def _feature_leaf(num):
name = list(converter.num2name(abs(num)))
for i in range(len(name)):
if name[i] in POS_REL_NAMES_FULL.keys():
name[i] = POS_REL_NAMES_FULL[name[i]]
embedding = np.array(
[word_vectors[tokenizers['vocab2token'][i]] for i in ' '.join([name[1], name[0], name[2]]).split(' ')])
summed_embedding = np.sum(embedding, axis=0) / 3
return summed_embedding if num > 0 else -summed_embedding
def prediction_to_assignment_embedding(softmax_list, info_list, embedder,
tokenizers, pres, objs):
"""
:param softmax_list: a torch.Tensor
:param info_list: [(img_name, (label1, bbox1), (label2, bbox2))]
:param embedders: (pe, ce, ae)
:return: the embedding of assignment
"""
def _feature(name):
embedding = np.array([
word_vectors[tokenizers['vocab2token'][i]] for i in name.split(' ')
])
summed_embedding = np.sum(embedding, axis=0)
return summed_embedding
embedded_clauses = []
for idx, info in enumerate(info_list):
prop = softmax_list[idx]
sub = objs[info_list[idx][1][0]]
obj = objs[info_list[idx][2][0]]
e_p = 0
for pres_idx in range(0, 70):
# e_p += prop[pres_idx] * torch.cuda.FloatTensor(_feature(tokenizers['token2vocab'][pres_idx]))
e_p += prop[pres_idx] * torch.cuda.FloatTensor(
_feature(pres[pres_idx]))
e_p = e_p / 70
e_p = (e_p + torch.cuda.FloatTensor(_feature(sub)) +
torch.cuda.FloatTensor(_feature(obj))) / 3
embedded_clauses.append(e_p)
for idx, info in enumerate(info_list):
pos = box_prop_name(info_list[idx][1][1], info_list[idx][2][1])
if pos in POS_REL_NAMES_FULL.keys():
pos = POS_REL_NAMES_FULL[pos]
sub = objs[info_list[idx][1][0]]
obj = objs[info_list[idx][2][0]]
embedded_clauses.append(
(torch.cuda.FloatTensor(_feature(pos)) + torch.cuda.FloatTensor(
_feature(sub)) + torch.cuda.FloatTensor(_feature(obj))) / 3)
adj0, features0, labels0 = assignment_to_gcn_compatible(
embedded_clauses, node_features)
embedded_clauses = embedder(features0.cuda().squeeze(0),
adj0.cuda().squeeze(0), labels0.cuda())
return embedded_clauses
def tree_prediction_to_assignment_embedding(softmax_list, info_list, embedder,
tokenizers, pres, objs):
def _feature(name):
embedding = np.array([
word_vectors[tokenizers['vocab2token'][i]] for i in name.split(' ')
])
summed_embedding = np.sum(embedding, axis=0)
return summed_embedding
embedded_clauses = []
for idx, info in enumerate(info_list):
prop = softmax_list[idx]
sub = objs[info_list[idx][1][0]]
obj = objs[info_list[idx][2][0]]
e_p = 0
for pres_idx in range(0, 70):
# e_p += prop[pres_idx] * torch.cuda.FloatTensor(_feature(tokenizers['token2vocab'][pres_idx]))
e_p += prop[pres_idx] * torch.cuda.FloatTensor(
_feature(pres[pres_idx]))
e_p = e_p / 70
e_p = (e_p + torch.cuda.FloatTensor(_feature(sub)) +
torch.cuda.FloatTensor(_feature(obj))) / 3
embedded_clauses.append(e_p)
for idx, info in enumerate(info_list):
pos = box_prop_name(info_list[idx][1][1], info_list[idx][2][1])
if pos in POS_REL_NAMES_FULL.keys():
pos = POS_REL_NAMES_FULL[pos]
sub = objs[info_list[idx][1][0]]
obj = objs[info_list[idx][2][0]]
embedded_clauses.append(
(torch.cuda.FloatTensor(_feature(pos)) + torch.cuda.FloatTensor(
_feature(sub)) + torch.cuda.FloatTensor(_feature(obj))) / 3)
tree0, features0, labels0 = assignment_to_tree_compatible(
embedded_clauses, node_features)
embedded_clauses = embedder(tree0, features0.cuda())
return embedded_clauses