-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path5_tokenizer.py
73 lines (67 loc) · 2.21 KB
/
5_tokenizer.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
from keras.preprocessing.text import Tokenizer
from pickle import dump
# load doc into memory
def load_doc(filename):
# open the file as read only
file = open(filename, 'r')
# read all text
text = file.read()
# close the file
file.close()
return text
# load a pre-defined list of photo identifiers
def load_set(filename):
doc = load_doc(filename)
dataset = list()
# process line by line
for line in doc.split('\n'):
# skip empty lines
if len(line) < 1:
continue
# get the image identifier
identifier = line.split('.')[0]
dataset.append(identifier)
return set(dataset)
# load clean descriptions into memory
def load_clean_descriptions(filename, dataset):
# load document
doc = load_doc(filename)
descriptions = dict()
for line in doc.split('\n'):
# split line by white space
tokens = line.split()
# split id from description
image_id, image_desc = tokens[0], tokens[1:]
# skip images not in the set
if image_id in dataset:
# create list
if image_id not in descriptions:
descriptions[image_id] = list()
# wrap description in tokens
desc = 'startseq ' + ' '.join(image_desc) + ' endseq'
# store
descriptions[image_id].append(desc)
return descriptions
# covert a dictionary of clean descriptions to a list of descriptions
def to_lines(descriptions):
all_desc = list()
for key in descriptions.keys():
[all_desc.append(d) for d in descriptions[key]]
return all_desc
# fit a tokenizer given caption descriptions
def create_tokenizer(descriptions):
lines = to_lines(descriptions)
tokenizer = Tokenizer()
tokenizer.fit_on_texts(lines)
return tokenizer
# load training dataset (6K)
filename = 'Flickr8k_text/Flickr_8k.trainImages.txt'
train = load_set(filename)
print('Dataset: %d' % len(train))
# descriptions
train_descriptions = load_clean_descriptions('descriptions.txt', train)
print('Descriptions: train=%d' % len(train_descriptions))
# prepare tokenizer
tokenizer = create_tokenizer(train_descriptions)
# save the tokenizer
dump(tokenizer, open('tokenizer.pkl', 'wb'))