def encode(self, sents):
batches = []
for b in range(0, len(sents), self.chunck_size):
tokens = [
self.tokenizer.encode(x)[:self.max_length]
for x in sents[b:b + self.chunck_size]
] # tokenize
# tokens = [self.tokenizer.convert_tokens_to_ids(x) for x in tokens] # convert to ids
tokens = torch.tensor(zero_padding(tokens)).transpose(
0, 1) # padding and into tensors
batches.append(tokens)
# print(tokens)
# break
# query the
cpu = torch.device('cpu')
out = []
clear_cache = 32
with torch.no_grad():
counter = 0
for batch in tqdm(batches):
batch = batch.to(self.device)
hidden_states = self.model(batch)[0]
# print(hidden_states)
out.append(hidden_states[:, -1, :].to(cpu).numpy())
counter += 1
# if(counter >= clear_cache):
# counter = 0
# torch.cuda.empty_cache()
return np.concatenate(out, axis=0)
def encode(self, sents):
batches = []
for b in range(0, len(sents), self.chunck_size):
tokens = [
self.tokenizer.tokenize(x)[:self.max_length]
for x in sents[b:b + self.chunck_size]
] # tokenize
tokens = [self.tokenizer.convert_tokens_to_ids(x) for x in tokens]
tokens = torch.tensor(zero_padding(tokens)).transpose(
0, 1) # padding and into tensors
batches.append(tokens)
# print(tokens)
# break
# query the
cpu = torch.device('cpu')
out = []
clear_cache = 32
with torch.no_grad():
counter = 0
for batch in tqdm(batches):
batch = batch.to(self.device)
hidden_states = self.model(
batch
)[0] # how to use the embedding: https://github.com/zihangdai/xlnet/blob/master/modeling.py @func: summarize_sequences
# print(mems.size())
# print(hidden_states[-1].size())
out.append(hidden_states[:, -1, :].to(cpu).numpy())
counter += 1
# if(counter >= clear_cache):
# counter = 0
# torch.cuda.empty_cache()
return np.concatenate(out, axis=0)
def encode(self, sents):
batches = []
# print(sents)
for b in range(0, len(sents), self.chunck_size):
tokens = [
self.tokenizer.encode(
x, add_special_tokens=(
self.name == 'roberta'))[:self.max_length]
for x in sents[b:b + self.chunck_size]
] # tokenize
# print(tokens)
# print([len(x) for x in tokens])
# print([len(x) for x in sents[b:b+self.chunck_size]])
tokens = torch.tensor(zero_padding(tokens)).transpose(
0, 1) # padding and into tensors
batches.append(tokens)
# print(tokens)
# break
# query the
cpu = torch.device('cpu')
out = []
with torch.no_grad():
counter = 0
for batch in (batches):
batch = batch.to(self.device)
hidden_states = self.model(batch)[0]
if (self.pooling == 'mean'):
sent_emb = hidden_states.mean(dim=1)
elif (self.pooling == 'first'):
sent_emb = hidden_states[:, 0, :]
else:
sent_emb = hidden_states[:, -1, :]
out.append(sent_emb.to(cpu).numpy())
counter += 1
return np.concatenate(out, axis=0)
def compress_speck(path, dest_path, dec_level, bpp):
if path[-1] != "/":
path += "/"
info = pickle.load(open(path + "info.dat", "r"))
if not os.path.exists(dest_path):
os.makedirs(dest_path)
codec = sk.speck()
info.wavelet = "cdf97"
info.wavelet_level = dec_level
info.frames = 3
info.bpp = bpp
for c in range(info.frames):
frame = cv2.imread(path + str(c) + ".png",
cv2.CV_LOAD_IMAGE_GRAYSCALE)
info.cols = frame.shape[1]
info.rows = frame.shape[0]
frame = tools.zero_padding(frame)
info.wavelet_cols = frame.shape[1]
info.wavelet_rows = frame.shape[0]
wavelet = lwt.cdf97(frame, dec_level)
