class RefDataset(Dataset):
def __init__(self, split):
self.refer = REFER(dataset='refcoco+', splitBy='unc')
self.ref_ids = self.refer.getRefIds(split=split)
self.image_embeds = np.load(
os.path.join("data", "embeddings", "FINALImageEmbeddings.npy"))
self.image_ids = list(
np.load(os.path.join("data", "embeddings", "FINALImageIDs.npy")))
before_text_embeds = time.time()
self.text_embeds = np.concatenate(
(np.load(
os.path.join("data", "embeddings",
"FINALTextEmbeddings1of2.npy")),
np.load(
os.path.join("data", "embeddings",
"FINALTextEmbeddings2of2.npy"))),
axis=0)
after_text_embeds = time.time()
print("Text Embedding Time: ", after_text_embeds - before_text_embeds)
assert (len(self.text_embeds) == 141564)
assert (self.text_embeds[0].shape[1] == 3072)
print('Found {} referred objects in {} split.'.format(
len(self.ref_ids), split))
def __len__(self):
return len(self.ref_ids)
def __getitem__(self, i):
ref_id = self.ref_ids[i]
ref = self.refer.loadRefs(ref_id)[0]
image_id = ref['image_id']
image = self.refer.Imgs[image_id]
image_idx = self.image_ids.index(image_id)
image_embed = self.image_embeds[image_idx, :, :, :]
height = image['height']
width = image['width']
bound_box = torch.Tensor(self.refer.getRefBox(ref_id))
bound_box[0] /= width
bound_box[1] /= height
bound_box[2] /= width
bound_box[3] /= height
#bound_box = bound_box.unsqueeze(dim=0)
#whole_file_name = ref['file_name']
#file_name = whole_file_name[:whole_file_name.rfind("_")]+".jpg"
sent = random.choice(ref['sentences'])
ref_expr = sent['raw']
text_id = sent['sent_id']
text_idx = text_id
text_embed = torch.from_numpy(self.text_embeds[text_idx])
return image_embed, text_embed, bound_box
class RefDataset(Dataset):
def __init__(self):
self.refer = REFER(dataset='refcoco+', splitBy='unc')
self.ref_ids = self.refer.getRefIds()
def __len__(self):
return len(self.ref_ids)
def __getitem__(self, i):
ref_id = self.ref_ids[i]
ref = self.refer.loadRefs(ref_id)[0]
for sent in ref['sentences']:
s = sent['raw']
sid = sent['sent_id']
return s, sid
