def __init__(self, vec_dim, dim, options={}):
"""
Instantiate the Layer (which will later be used to connect tensors)
Parameters
----------
vec_dim : int (width of the vector generated by the vectorizer)
dim : int (width of vectors in the rest of the network)
"""
super(StackedBiLSTM, self).__init__()
# Embedder (mostly to upscale the incoming character vectors)
self.embedder = Embedder(vec_dim, dim)
# Left to right Stacked LSTM
self.left2rightA = LSTMCell(dim, options=options) # Outputs two length-dim vectors
self.left2rightB = LSTMCell(dim, options=options) # Outputs two length-dim vectors
# Right to left Stacked LSTM
self.right2leftA = LSTMCell(dim, options=options) # Outputs two length-dim vectors
self.right2leftB = LSTMCell(dim, options=options) # Outputs two length-dim vectors
# Output decision layer
self.splitLayer = SplitLayer(dim, options=options) # Outputs a one-dimensional length-2 vector
self.Lzeros = pu.var_zeros(dim, ttype=options.get('ttype')) # Zeros for initialization from left
self.Lhzeros = pu.var_zeros(dim, ttype=options.get('ttype')) # Zeros for initialization (hidden layer)
self.Rzeros = pu.var_zeros(dim, ttype=options.get('ttype')) # same, for the right
self.Rhzeros = pu.var_zeros(dim, ttype=options.get('ttype'))
self.training = False # By default, but set to True during training with 'train()'
def calc_embeddings(docs: List[str], batch_size: int, root: str) -> np.ndarray:
"""Calculate embeddings (in batches).
Args:
docs: List of documents filenames.
batch_size: Batch size.
root: Root directory.
Returns:
Numpy array of (N, 768) of texts embeddings.
"""
embedder = Embedder()
all_embeddings = np.zeros((len(docs), 768), dtype=np.float32)
iters = len(docs) // batch_size
if len(docs) % batch_size > 0:
iters += 1
for i in trange(iters):
batch = docs[i * batch_size:(i + 1) * batch_size]
filenames = [os.path.join(root, doc) for doc in batch]
texts = [get_text_reduced(x, maxlen=512) for x in filenames]
embeddings = embedder.embed(texts)
all_embeddings[i * batch_size:(i + 1) * batch_size] = embeddings
return all_embeddings
def main():
args = arg_parse()
docs = [
os.path.join(dir, f) for dir in os.listdir(args.root)
for f in os.listdir(os.path.join(args.root, dir))
]
docs = sorted(docs)
index = Indexer(docs, args.index, args.root)
embedder = Embedder()
# L0
q_pos, q_neg = query_expand(args.query)
# Get all OR-ed tokens
q_pos_expand = re.sub(r" ", " AND ", q_pos)
hits = index.query_boolean(q_pos_expand.split())
# Remove all NOT-ed tokens
if q_neg:
for token in q_neg.split():
term = index.stemmer.stem(token)
try:
not_posting = index.tfidf(index.index[term])
except KeyError:
not_posting = []
hits = not_and_postings(not_posting, hits)
if not hits:
print("nothing found")
return
hits = sorted(hits, key=lambda item: item[1], reverse=True)
hits = hits[:args.l0_size]
# L1
doc_ids = [x[0] for x in hits]
filenames = [os.path.join(args.root, docs[i]) for i in doc_ids]
texts = [get_text_reduced(x, maxlen=512) for x in filenames]
if args.batch_size >= args.l0_size:
embeddings = embedder.embed(texts)
else:
embeddings = batch_embed(embedder, texts, args.batch_size)
query_emb = embedder.embed([q_pos])[0]
dist_cos = [cosine(query_emb, e) for e in embeddings]
idx_cos = np.argsort(dist_cos)
# Render
q_red = query_reduce(args.query)
resorted = [doc_ids[i] for i in idx_cos]
for i, id in enumerate(resorted[:args.l1_size]):
print("\n{}:".format(i))
index.render_file(q_red.split(), docs[id])
orig_pos = idx_cos[i]
print("\tL0 rank = {}; tf-idf = {:.3f}; cos-sim = {:.3f}".format(
orig_pos, hits[orig_pos][1], 1 - dist_cos[orig_pos]))
def build_model(config, src_field, tgt_field):
embed_dim = config.embed_dim
hidden_dim = config.hidden_dim
num_layers = config.num_layers
dropout_p = config.dropout_p
attention_type = config.attention
beam_width = config.beam_width
model = Seq2Seq(
LstmEncoder(Embedder(src_field, embed_dim, dropout_p), hidden_dim,
num_layers, dropout_p),
LstmDecoder(Embedder(tgt_field, embed_dim, dropout_p), hidden_dim,
num_layers, dropout_p,
build_attention(hidden_dim, attention_type), beam_width),
)
return model
def __init__(self, env, loss_fn, optim, gym=gym, preprocess_func=None, utility_func=None, embed=False, flatten=False, frameskip=1, batch_size=32, cuda=False, ale=False, init_skip=0, mid_skip=0, caution=0.0, render_skip=1):
self.n_agents = 1
if utility_func == None:
raise Exception("Need utility function")
if preprocess_func == None:
raise Exception("Need preprocess function")
if self.n_agents < 1:
raise Exception("Need at least 1 agent.")
