- 处理数据
- 读入vgg_feats.mat
- 读入
数据及介绍
Flickr8k 2013
-
数据处理
Flickr8k.token.txt每一行数据格式： 000268201_693b08cb0e.jpg#0 A child in a pink dress is climbing up a set of stairs in an entry way .
我们将其解析存放到一个dict()中img_to_caps.存放格式
img_to_caps['000268201_693b08cb0e'] =[caption1,caption2,caption3,caption4,caption5].
def __init__(self,path=path.join('Flickr8k_text','Flickr8k.token.sample.txt'),n_vocab=100,max_seq_len=16):
'''
the format of evary line in Flickr8k.token.txt
000268201_693b08cb0e.jpg#0 A child in a pink dress is climbing up a set of stairs in an entry way .
we will parse it to store img_to_caps, its the format is
img_to_caps['000268201_693b08cb0e'] = [caption1,caption2,caption3,caption4,caption5]
'''
self.img_to_caps = dict()
with open(path) as f:
for line in f:
tokens = line.split(' ')
img_fname, cap_idx = tokens[0].split('#')
caption = ' '.join(tokens[1:]).strip()
if img_fname not in self.img_to_caps:
self.img_to_caps[img_fname] = []
self.img_to_caps[img_fname].append(caption)
self.img_fnames = self.img_to_caps.keys()
print(self.img_fnames)
print(self.img_to_caps)
