forked from alexliyang/Hand-Gesture-Recognition-4
-
Notifications
You must be signed in to change notification settings - Fork 0
/
OurModel.py
165 lines (148 loc) · 5.88 KB
/
OurModel.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
from __future__ import print_function
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Dropout, Flatten, Activation
import numpy as np
import argparse
import cv2
import matplotlib
matplotlib.use('agg', warn=False, force=True)
from matplotlib import pyplot as plt
from keras.optimizers import SGD
import scipy.io
from keras.utils import np_utils
from keras.models import load_model
from keras.preprocessing.image import ImageDataGenerator
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-s", "--save-model", type=int, default=-1,
help="(optional) whether or not model should be saved to disk")
ap.add_argument("-l", "--load-model", type=int, default=-1,
help="(optional) whether or not pre-trained model should be loaded")
ap.add_argument("-w", "--weights", type=str,
help="(optional) path to weights file")
args = vars(ap.parse_args())
# read input data
hand_data = scipy.io.loadmat('hand_data')
hand_data_test = scipy.io.loadmat('hand_data_test')
# reshape the input data to (160,120,3)
# xtrain is the training images, ytrain is the labels
xtrain = hand_data["training"]
xtrain = xtrain.reshape(1500, 3, 160, 120)
xtrain = np.transpose(xtrain, (0, 3, 2, 1))
ytrain = hand_data["train_label"]
# xtest is the testing images (500)
# ytest is the testing labels
xtest = hand_data_test["testing"]
xtest = xtest.reshape(500, 3, 160, 120)
xtest = np.transpose(xtest, (0, 3, 2, 1))
ytest = hand_data_test['test_label']
# normalize to make convergence faster
xtrain = xtrain.astype('float32') / 255.0
xtest = xtest.astype('float32') / 255.0
# Convert 1-dimensional class arrays to 10-dimensional class matrices
ytrain = np_utils.to_categorical(ytrain, 10)
ytest = np_utils.to_categorical(ytest, 10)
model = load_model('my_model.h5')
# # Architecture of Lenet-5: INPUT => CONV => RELU => POOL => CONV => RELU => POOL => FC => RELU => FC
# # Convolution layer 1. Use 32 convolution filters
# # Activation function is ReLU
# # base experiment, without dropout and data augmentation
# model.add(Conv2D(32, (3, 3), border_mode='valid', input_shape=xtrain.shape[1:]))
# model.add(Activation('relu'))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(0.25))
#
# # conv + relu + maxpooling
# model.add(Conv2D(32, (3, 3), border_mode='valid'))
# model.add(Activation('relu'))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(0.25))
#
# # model.add(Conv2D(32,(3,3),border_mode = 'valid'))
# # model.add(Activation('relu'))
# model.add(Conv2D(32, (3, 3), border_mode='valid'))
# model.add(Activation('relu'))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(0.25))
#
# # model.add(Conv2D(64,(3,3),border_mode = 'valid'))
# # model.add(Activation('relu'))
# model.add(Conv2D(64, (3, 3), border_mode='valid'))
# model.add(Activation('relu'))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(0.25))
#
# # fully connected layer
# model.add(Flatten())
# model.add(Dense(384))
# model.add(Activation('relu'))
# model.add(Dropout(0.25))
#
# # fully connected layer
# model.add(Dense(10))
# model.add(Activation('softmax'))
#
# batch_size = 100
# epochs = 1
#
# model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
#
# if args["load_model"] < 0:
# datagen = ImageDataGenerator(
# zoom_range=0.2, # randomly zoom into images
# rotation_range=10, # randomly rotate images in the range (degrees, 0 to 180)
# width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
# height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
# horizontal_flip=True, # randomly flip images
# vertical_flip=False)
#
# history = model.fit_generator(datagen.flow(xtrain, ytrain, batch_size=batch_size),
# steps_per_epoch=int(np.ceil(xtrain.shape[0] / float(batch_size))),
# epochs=epochs,
# validation_data=(xtest, ytest),
# workers=4)
#
# score = model.evaluate(xtest, ytest)
# print(score)
#
# # check to see if the model should be saved to file
# if args["save_model"] > 0:
# print("[INFO] dumping weights to file...")
# #model.save_weights(args["weights"], overwrite=True)
# model.save('mymodel.h5')
# randomly select a few testing digits
for i in np.random.choice(np.arange(0, len(ytest)), size=(20,)):
# classify the digit
probs = model.predict(xtest[np.newaxis, i])
#print(probs)
prediction = probs.argmax(axis=1)
#print(prediction)
# resize the image from a 28 x 28 image to a 96 x 96 image so we
# can better see it
image = (xtest[i, :, :])
# cv2.putText(image, str(prediction[0]), (5, 20),
# cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 255, 0), 2)
# show the image and prediction
print("[INFO] Predicted: {}, Actual: {}".format(prediction[0],
np.argmax(ytest[i])))
cv2.imshow("Gesture", image)
cv2.waitKey(2000)
# plt.figure(figsize=[10,8])
# plt.plot(history.history['loss'],'r',linewidth=3.0)
# plt.plot(history.history['val_loss'],'b',linewidth=3.0)
# plt.legend(['Training loss', 'Validation Loss'],fontsize=16)
# plt.xlabel('Epochs ',fontsize=16)
# plt.ylabel('Loss',fontsize=16)
# plt.title('Loss Curves',fontsize=16)
# plt.savefig('ourmodel_loss.jpg')
# plt.show()
#
# plt.figure(figsize=[10,8])
# plt.plot(history.history['acc'],'r',linewidth=3.0)
# plt.plot(history.history['val_acc'],'b',linewidth=3.0)
# plt.legend(['Training Accuracy', 'Validation Accuracy'],fontsize=16)
# plt.xlabel('Epochs ',fontsize=16)
# plt.ylabel('Accuracy',fontsize=16)
# plt.title('Accuracy Curves',fontsize=16)
# plt.savefig('ourmodel_accuracy.jpg')
# plt.show()