-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathdatasets.py
207 lines (157 loc) · 8.25 KB
/
datasets.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
import torch
from torch.utils.data import Dataset
import h5py
import json
import os
class CaptionDataset(Dataset):
"""
A PyTorch Dataset class to be used in a PyTorch DataLoader to create batches.
"""
def __init__(self, data_folder, data_name, split, transform=None):
"""
:param data_folder: folder where data files are stored
:param data_name: base name of processed datasets
:param split: split, one of 'TRAIN', 'VAL', or 'TEST'
:param transform: image transform pipeline
"""
self.split = split
assert self.split in {'TRAIN', 'VAL', 'TEST'}
# Open hdf5 file where images are stored
self.h = h5py.File(os.path.join(data_folder, self.split + '_IMAGES_' + data_name + '.hdf5'), 'r')
self.imgs = self.h['images']
# Captions per image
self.cpi = self.h.attrs['captions_per_image']
# Load encoded captions (completely into memory)
with open(os.path.join(data_folder, self.split + '_CAPTIONS_' + data_name + '.json'), 'r') as j:
self.captions = json.load(j)
# Load caption lengths (completely into memory)
with open(os.path.join(data_folder, self.split + '_CAPLENS_' + data_name + '.json'), 'r') as j:
self.caplens = json.load(j)
# PyTorch transformation pipeline for the image (normalizing, etc.)
self.transform = transform
# Total number of datapoints
self.dataset_size = len(self.captions)
def __getitem__(self, i):
# Remember, the Nth caption corresponds to the (N // captions_per_image)th image
img = torch.FloatTensor(self.imgs[i // self.cpi] / 255.)
if self.transform is not None:
img = self.transform(img)
caption = torch.LongTensor(self.captions[i])
caplen = torch.LongTensor([self.caplens[i]])
if self.split is 'TRAIN':
return img, caption, caplen
else:
# For validation of testing, also return all 'captions_per_image' captions to find BLEU-4 score
all_captions = torch.LongTensor(
self.captions[((i // self.cpi) * self.cpi):(((i // self.cpi) * self.cpi) + self.cpi)])
return img, caption, caplen, all_captions
def __len__(self):
return self.dataset_size
class Fine_Tune_CaptionDataset(Dataset):
"""
A PyTorch Dataset class to be used in a PyTorch DataLoader to create gender-self-guided-fine-tuning batches.
"""
def __init__(self, data_folder, data_name, split, transform=None):
"""
:param data_folder: folder where data files are stored
:param data_name: base name of processed datasets
:param split: split, one of 'TRAIN', 'VAL', or 'TEST'
:param transform: image transform pipeline
"""
self.split = split
assert self.split in {'TRAIN', 'VAL', 'TEST'}
# Open hdf5 file where images are stored
self.h = h5py.File(os.path.join(data_folder, 'FT_' + self.split + '_IMAGES_' + data_name + '.hdf5'), 'r')
self.imgs = self.h['images']
# Captions per image
self.cpi = self.h.attrs['captions_per_image']
# Load encoded captions (completely into memory)
with open(os.path.join(data_folder, 'FT_' + self.split + '_CAPTIONS_' + data_name + '.json'), 'r') as j:
self.captions = json.load(j)
# Load caption lengths (completely into memory)
with open(os.path.join(data_folder, 'FT_' + self.split + '_CAPLENS_' + data_name + '.json'), 'r') as j:
self.caplens = json.load(j)
# Load neutral encoded captions (completely into memory)
with open(os.path.join(data_folder, 'FT_' + self.split + '_N_CAPTIONS_' + data_name + '.json'), 'r') as j:
self.n_captions = json.load(j)
# Load neutral encoded captions (completely into memory)
with open(os.path.join(data_folder, 'FT_' + self.split + '_GENDER_POS_' + data_name + '.json'), 'r') as j:
self.gender_pos = json.load(j)
# PyTorch transformation pipeline for the image (normalizing, etc.)
self.transform = transform
# Total number of datapoints
self.dataset_size = len(self.captions)
def __getitem__(self, i):
# Remember, the Nth caption corresponds to the (N // captions_per_image)th image
img = torch.FloatTensor(self.imgs[i // self.cpi] / 255.)
