-
Notifications
You must be signed in to change notification settings - Fork 1
/
TrainModels.py
317 lines (282 loc) · 12.5 KB
/
TrainModels.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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
from sklearn.utils import class_weight
import numpy as np
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Conv2D, Dropout, Flatten, MaxPooling2D, Activation, Dense, BatchNormalization
from keras.utils import np_utils
from keras.models import save_model
import pickle
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
import math
from matplotlib import pyplot as plt
from keras.utils import to_categorical
from keras.optimizers import SGD
from keras.applications.resnet50 import ResNet50
from keras.callbacks import ModelCheckpoint
import sys
def train_connected_character_recognition_model():
with open("./Datasets/connectedCharacterRecognition.pickle", "rb") as f:
X, y = pickle.load(f)
y = np.array(y)
X = np.array(X)
X = X.astype('float32')
X = X / 255.0
unique, counts = np.unique(y, return_counts=True)
print(dict(zip(unique, counts)))
X = X.reshape((-1, 28, 56, 1))
y = to_categorical(y, num_classes=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.10, random_state=42)
print('Number of images in x_train', X_train.shape[0])
print('Number of images in x_test', X_test.shape[0])
input_shape = (28, 56, 1)
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), padding='same', use_bias=False, input_shape=input_shape))
model.add(Activation('relu'))
model.add(Conv2D(filters=32, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(.2))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(Activation('relu'))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(.2))
model.add(Conv2D(filters=128, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(Activation('relu'))
model.add(Conv2D(filters=128, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Conv2D(filters=256, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(Activation('relu'))
model.add(Conv2D(filters=256, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(.3))
model.add(Dense(512, activation='relu'))
model.add(BatchNormalization())
model.add(Dense(units=2, activation='softmax'))
sgd = SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
model.summary()
batch_size = 128
steps = math.ceil(X_train.shape[0] / batch_size)
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=0, # randomly rotate images in the range (degrees, 0 to 180)
zoom_range=0.15, # Randomly zoom image
width_shift_range=0.15, # randomly shift images horizontally (fraction of total width)
height_shift_range=0, # randomly shift images vertically (fraction of total height)
horizontal_flip=False, # randomly flip images
vertical_flip=False)
history = model.fit_generator(datagen.flow(X_train, y_train, batch_size=batch_size),
epochs=10, validation_data=(X_test, y_test),
verbose=2, steps_per_epoch=steps)
save_model(model, './Models/connected_character_recognition_8cnn.h5')
score = model.evaluate(X_test, y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
print(score)
print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.grid()
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.grid()
plt.show()
def train_implicit_segmentation_model():
model = Sequential()
mod = ResNet50(include_top=False, weights='imagenet', input_shape=(56, 112, 3), pooling='max')
mod.summary()
model.add(ResNet50(include_top=False, weights='imagenet', input_shape=(56, 112, 3), pooling='max'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(units=5256, activation='softmax'))
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
model.summary()
batch_size = 64
epochs = 20
train_steps = math.ceil(2907882 / batch_size)
valid_steps = math.ceil(323098 / batch_size)
checkpoint = ModelCheckpoint("./Models/implicit_segmentation_model.hdf5",
monitor='loss', verbose=1, save_best_only=True, mode='auto', period=1)
train_datagen = ImageDataGenerator(
rescale=1. / 255,
zoom_range=0.15,
width_shift_range=0.15)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
'./Datasets/implicitSegmentation/train',
target_size=(56, 112),
batch_size=batch_size,
class_mode='categorical',
color_mode='rgb')
validation_generator = test_datagen.flow_from_directory(
'./Datasets/implicitSegmentation/test',
target_size=(56, 112),
batch_size=batch_size,
class_mode='categorical',
color_mode='rgb')
history = model.fit_generator(
train_generator,
steps_per_epoch=train_steps,
epochs=epochs,
verbose=2,
validation_data=validation_generator,
validation_steps=valid_steps, callbacks=[checkpoint])
save_model(model, './Models/implicit_segmentation_model.h5')
batch_size = 146
test_datagen = ImageDataGenerator(rescale=1. / 255)
validation_generator = test_datagen.flow_from_directory(
'./Datasets/implicitSegmentation/test',
target_size=(56, 112),
batch_size=batch_size,
class_mode='categorical',
color_mode='rgb')
valid_steps = math.ceil(323098 / batch_size)
score = model.evaluate_generator(validation_generator, steps=valid_steps, verbose=1)
print('Test score:', score[0])
print('Test accuracy:', score[1])
print(score)
print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.grid()
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.grid()
plt.show()
def train_single_character_model():
with open("./Datasets/single_character.pickle", "rb") as f:
X_train, X_test, y_train, y_test = pickle.load(f)
X_train = X_train.astype('float16')
X_test = X_test.astype('float16')
X_train = np.array(X_train) / 255.0
y_train = np.array(y_train)
X_test = np.array(X_test) / 255.0
y_test = np.array(y_test)
print('x_train shape:', X_train.shape)
print('Number of images in x_train', X_train.shape[0])
print('Number of images in x_test', X_test.shape[0])
X_train = X_train.reshape(-1, 28, 28, 1)
X_test = X_test.reshape(-1, 28, 28, 1)
y_train = y_train.astype(int)
bc = np.bincount(y_train)
print(bc)
class_weights = class_weight.compute_class_weight('balanced', np.unique(y_train), y_train)
class_weights = dict(enumerate(class_weights))
y_train = np_utils.to_categorical(y_train, 72)
y_test = np_utils.to_categorical(y_test, 72)
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), padding='same', use_bias=False, input_shape=(28, 28, 1)))
model.add(Activation('relu'))
model.add(Conv2D(filters=32, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(.3))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(Activation('relu'))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(.3))
model.add(Conv2D(filters=128, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(Activation('relu'))
model.add(Conv2D(filters=128, kernel_size=(3, 3), padding='same', use_bias=False))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(.3))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(units=72, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
opt = optimizers.Adamax(lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=0, # randomly rotate images in the range (degrees, 0 to 180)
zoom_range=0.2, # Randomly zoom image
width_shift_range=0, # randomly shift images horizontally (fraction of total width)
height_shift_range=0, # randomly shift images vertically (fraction of total height)
horizontal_flip=False, # randomly flip images
vertical_flip=False)
checkpoint = ModelCheckpoint("./Models/single_char_model_6cnn.hdf5",
monitor='loss', verbose=1, save_best_only=True, mode='auto', period=1)
batch_size = 64
steps = math.ceil(X_train.shape[0] / batch_size)
history = model.fit_generator(datagen.flow(X_train, y_train, batch_size=batch_size),
epochs=15, validation_data=(X_test, y_test),
verbose=2, steps_per_epoch=steps, callbacks=[checkpoint])
save_model(model, './Models/single_char_model_6cnn.h5')
score = model.evaluate(X_test, y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
print(score)
print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.grid()
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.grid()
plt.show()
if sys.argv[1] == 'connectedCharacterRecognition':
train_connected_character_recognition_model()
elif sys.argv[1] == 'implicitSegmentation':
train_implicit_segmentation_model()
elif sys.argv[1] == 'singleCharacter':
train_single_character_model()
else:
print("Wrong argument!")