-
Notifications
You must be signed in to change notification settings - Fork 1
/
train.py
151 lines (118 loc) · 5.11 KB
/
train.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
import cv2 # working with, mainly resizing, images
import numpy as np # dealing with arrays
import os # dealing with directories
from random import shuffle # mixing up or currently ordered data that might lead our network astray in training.
from tqdm import tqdm # a nice pretty percentage bar for tasks. Thanks to viewer Daniel BA1/4hler for this suggestion
import tensorflow as tf
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
# https://pythonprogramming.net/tflearn-machine-learning-tutorial/
# https://pythonprogramming.net/convolutional-neural-network-kats-vs-dogs-machine-learning-tutorial/
TRAIN_DIR = './train'
TEST_DIR = './test'
IMG_SIZE = 50
LR = 1e-3
MODEL_NAME = 'dogsvscats-{}-{}.model'.format(LR, '2conv-basic')
def label_img(img):
word_label = img.split('.')[0][:3]
# conversion to one-hot array [cat,dog]
# [much cat, no dog]
if word_label == 'cat': return [1,0]
# [no cat, very doggo]
elif word_label == 'dog': return [0,1]
def create_train_data():
training_data = []
for img in tqdm(os.listdir(TRAIN_DIR)):
label = label_img(img)
path = os.path.join(TRAIN_DIR,img)
img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
training_data.append([np.array(img),np.array(label)])
shuffle(training_data)
np.save('train_data.npy', training_data)
return training_data
def create_test_data():
testing_data = []
for img in tqdm(os.listdir(TEST_DIR)):
path = os.path.join(TEST_DIR,img)
img_num = img.split('.')[0][3:]
img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
testing_data.append([np.array(img), img_num])
shuffle(testing_data)
np.save('test_data.npy', testing_data)
return testing_data
# train_data = create_train_data()
# test_data = create_test_data()
train_data = np.load('train_data.npy')
test_data = np.load('test_data.npy')
# convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
# convnet = conv_2d(convnet, 32, 5, activation='relu')
# convnet = max_pool_2d(convnet, 5)
# convnet = conv_2d(convnet, 64, 5, activation='relu')
# convnet = max_pool_2d(convnet, 5)
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = dropout(convnet, 0.8)
# convnet = fully_connected(convnet, 2, activation='softmax')
# convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
# model = tflearn.DNN(convnet, tensorboard_dir='log')
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 128, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log', tensorboard_verbose=0)
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('model loaded!')
train = train_data[:-200]
test = train_data[-200:]
X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
Y = [i[1] for i in train]
test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
test_y = [i[1] for i in test]
model.fit({'input': X}, {'targets': Y}, n_epoch=3, validation_set=({'input': test_x}, {'targets': test_y}),
snapshot_step=500, show_metric=True, run_id=MODEL_NAME)
model.save(MODEL_NAME)
import matplotlib.pyplot as plt
# if you need to create the data:
#test_data = process_test_data()
# if you already have some saved:
test_data = np.load('test_data.npy')
fig=plt.figure(figsize=(6, 6))
# d = test_data[0]
# img_data, img_num = d
# data = img_data.reshape(IMG_SIZE, IMG_SIZE, 1)
# prediction = model.predict([data])[0]
# ax = fig.add_subplot(111)
# ax.imshow(img_data, cmap="gray")
# print(f"cat: {prediction[0]}, dog: {prediction[1]}")
for num,data in enumerate(test_data[:12]):
# cat: [1,0]
# dog: [0,1]
img_num = data[1]
img_data = data[0]
y = fig.add_subplot(4,4,num+1)
orig = img_data
data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)
#model_out = model.predict([data])[0]
model_out = model.predict([data])[0]
if np.argmax(model_out) == 1: str_label='Dog'
else: str_label='Cat'
y.imshow(orig,cmap='gray')
plt.title(str_label)
y.axes.get_xaxis().set_visible(False)
y.axes.get_yaxis().set_visible(False)
plt.show()