if self.n_agents > 1:
raise NotImplementedError
super(Coach, self).__init__()
print("Initializing Coach")
self.ale = ale
self.name = env
self.gym = gym
self.dones = [False for _ in range(self.n_agents)]
self.length = 0
self.memory = Memory(self.n_agents)
self.episode = []
self.embedder = Embedder()
self.embedding = embed
self.flatten = flatten
self.best_episode = []
self.p_obs = torch.zeros(1)
self.values = []
self.frameskip = frameskip
self.loss_fn=loss_fn
self.optim = optim
self.preview = False
self.single_step = False
self.norm = True
self.render = False
self.debug_render = False
self.caution = caution#0.95
self.life = -1
self.life = -1
self.init_skip = init_skip#70
self.render_frameskip = render_skip
self.mid_skip = mid_skip#50
self.steps = 0
self.batch_size = batch_size
self.preprocess_frame = preprocess_func
self.update = utility_func
self.cuda = cuda
atexit.register(self.end)
#create environments
self.envs = [self.gym.make(self.name) for _ in range(self.n_agents)]
self.env = 0
self.actions = self.envs[0].action_space.n
os.system("toilet {}".format(self.name))
def build_model(cfg, char_voca, word_voca=None, gazet=None, pos_voca=None):
"""Build Neural Network based Ner model (Embedder + Classifier)"""
# Build Embedder
embedder = Embedder(window=cfg.window,
char_voca=char_voca,
word_voca=word_voca,
jaso_dim=cfg.jaso_dim,
char_dim=cfg.char_dim,
word_dim=cfg.word_dim,
gazet=gazet,
gazet_embed=True,
pos_enc=True,
phoneme=True,
pos_voca_size=len(pos_voca),
pos_dim=cfg.pos_dim)
print('Total Embedding_size: ', embedder.embed_dim)
encoder_name, decoder_name = cfg.model_name.lower().split('-')
# Build Encoder
if encoder_name == 'fnn5':
encoder = models.Fnn5(context_len=cfg.context_len,
in_dim=embedder.embed_dim,
hidden_dim=cfg.hidden_dim)
elif encoder_name == 'cnn7':
encoder = models.Cnn7(in_dim=embedder.embed_dim,
hidden_dim=cfg.hidden_dim)
elif encoder_name == 'cnn8':
encoder = models.Cnn8(context_len=cfg.context_len,
in_dim=embedder.embed_dim,
hidden_dim=cfg.hidden_dim)
elif encoder_name in ['gru', 'lstm', 'sru']:
encoder = models.RnnEncoder(context_len=cfg.context_len,
in_dim=embedder.embed_dim,
out_dim=cfg.hidden_dim,
cell=encoder_name)
else:
raise ValueError('unknown model name: %s' % cfg.model_name)
# Build Decoder
if decoder_name.lower() == 'fc':
decoder = models.FCDecoder(in_dim=encoder.out_dim,
hidden_dim=cfg.hidden_dim,
n_tags=cfg.n_tags)
elif decoder_name in ['gru', 'lstm', 'sru']:
decoder = models.RnnDecoder(in_dim=encoder.out_dim,
hidden_dim=cfg.hidden_dim,
n_tags=cfg.n_tags,
num_layers=cfg.num_layers,
cell=decoder_name)
model = models.Ner(embedder, encoder, decoder)
return model
def __init__(self,
trained_model_PATH,
vocabulary='./XX/vocabulary.pkl',
tag='./XX/tags.pkl',
status='raw'):
self.trained_model_PATH = trained_model_PATH
self.vocabulary = vocabulary
self.tag = tag
self.model = None
self.embedding = Embedder(vocabulary, tag)
self.loadmodel()
def embed(stego, secret, chromosome):
"""Embed secret message into the host using the chromosome"""
if len(chromosome) > 7:
chromosome = helper_individual.packchromosome(chromosome)
# Convert to a flattened pixel sequence
stego_sequence = MatScanner.scan_genetic(stego, chromosome)
secret = secret.flatten()
stego_sequence = Embedder.embed(stego_sequence, secret, chromosome)
# Reshape the stego image
return MatScanner.reshape_genetic(stego_sequence, stego.shape, chromosome)
class Application:
def __init__(self):
self.messenger = Messenger()
self.embedder = Embedder()
def start(self):
text = self.messenger.get_text()
if text is not None:
lang = detect(text)
if lang == "en" or lang == "ne":
sentences, embeddings = self.embedder.encode(text, lang)
self.messenger.send_embeddings(sentences, embeddings, lang)
def main():
embedder = Embedder()
parser = DocParser()
# iterate through grobid
with open('grobid_data.pkl', 'wb') as output:
for subdir, dirs, files in os.walk(grobid_path):
print(len(files))
count = 0
for file in files:
print(count)
count += 1
# print(os.path.join(subdir, file))
doc = parser.parseXML(os.path.join(subdir, file))
doc.id = str(file).split('.')[0]