wavelet = tools.quant(wavelet, 0.00001)
coded_frame = codec.compress(wavelet, bpp)
stream = dict()
stream["wise_bit"] = coded_frame[3]
stream["payload"] = coded_frame[4]
try:
pickle.dump(stream, open(dest_path + str(c) + ".speck", "wb"))
except:
print "Failed to create: " + dest_path + str(c) + ".speck"
pickle.dump(info, open(dest_path + "info.dat", "w"))
def encode(self, sents):
batches = []
for b in range(0, len(sents), self.chunck_size):
tokens = [self.tokenizer.encode(x)[:self.max_length] for x in sents[b:b + self.chunck_size]] # tokenize
tokens = torch.tensor(zero_padding(tokens)).transpose(0, 1) # padding and into tensors
batches.append(tokens)
# print(tokens)
# break
# query the
cpu = torch.device('cpu')
out = []
with torch.no_grad():
counter = 0
for batch in tqdm(batches):
batch = batch.to(self.device)
hidden_states = self.model(batch)[0]
out.append(hidden_states[:, -1, :].to(cpu).numpy())
counter += 1
return np.concatenate(out, axis=0)
def compress_motion_speck(path, dest_path, bpp, dec_level=4,
macroblock_size=8, fixed_keyframe=0):
"""This method compress a image sequence from a directory using speck and
motion compensation.
Args:
path: The directory where the image sequence to be encoded is stored
dest_path: A destination directory where the encoded frames will be
stored
bpp: Compression ratio on bits per pixel
Kwargs:
dec_level: Level of wavelet decomposition to be used
macroblock_size: size of the macroblock used for motion compensation
fixed_keyframe: size of the Group of Pictures
"""
if path[-1] != "/":
path += "/"
info = pickle.load(open(path + "info.dat", "r"))
is_key = 0
info.fixed_keyframe = fixed_keyframe
info.full_size = 1
if not os.path.exists(dest_path):
os.makedirs(dest_path)
info.macroblock_size = macroblock_size
codec = sk.speck()
info.wavelet = "cdf97"
info.wavelet_level = dec_level
info.full_size = 100
for c in range(info.frames):
original_frame = cv2.imread(path + str(c) + ".png",
cv2.CV_LOAD_IMAGE_GRAYSCALE)
info.cols = original_frame.shape[1]
info.rows = original_frame.shape[0]
frame = tools.zero_padding(original_frame)
info.wavelet_cols = frame.shape[1]
info.wavelet_rows = frame.shape[0]
if is_key == 0:
wavelet = lwt.cdf97(frame, dec_level)
wavelet = tools.quant(wavelet, 0.0001)
coded_frame = codec.compress(wavelet, bpp)
stream = dict()
stream["wise_bit"] = coded_frame[3]
stream["payload"] = coded_frame[4]
try:
pickle.dump(stream, open(dest_path + str(c) + ".speck", "wb"))
except:
print "Failed to create: " + dest_path + str(c) + ".png"
iwave = codec.expand(coded_frame[4], frame.shape[1],
frame.shape[0], dec_level, coded_frame[3])
iframe = lwt.icdf97(iwave)
is_key = fixed_keyframe - 1
key_frame = iframe
info.motion_vectors += [0]
else:
p_frame, mvs = intraframe.encode_motion_frame(frame,
key_frame,
macroblock_size,
info.full_size)
info.motion_vectors += [(mvs)]
is_key -= 1
wavelet = lwt.cdf97(p_frame, dec_level)
wavelet = tools.quant(wavelet, 0.0001)
coded_frame = codec.compress(wavelet, bpp)
stream = dict()
stream["wise_bit"] = coded_frame[3]
stream["payload"] = coded_frame[4]
try:
pickle.dump(stream, open(dest_path + str(c) + ".speck", "wb"))
except:
print "Failed to create: " + dest_path + str(c) + ".png"
pickle.dump(info, open(dest_path + "info.dat", "w"))
