def process (self, filename):
curSize = 0
progress = Progress(filename, 0, os.stat(filename)[6])
for ln in open(filename):
if ln.startswith('RF'):
self.processRF(ln)
curSize += len(ln)
progress.update(curSize)
def __init__(self, tag: str, from_top: bool = True):
self.base_url = (f'https://archiveofourown.org/tags/'
f'{quote(tag).replace(".", "*d*")}/works?page=')
tag_path = paths.tag_path(tag)
self.progress = Progress(tag_path)
self.last = self.progress.read()[0]
self.path = paths.meta_path(tag)
log_path = paths.meta_log_path(tag)
super().__init__(tag + '_meta', log_path)
self.from_top = self._start_from_top(from_top)
def main(argv=None):
_init_output_directories()
# step 1: create the negatives and positives directory
if FLAGS.do_full_prepare:
print('Loading labels from %s' % FLAGS.label_file)
lr = LabelRecord()
label_records = lr.load(FLAGS.label_file)
all_bounding_boxes = Box.get_all_bounding_boxes(label_records)
counter = 0
# fill examples, originals, negatives, and positives directories
print('Processing images...')
for (_, v) in label_records.items():
Progress.show_progress(counter)
image = CXRImage.get_image_data(v.filename, FLAGS.image_path)
basefilename = os.path.splitext(v.filename)[0]
if v.hasBoundingBox:
for i in range(0, v.boundingBoxes.shape[0]):
box = v.boundingBoxes[i, :]
#CXRImage.extract_center_and_write(image,box,1024,1024,FLAGS.positives_dir)
CXRImage.extract_anisotropic_scale_and_write(
image, box, FLAGS.image_size, FLAGS.image_size,
FLAGS.positives_dir)
CXRImage.write_image(image, FLAGS.examples_dir,
"%s.jpg" % basefilename)
else:
i = np.int32(
np.random.randint(0, all_bounding_boxes.shape[0] - 1))
box = all_bounding_boxes[i, :]
CXRImage.extract_anisotropic_scale_and_write(
image, box, FLAGS.image_size, FLAGS.image_size,
FLAGS.negatives_dir)
#CXRImage.extract_center_and_write(image,box,1024,1024,FLAGS.negatives_dir)
if (v.hasBoundingBox):
img = (CXRImage.xlate_image(image) * 255).astype(np.uint8)
CXRImage.write_image_with_bounding_boxes(
img, FLAGS.originals_dir, "%s.jpg" % basefilename,
v.boundingBoxes)
counter = counter + 1
# step 2: create the pre-training features by combining negatives and positives into pre_train.tfrecord
print('\nCreating pre-train file...')
rec = Record(1024, 1024, 1 if FLAGS.grayscale else 3)
total = rec.create_pre_train_file(FLAGS.positives_dir, FLAGS.negatives_dir,
FLAGS.pre_train_file)
print('\n%d files combined in %s' % (total, FLAGS.pre_train_file))
def process_tweets(self):
from utils.twitter.tokenizer import Tweet_Tokenizer
# for more documentation, visit:
# https://dev.twitter.com/overview/api/tweets
def extract_text(tweet_json):
try:
tweet_json["text"]
except KeyError:
return
orig_text = tweet_json["text"].lower().strip()
tweet_text = Tweet_Tokenizer.apply_regex_to_text(
orig_text, self.replace_hashtags, self.replace_links,
self.replace_user_refs)
tweet_obj = Tweet(tweet_text, orig_text)
#get, process, and package hashtags (this also stores and counts them)
hashtags = [
Hashtag(h["text"].lower())
for h in tweet_json["entities"]["hashtags"]
]
#connect hashtags to tweet and vice versa
tweet_obj.register_hashtags(hashtags)
[h.register_tweet(tweet_obj) for h in hashtags]
if self.show_progress:
with Progress("Extracting tweets",
len(self.tweet_JSON_objs)) as up:
[
up(extract_text(tweet_obj))
for tweet_obj in self.tweet_JSON_objs[0]
]
else:
print("Extracting tweets.")