if len(doc.abstract) == 0:
continue
doc.embedding = embedder.embed(doc.abstract)
# pair = variablesFromPair((doc.abstract, doc.title), word_index, embedding_map)
# if (len(pair[0]) == 0 or len(pair[1]) == 0):
# continue
# doc.embedding = encode(encoder, pair[0])
pickle.dump(doc, output, pickle.HIGHEST_PROTOCOL)
def __init__(self, vec_dim, dim, options={}):
"""
Instantiate the object and set options
"""
print("options:", options)
self.set_options(options, default)
options['ttype'] = self.get('ttype')
self.validation_graph = None
# self.bilstm = StackedBiLSTM(vec_dim, dim, options=options) # A Bi-directional LSTM
self.bilstm = SimpleBiLSTM(dim,
options=options) # A Bi-directional LSTM
self.embedder = Embedder(
vec_dim, dim, options=options
) # Embedder (mostly for upscaling incoming vectors)
self.class_weights = pu.torchvar(self.get('class_weights'),
ttype=self.get('ttype'))
# Loss functions
self.coef1 = pu.torchvar([0.1])
self.coef2 = pu.torchvar([0.2])
self.coef3 = pu.torchvar([0.3])
self.coef4 = pu.torchvar([0.4])
self.accuracyLoss = pu.AccuracyLoss()
self.skewLoss = pu.SkewedL1Loss(self.class_weights)
self.criterion_CE = nn.CrossEntropyLoss(weight=self.class_weights,
size_average=False)
self.criterion_MSE = nn.MSELoss()
self.orig_loss = None
if torch.cuda.is_available():
self.bilstm = self.bilstm.cuda()
self.coef1 = self.coef1.cuda()
self.coef2 = self.coef2.cuda()
self.coef3 = self.coef3.cuda()
self.coef4 = self.coef4.cuda()
self.accuracyLoss = self.accuracyLoss.cuda()
self.skewLoss = self.skewLoss.cuda()
self.criterion_CE = self.criterion_CE.cuda()
self.criterion_MSE = self.criterion_MSE.cuda()
self.eval_mode() # eval mode by default
def batch_embed(embedder: Embedder, texts: List[str],
batch_size: int) -> np.ndarray:
"""Get embeddings in batches if GPU memory is not enough.
Args:
embedder: Embedder with DistilBERT model.
texts: List of songs' texts.
batch_size: Batch size.
Returns:
Numpy array of (N, 768) of texts embeddings.
"""
embeddings = np.zeros((len(texts), 768))
iters = len(texts) // batch_size
if len(texts) % batch_size > 0:
iters += 1
for i in range(iters):
batch = texts[i * batch_size:(i + 1) * batch_size]
emb_batch = embedder.embed(batch)
embeddings[i * batch_size:(i + 1) * batch_size] = emb_batch
return embeddings
def __init__(self, cfg):
super(GenericModel, self).__init__()
self.cfg = cfg
self.embedder = Embedder(cfg['embedder'])
self.reasoner = Reasoner(cfg['reasoner'])
# epochs for METN pre training
if args.property is 'QED':
embedder_epochs_num = 1
elif args.property is 'DRD2':
embedder_epochs_num = 12
else:
print("property must bt 'QED 'or 'DRD2'")
exit()
if args.conditional or args.no_pre_train:
embedder_epochs_num = 0
if args.is_CDN is True:
_, _, boundaries = create_dataset(args.property, rebuild_dataset=False)
dataset_CDN = Dataset('dataset/' + args.property + '/CDN/CDN')
model_CDN = Embedder(dataset_CDN, 'CDN', args).to(device)
embedder_epochs_num = args.epochs
fit(args, model_CDN, embedder_epochs_num, boundaries, is_validation=True)
exit()
# prepare dataset
dataset_file_A, dataset_file_B, boundaries = create_dataset(args.property, args.rebuild_dataset)
dataset_A = Dataset(dataset_file_A, use_atom_tokenizer=args.tokenize, isB=False)
dataset_B = Dataset(dataset_file_B, use_atom_tokenizer=args.tokenize, isB=True)
# create and pre-train the embedders (METNs)
model_A = Embedder(dataset_A, 'Embedder A', args).to(device)
fit(args, model_A, embedder_epochs_num, boundaries, is_validation=True)
model_B = Embedder(dataset_B, 'Embedder B', args).to(device)
fit(args, model_B, embedder_epochs_num, boundaries, is_validation=False)
from detectors import DetectorSSD, DetectorVJ, DetectorHOG, DetectorMMOD, DetectorLBP
from embedder import Embedder
from recognizer import Recognizer
import recognize_process as rp
detector_vj = DetectorVJ()
detector_ssd = DetectorSSD()
detector_hog = DetectorHOG()
detector_mmod = DetectorMMOD()
detector_lbp = DetectorLBP()
embedder = Embedder()
recognizer = Recognizer()
# вычисление областей ROI всеми детекторами на датасете
def calc_all_detectors():
print('Haar detector calculating...')