if self.transform is not None:
img = self.transform(img)
caption = torch.LongTensor(self.captions[i])
caplen = torch.LongTensor([self.caplens[i]])
n_caption = torch.LongTensor(self.n_captions[i])
gender_pos = torch.LongTensor([self.gender_pos[i]])
if self.split is 'TRAIN':
return img, caption, caplen, n_caption, gender_pos
else:
# For validation of testing, also return all 'captions_per_image' captions to find BLEU-4 score
all_captions = torch.LongTensor(
self.captions[((i // self.cpi) * self.cpi):(((i // self.cpi) * self.cpi) + self.cpi)])
return img, caption, caplen, all_captions
def __len__(self):
return self.dataset_size
class Fine_Tune_CaptionDataset_With_Mask(Dataset):
"""
A PyTorch Dataset class to be used in a PyTorch DataLoader to create gender-supervised-guided-fine-tuning batches.
"""
def __init__(self, data_folder, data_name, split, transform=None):
"""
:param data_folder: folder where data files are stored
:param data_name: base name of processed datasets
:param split: split, one of 'TRAIN', 'VAL', or 'TEST'
:param transform: image transform pipeline
"""
self.split = split
assert self.split in {'TRAIN', 'VAL', 'TEST'}
# Open hdf5 file where images are stored
self.h = h5py.File(os.path.join(data_folder, 'FTB_' + self.split + '_IMAGES_' + data_name + '.hdf5'), 'r')
self.imgs = self.h['images']
# Open hdf5 file where masks are stored
self.h = h5py.File(os.path.join(data_folder, 'FTB_' + self.split + '_MASKS_' + data_name + '.hdf5'), 'r')
self.mask_imgs = self.h['images']
# Captions per image
self.cpi = self.h.attrs['captions_per_image']
# Load encoded captions (completely into memory)
with open(os.path.join(data_folder, 'FTB_' + self.split + '_CAPTIONS_' + data_name + '.json'), 'r') as j:
self.captions = json.load(j)
# Load caption lengths (completely into memory)
with open(os.path.join(data_folder, 'FTB_' + self.split + '_CAPLENS_' + data_name + '.json'), 'r') as j:
self.caplens = json.load(j)
# Load neutral encoded captions (completely into memory)
with open(os.path.join(data_folder, 'FTB_' + self.split + '_N_CAPTIONS_' + data_name + '.json'), 'r') as j:
self.n_captions = json.load(j)
# Load neutral encoded captions (completely into memory)
with open(os.path.join(data_folder, 'FTB_' + self.split + '_GENDER_POS_' + data_name + '.json'), 'r') as j:
self.gender_pos = json.load(j)
# PyTorch transformation pipeline for the image (normalizing, etc.)
self.transform = transform
# Total number of datapoints
self.dataset_size = len(self.captions)
def __getitem__(self, i):
# Remember, the Nth caption corresponds to the (N // captions_per_image)th image
img = torch.FloatTensor(self.imgs[i // self.cpi] / 255.)
if self.transform is not None:
img = self.transform(img)
mask_img = torch.FloatTensor(self.mask_imgs[i // self.cpi] / 255.)
caption = torch.LongTensor(self.captions[i])
caplen = torch.LongTensor([self.caplens[i]])
n_caption = torch.LongTensor(self.n_captions[i])
gender_pos = torch.LongTensor([self.gender_pos[i]])
if self.split is 'TRAIN':
return img, caption, caplen, n_caption, gender_pos, mask_img
else:
# For validation of testing, also return all 'captions_per_image' captions to find BLEU-4 score
all_captions = torch.LongTensor(
self.captions[((i // self.cpi) * self.cpi):(((i // self.cpi) * self.cpi) + self.cpi)])
return img, caption, caplen, all_captions
def __len__(self):
return self.dataset_size