[extract_text(tweet_obj) for tweet_obj in self.tweet_JSON_objs]
def process (self, filename, minlevel, maxlevel):
self.__minlevel = minlevel
self.__maxlevel = maxlevel
cursize = 0
progress = Progress(filename, 0, os.stat(filename)[6])
for ln in open(filename):
if ln.startswith('AF'):
self.processAF(ln)
elif ln.startswith('LF'):
self.processLF(ln)
elif ln.startswith('LM'):
self.processLM(ln)
elif ln.startswith('PF'):
self.processPF(ln)
cursize += len(ln)
progress.update(cursize)
def extract_batch(filelist, savedir, descobj, verbose=False):
""" Extract features/descriptors from a batch of images. Single-threaded.
This function calls an image descripor object on a batch of images in order
to extract the images descripor. If a feature/descriptor file already exists
for the image, it is skipped. This is a single-threaded pipeline.
Arguments:
filelist: A list of files of image names including their paths of images
to read and extract descriptors from
savedir: A directory in which to save all of the image features. They
are pickled objects (protocol 2) with the same name as the
image file. The object that is pickled is the return from
descobj.extract().
decobj: An image descriptor object which does the actual extraction
work. the method called is descobj.extract(image). See
descriptors.Descriptor for an abstract base class.
verbose: bool, display progress?
Returns:
True if there we any errors extracting image features. False otherwise.
If there is a problem extracting any image descriptors, a file
"errors.log" is created in the savedir directory with a list of file
names, error number and messages.
"""
# Try to make the save path
if not os.path.exists(savedir):
os.mkdir(savedir)
errflag = False
# Set up progess updates
nfiles = len(filelist)
progbar = Progress(nfiles, title="Extracting descriptors", verbose=verbose)
# Iterate through all of the images in filelist and extract features
for i, impath in enumerate(filelist):
errflag |= extract(impath, savedir, descobj)
progbar.update(i)
progbar.finished()
if errflag == True:
print('Done with errors. See the "errors.log" file in ' + savedir)
def build (self, model, grid, level):
simplify = True
self.__meshset = set()
total = 0
for mesh in model.keys():
total += 1
self.__model = model
counter = 0
progress = Progress(("construct<%d>...." % level), 0, total)
for mesh, parcel in self.__model.items():
mainmap = MainMapBuilder()
rect = grid.getMeshRect(mesh)
bin = mainmap.build(parcel, rect, simplify)
offset = self.__stream.tell()
self.__stream.write(bin)
self.__index_builder.registerParcel(mesh, offset, len(bin))
counter += 1
progress.update(counter)
def process(self, level):
# enum
meshList = set()
if level == 0:
for meshId in self.__modelSrc.keys():
meshList.add(meshId)
else:
for meshId in self.__modelSrc.keys():
meshList.add(self.__grid.getUpperMesh(meshId))
# construct
counter = 0
progress = Progress(("building <%d>...." % level), 0, len(meshList))
for meshId in meshList:
progress.update(counter); counter += 1
parcel = self.__constructParcel(meshId)
if parcel:
self.__modelOut.put(meshId, parcel)
pass
return None
def AddSequences():
"""Creates one training, validation."""
errors = []
# Generate datasets file lists.
sequences = FindPatternFiles(FLAGS.input_dir, FLAGS.view_pattern, errors)
num_frames = PrintSequencesInfo(sequences,
'Found the following datasets and files:')
# Sharding and randomizing sets.
if FLAGS.max_per_shard > 0:
sequences = ShardSequences(sequences, FLAGS.max_per_shard)
num_frames = PrintSequencesInfo(sequences, 'After sharding:')
tf.logging.info('')
# Process sets.
progress = Progress(num_frames)
output_list = []
for sequence in sequences:
record_name = os.path.join(FLAGS.output_dir,
'%s.tfrecord' % sequence['name'])
if tf.gfile.Exists(record_name) and not FLAGS.overwrite:
ok, num_frames = CheckRecord(record_name, sequence)
if ok:
progress.Add(num_frames)
tf.logging.info('Skipping existing output file: %s' %
record_name)
continue
else:
tf.logging.info(
'File does not match sequence, reprocessing...')