detector_vj.calc_dataset()
print('SSD detector calculating...')
detector_ssd.calc_dataset()
print('HOG detector calculating...')
detector_hog.calc_dataset()
print('MMOD detector calculating...')
detector_mmod.calc_dataset()
print('LBP detector calculating...')
detector_lbp.calc_dataset()
for part in parts:
if len(part.split()) > 1:
labels.append(part.split()[0] +
''.join(''.join([w[0].upper(), w[1:].lower()])
for w in part.split()[1:]))
if useSynonyms:
predicates = [max(part.split(), key=len) for part in parts]
if predicates is not None and len(predicates) > 0:
for predicate in predicates:
for part in list(parts):
if predicate in part:
for syn in gloveModel.gloveModel.most_similar(
predicate.lower()):
parts.append(part.replace(predicate, syn[0]))
if len(parts) == 0:
resultsExists = False
parts = list(splitter.split(gen_question, min=minLen, max=maxLen))
# create embedder part
vectors = []
for part in parts:
vectors.append(gloveModel.getVector(part))
return vectors, parts, pos, gen_question, labels, resultsExists
# ===== main testing =====
if __name__ == "__main__":
pp(
processQuestion(Embedder('../glove.6B.50d.txt'),
'who was named as president of the USA',
useAPI=True,
useSynonyms=True))
def __init__(self):
self.messenger = Messenger()
self.embedder = Embedder()
class StackedBiLSTM(nn.Module):
"""
Bi-directional Stacked LSTM, designed to read a whole line and make predictions on each interstitial. The stacking is done
simply by using two LSTMs where there was previously one. They feed into each other before producing output.
For a line containing N characters, N-1 predictions will be made.
This layer also commands the "underlying" layers: left2right (A and B), right2left, splitLayer.
This layer takes care of setting modes, and saving / loading.
"""
def __init__(self, vec_dim, dim, options={}):
"""
Instantiate the Layer (which will later be used to connect tensors)
Parameters
----------
vec_dim : int (width of the vector generated by the vectorizer)
dim : int (width of vectors in the rest of the network)
"""
super(StackedBiLSTM, self).__init__()
# Embedder (mostly to upscale the incoming character vectors)
self.embedder = Embedder(vec_dim, dim)
# Left to right Stacked LSTM
self.left2rightA = LSTMCell(dim, options=options) # Outputs two length-dim vectors
self.left2rightB = LSTMCell(dim, options=options) # Outputs two length-dim vectors
# Right to left Stacked LSTM
self.right2leftA = LSTMCell(dim, options=options) # Outputs two length-dim vectors
self.right2leftB = LSTMCell(dim, options=options) # Outputs two length-dim vectors
# Output decision layer
self.splitLayer = SplitLayer(dim, options=options) # Outputs a one-dimensional length-2 vector
self.Lzeros = pu.var_zeros(dim, ttype=options.get('ttype')) # Zeros for initialization from left
self.Lhzeros = pu.var_zeros(dim, ttype=options.get('ttype')) # Zeros for initialization (hidden layer)
self.Rzeros = pu.var_zeros(dim, ttype=options.get('ttype')) # same, for the right
self.Rhzeros = pu.var_zeros(dim, ttype=options.get('ttype'))
self.training = False # By default, but set to True during training with 'train()'
def get_parameters(self):
"""
Return a list of trainable parameters for the PyTorch optimizer
"""
parameters = list(self.parameters())
parameters.extend( list( self.embedder.parameters() ))
parameters.extend( list( self.left2rightA.parameters() ))
parameters.extend( list( self.left2rightB.parameters() ))
parameters.extend( list( self.right2leftA.parameters() ))
parameters.extend( list( self.right2leftB.parameters() ))
parameters.extend( list( self.splitLayer.parameters() ))
return parameters
def training_mode(self):
"""
Set models for training mode
"""
self.train()
self.embedder.train()
self.left2rightA.train()
self.left2rightB.train()
self.right2leftA.train()
self.right2leftB.train()
self.splitLayer.train()
