def batcher(params, batch):
model = params['model']
sentences = [' '.join(s) for s in batch]
tokenizer = params['tokenizer']
sentences_index = [
tokenizer.encode(s, add_special_tokens=True) for s in sentences
]
features_input_ids = []
features_mask = []
for sent_ids in sentences_index:
# Truncate if too long
if len(sent_ids) > params['max_seq_length']:
sent_ids = sent_ids[:params['max_seq_length']]
sent_mask = [1] * len(sent_ids)
# Padding
padding_length = params['max_seq_length'] - len(sent_ids)
sent_ids += ([0] * padding_length)
sent_mask += ([0] * padding_length)
# Length Check
assert len(sent_ids) == params['max_seq_length']
assert len(sent_mask) == params['max_seq_length']
features_input_ids.append(sent_ids)
features_mask.append(sent_mask)
batch_input_ids = torch.tensor(features_input_ids, dtype=torch.long)
batch_input_mask = torch.tensor(features_mask, dtype=torch.long)
batch = [batch_input_ids.to(device), batch_input_mask.to(device)]
inputs = {"input_ids": batch[0], "attention_mask": batch[1]}
model.zero_grad()
with torch.no_grad():
features = model(**inputs)[1]
'''
features = [layer_emb.cpu().numpy() for layer_emb in features]
all_layer_embedding = []
for i in range(features[0].shape[0]):
all_layer_embedding.append(np.array([layer_emb[i] for layer_emb in features]))
'''
all_layer_embedding = torch.stack(features).permute(1, 0, 2,
3).cpu().numpy()
embed_method = utils.generate_embedding(params['embed_method'],
features_mask)
embedding = embed_method.embed(params, all_layer_embedding)
return embedding
# Length Check
assert len(sent_ids) == params['max_seq_length']
assert len(sent_mask) == params['max_seq_length']
features_input_ids.append(sent_ids)
features_mask.append(sent_mask)
batch_input_ids = torch.tensor(features_input_ids, dtype=torch.long)
batch_input_mask = torch.tensor(features_mask, dtype=torch.long)
batch = [batch_input_ids.to(device), batch_input_mask.to(device)]
inputs = {"input_ids": batch[0], "attention_mask": batch[1]}
model.zero_grad()
with torch.no_grad():
features = model(**inputs)[1]
features = [layer_emb.cpu().numpy() for layer_emb in features]
all_layer_embedding = []
for i in range(features[0].shape[0]):
all_layer_embedding.append(
np.array([layer_emb[i] for layer_emb in features]))
embed_method = utils.generate_embedding(params['embed_method'],
features_mask)
embedding = embed_method.embed(params, all_layer_embedding)
similarity = embedding[0].dot(embedding[1]) / np.linalg.norm(
embedding[0]) / np.linalg.norm(embedding[1])
print('The similarity between these two sentences are (from 0-1):',
similarity)
left = ya != 0 or yc != 0
right = yb != 0 or yd != 0
left_eye_and_nose = ya != 0 or ye != 0
right_eye_and_nose = yb != 0 or ye != 0
left_mouth_and_nose = yc != 0 or ye != 0
right_mouth_and_nose = yd != 0 or ye != 0
if eye is True or mouth is True or left is True or right is True or left_eye_and_nose is True or right_eye_and_nose is True or left_mouth_and_nose is True or right_mouth_and_nose is True:
likely_face = True
name = ''
iobject = transform.resize(image=iobject, output_shape=[112, 112])
iobject = np.mean(iobject, axis=-1, keepdims=True)
iobject = np.concatenate([iobject, iobject, iobject], axis=-1)
iobject = np.array(iobject, dtype='int32')
embedding1d = generate_embedding(interpreter=interpreter3,
input_details=input_details3,
output_details=output_details3,
pix=iobject)
oid = recognize(embedding2d=embedding2d, embedding1d=embedding1d)
name = '' if oid == -1 else ID_map[oid]
if likely_face is not True and name == '':
continue
scale = edge / 112
ya, xa = y1 + int(scale * ya), x1 + int(scale * xa)
yb, xb = y1 + int(scale * yb), x1 + int(scale * xb)
yc, xc = y1 + int(scale * yc), x1 + int(scale * xc)
yd, xd = y1 + int(scale * yd), x1 + int(scale * xd)
ye, xe = y1 + int(scale * ye), x1 + int(scale * xe)
bboxes.append(
for i in range(total_ids):
ID = IDs[i]
file_names = listdir(ids_dir + '/' + ID)
while '.DS_Store' in file_names:
file_names.remove('.DS_Store')
embeddings = []
for j in range(len(file_names)):
file_name = file_names[j]
pix = io.imread(ids_dir + '/' + ID + '/' + file_name)
pix = np.mean(pix, axis=-1, keepdims=True)
pix = np.concatenate([pix, pix, pix], axis=-1)
pix = np.array(pix, dtype='int32')
# Origin
embedding = generate_embedding(interpreter=interpreter,
input_details=input_details,
output_details=output_details,
pix=pix)
embeddings.append(embedding)
# Flip
pix = np.fliplr(pix)
embedding = generate_embedding(interpreter=interpreter,
input_details=input_details,
output_details=output_details,
pix=pix)
embeddings.append(embedding)
embedding2d[i] = np.mean(np.array(embeddings, dtype='float32'), axis=0)
np.save(output_path + '/embedding2d.npy', embedding2d)