output_dir = os.path.dirname(record_name)
if not tf.gfile.Exists(output_dir):
tf.logging.info('Creating output directory: %s' % output_dir)
tf.gfile.MakeDirs(output_dir)
output_list.append(record_name)
tf.logging.info('Writing to ' + record_name)
writer = tf.python_io.TFRecordWriter(record_name)
AddSequence(sequence, writer, progress, errors)
writer.close()
tf.logging.info('Wrote dataset files: ' + str(output_list))
tf.logging.info('All errors (%d): %s' % (len(errors), str(errors)))
def main():
# load data
mnist = input_data.read_data_sets(args.dataset_path + 'MNIST_data',
one_hot=True)
# we can access to images like this:
# images = mnist.train.images; images.shape = []
# labels = mnist.train.labels; each label is a probability distribution.
print(mnist.train.num_examples)
max_epoch = args.max_epoch
max_loop_z = args.max_loop_z
with tf.Graph().as_default():
config = Config()
# model = MLP(config)
model = DCGN(config)
tf.get_default_graph().finalize()
progress = Progress()
n_batch_loop = int(mnist.train.num_examples / config.batch_size)
for epoch in range(max_epoch):
sum_cost = 0
progress.start_epoch(epoch, max_epoch)
for t in range(n_batch_loop):
# batch_X: batch_size x n_input
# batch_y: batch_size
batch_X, batch_y = mnist.train.next_batch(config.batch_size,
shuffle=False)
batch_indices = np.arange(
t * config.batch_size,
t * config.batch_size + config.batch_size)
for z_t in range(max_loop_z):
cost_z = model.forward_backprop_z(batch_X, batch_indices)
model.project_z_L2()
#print(cost_z)
cost_per_sample = model.forward_backprop_theta(
batch_X, batch_indices)
sum_cost += cost_per_sample
# model.increaseBatchID()
if t % 10 == 0:
progress.show(t, n_batch_loop, {})
print("cost: {}".format(sum_cost / n_batch_loop))
model.save(epoch, args.model_dir)
def extract_batch(filelist, savedir, descobj, verbose=False):
""" Extract features/descriptors from a batch of images. Single-threaded.
This function calls an image descripor object on a batch of images in order
to extract the images descripor. If a feature/descriptor file already exists
for the image, it is skipped. This is a single-threaded pipeline.
Arguments:
filelist: A list of files of image names including their paths of images
to read and extract descriptors from
savedir: A directory in which to save all of the image features. They
are pickled objects (protocol 2) with the same name as the
image file. The object that is pickled is the return from
descobj.extract().
decobj: An image descriptor object which does the actual extraction
work. the method called is descobj.extract(image). See
descriptors.Descriptor for an abstract base class.
verbose: bool, display progress?
Returns:
True if there we any errors extracting image features. False otherwise.
If there is a problem extracting any image descriptors, a file
"errors.log" is created in the savedir directory with a list of file
names, error number and messages.
"""
# Try to make the save path
if not os.path.exists(savedir):
os.mkdir(savedir)
errflag = False
# Set up progess updates
nfiles = len(filelist)
progbar = Progress(nfiles, title='Extracting descriptors', verbose=verbose)
# Iterate through all of the images in filelist and extract features
for i, impath in enumerate(filelist):
errflag |= extract(impath, savedir, descobj)
progbar.update(i)
progbar.finished()
if errflag == True:
print('Done with errors. See the "errors.log" file in ' + savedir)
def __init__(self,
json_txt,
show_progress=False,
replace_hashtags=True,
replace_user_refs=False,
replace_links=True):
import json
self.show_progress = show_progress
self.replace_links = replace_links
self.replace_hashtags = replace_hashtags
self.replace_user_refs = replace_user_refs
#parse text into json objects
if self.show_progress:
from utils.progress import Progress
with Progress("Parsing text into JSON Object",
len(json_txt)) as up:
self.tweet_JSON_objs = [
u(json.loads(line)) for line in json_txt
]
else:
print("Parsing text into JSON Object.")
self.tweet_JSON_objs = [json.loads(line) for line in json_txt]
#extract text from tweets
self.process_tweets()
def extract_smp(filelist, savedir, descobj, njobs=None, verbose=False):
""" Extract features/descriptors from a batch of images. Multi-threaded.