def eval_mode(self):
"""
Set models for evaluation mode, which has, for instance, no dropout
"""
self.eval()
self.embedder.eval()
self.left2rightA.eval()
self.left2rightB.eval()
self.right2leftA.eval()
self.right2leftB.eval()
self.splitLayer.eval()
def save(self, dirpath):
"""
Save the current state of the model
"""
try:
torch.save(self.state_dict(), dirpath+'/StackedBiLSTM.pth')
except:
raise
self.embedder.save(dirpath)
self.left2rightA.save(dirpath, '/left2rightA.pth')
self.left2rightB.save(dirpath, '/left2rightB.pth')
self.right2leftA.save(dirpath, '/right2leftA.pth')
self.right2leftB.save(dirpath, '/right2leftB.pth')
self.splitLayer.save(dirpath)
def load(self, dirpath):
"""
Load the models from a specified directory. Toss exceptions because models won't exist on the first run.
"""
try:
state_dict = torch.load(dirpath+'/StackedBiLSTM.pth', map_location=lambda storage, loc: storage)
except:
pass
self.embedder.load(dirpath)
self.left2rightA.load(dirpath, '/left2rightA.pth')
self.left2rightB.load(dirpath, '/left2rightB.pth')
self.right2leftA.load(dirpath, '/right2leftA.pth')
self.right2leftB.load(dirpath, '/right2leftB.pth')
self.splitLayer.load(dirpath)
def forward(self, line):
"""
The 'forward()' for this network. This function takes one sample at a time, where each sample is a line of text.
Each LSTM, as it proceeds character by character, it makes a prediction *after* having consumed the character on both sides of an interstice.
Parameters
----------
line : (tensor) list of N vectors (where each vector represents one character)
Returns
-------
(tensor) list of N-1 pairs (each pair of floats represents one interstice-- both the probability of no split and yes split)
"""
inputs = [] # List of list of tensor. Will hold the cell and hidden states at each possible split location
# i.e. the value associated with the first interstice will be at index 0, etc.
### Run line through the left2right LSTM ###
LCA = self.Lzeros # left2right cell state
LHA = self.Lhzeros # left2right hidden state
LCB = self.Lzeros # same for right2left ...
LHB = self.Lhzeros
num = 0
loc = 0 # First interstice is number 0
for x in line:
x = self.embedder(x)
# Get the states for interstice number 'loc'
LCA, LHA = self.left2rightA(x, LCA, LHA) # Run this character through the Left->-Right LSTM
LCB, LHB = self.left2rightB(LHA, LCB, LHB) # Run this character through the second Left->-Right LSTM
# If we have consumed at least two characters, we will store our first output, which applies to the interstice between the last two characters
if num >= 1:
inputs.append( [LCB, LHB] )
assert(inputs[loc] == [LCB, LHB])
assert(len(inputs[loc]) == 2)
loc += 1 # For instance, loc=0 represents interstitial between the first and second char
num += 1
### Run line through the right2left LSTM ###
RCA = self.Rzeros
RHA = self.Rhzeros
RCB = self.Rzeros
RHB = self.Rhzeros
num = 0
for x in reversed(line): # Iterate backwards through the same list of vectors
x = self.embedder(x)
# Get the states for interstice number 'loc'
RCA, RHA = self.right2leftA(x, RCA, RHA) # Run this character through the Right->-Left LSTM
RCB, RHB = self.right2leftB(RHA, RCB, RHB) # Run this character through the second Right->-Left LSTM
if num >= 1:
loc -= 1 # Keep this process in reverse alignment with the other
try:
inputs[loc].extend([RCB, RHB])
assert(len(inputs[loc]) == 4)
except:
raise
num += 1 # Just to keep track of how many characters we've consumed
### Combine output from both LSTMs and run through the SplitLayer ###
# 'preds' will have one fewer element than 'line' because each prediction applies to the interstitial between two elements of 'line'
preds = None
for item in inputs:
LC, LH, RC, RH = item # Just the output from the second layer of each stacking
pred = self.splitLayer(LH, RH) # Splitter layer takes as input the hidden state from both directions
