(X_train, y_train, batch_size=32, epochs=12, verbose=1, validation_data=(X_test, y_test))
print('Training time: %s' % (t - time.time()))
(loss, accuracy) = custom_vgg_model2.evaluate(X_test, y_test, batch_size=10, verbose=1)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))
#%%
import matplotlib.pyplot as plt
# visualizing losses and accuracy
train_loss=hist.history['loss']
val_loss=hist.history['val_loss']
train_acc=hist.history['acc']
val_acc=hist.history['val_acc']
xc=range(12)
plt.figure(1,figsize=(7,5))
plt.plot(xc,train_loss)
plt.plot(xc,val_loss)
plt.xlabel('num of Epochs')
plt.ylabel('loss')
plt.title('train_loss vs val_loss')
plt.grid(True)
plt.legend(['train','val'])
#print plt.style.available # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])
plt.figure(2,figsize=(7,5))
plt.plot(xc,train_acc)
plt.plot(xc,val_acc)
plt.xlabel('num of Epochs')
plt.ylabel('accuracy')
plt.title('train_acc vs val_acc')
plt.grid(True)
plt.legend(['train','val'],loc=4)
#print plt.style.available # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])