pred = torch.unsqueeze(pred, 0) # Add a dimension so that 'tensor_cat()' will work correctly
if preds is None:
preds = pred
else:
preds = pu.tensor_cat(preds, pred, 0) # Build a stack of tensors
try:
assert(len(line) - 1 == len(preds))
except:
err([preds, len(line), len(preds)])
raise
return preds
CARRIER = "../Carrier2.jpg"
BIOMETRIC = "../FingerPrint.png"
EXPECTED = "./Expected.png"
biometric = cv2.imread(BIOMETRIC)
carrier = cv2.imread(CARRIER)
expected = cv2.cvtColor(cv2.imread(EXPECTED), cv2.COLOR_BGR2GRAY)
BIOMETRIC_SIZE = biometric.shape[0]
actualSize = carrier.shape
corners = [[0, 0], [0, 0], [0, 0], [0, 0]]
embedded = carrier.copy()
em = Embedder(PASSES, KEY, CHANNELS, DEPTH, MASK)
ex = Extractor(PASSES, KEY, ~MASK, SHIFT)
em_psnr = []
ex_psnr = []
for iteration in range(ITERATIONS):
embedded = em.embed(biometric, embedded)
filename = './CarrierVsRecoved/Iteration_' + str(iteration) + '.jpg'
cv2.imwrite(filename, embedded)
embedded = cv2.imread(filename)
em_psnr.append(cv2.PSNR(carrier, embedded))
extracted = ex.extract(embedded, corners, actualSize, BIOMETRIC_SIZE)
ex_psnr.append(cv2.PSNR(expected, extracted))
print(iteration, em_psnr[-1], ex_psnr[-1])
def recognize_video(detector,
embedder: Embedder,
recognizer: Recognizer,
detector_params='default',
source=0):
# инициализация видеопотока
print('Starting video stream...')
vs = VideoStream(src=source).start()
if not is_detector(detector):
raise TypeError('Incorrect type of detector')
# разогрев камеры
time.sleep(0.5)
# запуск оценщика пропускной способности FPS
fps = FPS().start()
# цикл по фреймам из видео
while True:
frame = vs.read()
if detector_params == 'default':
faces_roi, boxes = detector.calc_image(frame, return_mode='both')
elif type(detector) == DetectorSSD:
confidence = detector_params[0]
faces_roi, boxes = detector.calc_image(frame,
confidence=confidence,
return_mode='both')
elif type(detector) == DetectorVJ or type(detector) == DetectorLBP:
[scale_factor, min_neighbors] = detector_params
faces_roi, boxes = detector.calc_image(frame,
scale_factor=scale_factor,
min_neighbors=min_neighbors,
return_mode='both')
elif type(detector) == DetectorHOG or type(detector) == DetectorMMOD:
upsampling_times = detector_params[0]
faces_roi, boxes = detector.calc_image(
frame, upsampling_times=upsampling_times, return_mode='both')
for i in range(len(faces_roi)):
embeddings = embedder.calc_face(faces_roi[i])
name = recognizer.recognize(embeddings)
start_x, start_y, end_x, end_y = boxes[i]
text = '{}'.format(name)
y = start_y - 10 if start_y - 10 > 10 else start_y + 10
cv2.rectangle(frame, (start_x, start_y), (end_x, end_y),
(0, 0, 255), 2)
cv2.putText(frame, text, (start_x, y), cv2.FONT_HERSHEY_SIMPLEX,
0.45, (0, 0, 255), 2)
# обновление счетчика FPS
fps.update()
# показ выходного фрейма
cv2.imshow('Frame', frame)
key = cv2.waitKey(1) & 0xFF
# завершение при нажатии 'q'
if key == ord("q"):
break
fps.stop()
print('Elasped time: {:.2f}'.format(fps.elapsed()))
print('Approx. FPS: {:.2f}'.format(fps.fps()))
cv2.destroyAllWindows()
vs.stop()
def recognize_image(detector,
embedder: Embedder,
recognizer: Recognizer,
image,
detector_params='default',
showing=True,
saving_path=''):
image_t = type(image)
if image_t is str:
image = image.replace('/', os.path.sep)
image = cv2.imread(image)
elif image_t is list:
image = np.array(image)
if not is_detector(detector):
raise TypeError('Incorrect type of detector')
# вызов детектора с заданными параметрами
if detector_params == 'default':
faces_roi, boxes = detector.calc_image(image, return_mode='both')
elif type(detector) == DetectorSSD:
confidence = detector_params[0]
faces_roi, boxes = detector.calc_image(image,
confidence=confidence,
return_mode='both')
elif type(detector) == DetectorVJ or type(detector) == DetectorLBP:
[scale_factor, min_neighbors] = detector_params
faces_roi, boxes = detector.calc_image(image,
scale_factor=scale_factor,
min_neighbors=min_neighbors,
return_mode='both')
elif type(detector) == DetectorHOG or type(detector) == DetectorMMOD:
upsampling_times = detector_params[0]
faces_roi, boxes = detector.calc_image(
image, upsampling_times=upsampling_times, return_mode='both')
# для каждого обнаруженного лица
for i in range(len(faces_roi)):
# получение признаков
embeddings = embedder.calc_face(faces_roi[i])
# получение класса
name = recognizer.recognize(embeddings)
start_x, start_y, end_x, end_y = boxes[i]
# рисование ограничительной рамки лица, написание имени
text = '{}'.format(name)
y = start_y - 10 if start_y - 10 > 10 else start_y + 10
cv2.rectangle(image, (start_x, start_y), (end_x, end_y), (255, 0, 0),
4)
cv2.putText(image, text, (start_x, y), cv2.FONT_HERSHEY_SIMPLEX, 1.5,
(255, 0, 0), 4)
if saving_path != '':
cv2.imwrite(saving_path, image)
# если нужно вывести изоражение на экран
if showing:
cv2.imshow('Image', image)
cv2.waitKey(0)
carrier = gl.washBitDepth(carrier, ~GUIDE_MASK)
carrier = gl.generateGuideLines(carrier, GUIDE_MASK)
x1 = int(CARRIER_SIZE[0] / 2) - int(CARRIER_SIZE[0] / 4)
x2 = int(CARRIER_SIZE[0] / 2) + int(CARRIER_SIZE[0] / 4)
y1 = int(CARRIER_SIZE[1] / 2) - int(CARRIER_SIZE[1] / 4)
y2 = int(CARRIER_SIZE[1] / 2) + int(CARRIER_SIZE[1] / 4)
crop = (x1, y1, x2, y2)
untouched = carrier[crop[0]:crop[2], crop[1]:crop[3]]
em_psnr = []
ex_psnr = []
for passes in range(MAX_PASSES):
em = Embedder(passes, KEY, CHANNELS, DEPTH, MASK)
ex = Extractor(passes, KEY, ~MASK, SHIFT)
embedded = em.embed(biometric, carrier)
cropped = embedded[crop[0]:crop[2], crop[1]:crop[3]]
margins = gl.getMargins(cropped, GUIDE_MASK)
corners = gl.marginsToCorners(margins)
actualSize = gl.getActualSize(cropped, margins)
extracted = ex.extract(cropped, corners, actualSize, BIOMETRIC_SIZE)
ex_psnr.append(cv2.PSNR(expected, extracted))
em_psnr.append(cv2.PSNR(np.uint8(cropped), np.uint8(untouched)))
print(passes, em_psnr[-1], ex_psnr[-1])
cv2.imwrite('./final.png', extracted)
for pos in range(max_seq_len):
for i in range(0, d_model, 2):
pe[pos, i] = math.sin(pos / (10000**((2 * i) / d_model)))
pe[pos,
i + 1] = math.cos(pos / (10000**((2 * (i + 1)) / d_model)))
self.pe = pe.unsqueeze(0)
self.pe.requires_grad = False
def forward(self, x) -> torch.Tensor:
ret = math.sqrt(self.d_model) * x + self.pe
return ret
if __name__ == "__main__":
train_dl, val_dl, test_dl, TEXT = get_IMDb_Dataloaders_and_TEXT(
max_length=256, batch_size=24)
batch = next(iter(train_dl))
net1 = Embedder(TEXT.vocab.vectors)
net2 = PositionalEncoder(d_model=300, max_seq_len=256)
with timer("forward"):
x = batch.Text[0]
x1 = net1(x)
x1 = x1.to(device)
x2 = net2(x1)
assert x1.shape == torch.Size([24, 256, 300])
assert x2.shape == torch.Size([24, 256, 300])
def __init__(
self,
params,
input_vocabulary,
output_vocabulary,
anonymizer):
self.params = params
self._pc = dy.ParameterCollection()
if params.new_version:
self.controller = Controller(output_vocabulary)
else:
self.controller = None
# Create the input embeddings
self.input_embedder = Embedder(self._pc,
params.input_embedding_size,
name="input-embedding",
vocabulary=input_vocabulary,
anonymizer=anonymizer)
# Create the output embeddings
self.output_embedder = Embedder(self._pc,
params.output_embedding_size,
name="output-embedding",
vocabulary=output_vocabulary,
anonymizer=anonymizer)
# Create the encoder
encoder_input_size = params.input_embedding_size
if params.discourse_level_lstm:
encoder_input_size += params.encoder_state_size / 2
self.utterance_encoder = Encoder(params.encoder_num_layers,
encoder_input_size,
params.encoder_state_size,
self._pc)
# Positional embedder for utterances
attention_key_size = params.encoder_state_size
if params.state_positional_embeddings:
attention_key_size += params.positional_embedding_size
self.positional_embedder = Embedder(
self._pc,
params.positional_embedding_size,
name="positional-embedding",
num_tokens=params.maximum_utterances)
# Create the discourse-level LSTM parameters
if params.discourse_level_lstm:
self.discourse_lstms = du.create_multilayer_lstm_params(
1, params.encoder_state_size, params.encoder_state_size / 2, self._pc, "LSTM-t")
self.initial_discourse_state = du.add_params(self._pc, tuple(
[params.encoder_state_size / 2]), "V-turn-state-0")
# Snippet encoder
final_snippet_size = 0
if params.use_snippets and not params.previous_decoder_snippet_encoding:
snippet_encoding_size = int(params.encoder_state_size / 2)
final_snippet_size = params.encoder_state_size
if params.snippet_age_embedding:
snippet_encoding_size -= int(
params.snippet_age_embedding_size / 4)
self.snippet_age_embedder = Embedder(
self._pc,
params.snippet_age_embedding_size,
name="snippet-age-embedding",
num_tokens=params.max_snippet_age_embedding)
final_snippet_size = params.encoder_state_size \
+ params.snippet_age_embedding_size / 2
self.snippet_encoder = Encoder(params.snippet_num_layers,
params.output_embedding_size,
snippet_encoding_size,
self._pc)
token_predictor = construct_token_predictor(self._pc,
params,
output_vocabulary,
attention_key_size,
final_snippet_size,
anonymizer)
# 注意：此处在input增加了decoder_state_size维度
self.decoder = SequencePredictor(
params,
params.output_embedding_size +
attention_key_size + params.decoder_state_size,
self.output_embedder,
self._pc,
token_predictor)
self.trainer = dy.AdamTrainer(
self._pc, alpha=params.initial_learning_rate)
self.dropout = 0.
def make_dataset(images_path='dataset'):
detector = DetectorSSD()
embedder = Embedder()
images_path = images_path.replace('/', os.path.sep)
ind_image_paths = list(paths.list_images(images_path))
# списки для лиц и имен, взаимосоответствующие по индексу
known_ems = []
known_names = []
for (i, image_path) in enumerate(ind_image_paths):
print(i + 1)
# получение имя из пути к файлу
name = image_path.split(os.path.sep)[-2]
image = cv2.imread(image_path)
# ОБЫЧНОЕ
temp_img = image.copy()
face = detector.calc_image(temp_img)[0]
embeddings = embedder.calc_face(face)
known_ems.append(embeddings.flatten())
known_names.append(name)
# ТЕМНЕЕ 4
for i in range(1, 5):
temp_img = image.copy()
face = detector.calc_image(ie.darken(temp_img, i / 10))
if len(face) > 0:
embeddings = embedder.calc_face(face[0])
known_ems.append(embeddings.flatten())
known_names.append(name)
# СВЕТЛЕЕ 4
for i in range(1, 5):
temp_img = image.copy()
face = detector.calc_image(ie.brighten(temp_img, i / 10))
if len(face) > 0:
embeddings = embedder.calc_face(face[0])
known_ems.append(embeddings.flatten())
known_names.append(name)
# ДОЖДЬ 3
temp_img = image.copy()
face = detector.calc_image(ie.add_rain(temp_img, rain_type='drizzle'))
if len(face) > 0:
embeddings = embedder.calc_face(face[0])
known_ems.append(embeddings.flatten())
known_names.append(name)
temp_img = image.copy()
face = detector.calc_image(ie.add_rain(temp_img, rain_type='heavy'))
if len(face) > 0:
embeddings = embedder.calc_face(face[0])
known_ems.append(embeddings.flatten())
known_names.append(name)
temp_img = image.copy()
face = detector.calc_image(
ie.add_rain(temp_img, rain_type='torrential'))
if len(face) > 0:
embeddings = embedder.calc_face(face[0])
known_ems.append(embeddings.flatten())
known_names.append(name)
# ТУМАН 4
for i in range(1, 5):
temp_img = image.copy()
face = detector.calc_image(ie.add_fog(temp_img, i / 10))
if len(face) > 0:
embeddings = embedder.calc_face(face[0])
known_ems.append(embeddings.flatten())
known_names.append(name)
embeddings = {'embeddings': known_ems, 'names': known_names}
f = open('weather_ems/ems_weather_4.pickle', 'wb')
f.write(pickle.dumps(embeddings))
f.close()
print(len(known_ems), len(known_names))
return known_ems, known_names