This function calls an image descripor object on a batch of images in order
to extract the images descripor. If a feature/descriptor file already exists
for the image, it is skipped. This is a multi-threaded (SMP) pipeline
suitable for running on a single computer.
Arguments:
filelist: A list of files of image names including their paths of images
to read and extract descriptors from
savedir: A directory in which to save all of the image features. They
are pickled objects (protocol 2) with the same name as the
image file. The object that is pickled is the return from
descobj.extract().
decobj: An image descriptor object which does the actual extraction
work. the method called is descobj.extract(image). See
descriptors.Descriptor for an abstract base class.
njobs: int, Number of threads to use. If None, then the number of
threads is chosen to be the same as the number of cores.
verbose: bool, display progress?
Returns:
True if there we any errors extracting image features. False otherwise.
If there is a problem extracting any image descriptors, a file
"errors.log" is created in the savedir directory with a list of file
names, error number and messages.
"""
# Try to make the save path
if not os.path.exists(savedir):
os.mkdir(savedir)
# Set up parallel job
pool = mp.Pool(processes=njobs)
# Iterate through all of the images in filelist and extract features
result = pool.map_async(
__extract_star,
itertools.izip(filelist, itertools.repeat(savedir),
itertools.repeat(descobj)))
# Set up progess updates
nfiles = len(filelist)
progbar = Progress(nfiles, title='Extracting descriptors', verbose=verbose)
# Get the status
while ((result.ready() is not True) and (verbose == True)):
approx_rem = nfiles - result._number_left * result._chunksize
progbar.update(max(0, approx_rem))
time.sleep(5)
progbar.finished()
# Get notification of errors
errflag = any(result.get())
pool.close()
pool.join()
if errflag == True:
print('Done, with errors. See the "errors.log" file in ' + savedir)
def main(args):
###############################
# TRAIN PREP
###############################
print("Loading data")
train_loader, valid_loader, data_var, input_size = \
data.get_data(args.data_folder,args.batch_size)
args.input_size = input_size
args.downsample = args.input_size[-1] // args.enc_height
args.data_variance = data_var
print(f"Training set size {len(train_loader.dataset)}")
print(f"Validation set size {len(valid_loader.dataset)}")
print("Loading model")
if args.model == 'diffvqvae':
model = DiffVQVAE(args).to(device)
elif args.model == 'vqvae':
model = VQVAE(args).to(device)
print(
f'The model has {utils.count_parameters(model):,} trainable parameters'
)
optimizer = optim.Adam(model.parameters(),
lr=args.learning_rate,
amsgrad=False)
print(f"Start training for {args.num_epochs} epochs")
num_batches = math.ceil(
len(train_loader.dataset) / train_loader.batch_size)
pbar = Progress(num_batches, bar_length=10, custom_increment=True)
# Needed for bpd
args.KL = args.enc_height * args.enc_height * args.num_codebooks * \
np.log(args.num_embeddings)
args.num_pixels = np.prod(args.input_size)
###############################
# MAIN TRAIN LOOP
###############################
best_valid_loss = float('inf')
train_bpd = []
train_recon_error = []
train_perplexity = []
args.global_it = 0
for epoch in range(args.num_epochs):
pbar.epoch_start()
train_epoch(args, vq_vae_loss, pbar, train_loader, model, optimizer,
train_bpd, train_recon_error, train_perplexity)
# loss, _ = test(valid_loader, model, args)
# pbar.print_eval(loss)
valid_loss = evaluate(args, vq_vae_loss, pbar, valid_loader, model)
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
best_valid_epoch = epoch
torch.save(model.state_dict(), args.save_path)
pbar.print_end_epoch()
print("Plotting training results")
utils.plot_results(train_recon_error, train_perplexity,
"results/train.png")
print("Evaluate and plot validation set")
generate_samples(model, valid_loader)
class Meta(Page):
def __init__(self, tag: str, from_top: bool = True):
self.base_url = (f'https://archiveofourown.org/tags/'
f'{quote(tag).replace(".", "*d*")}/works?page=')
tag_path = paths.tag_path(tag)
self.progress = Progress(tag_path)
self.last = self.progress.read()[0]
self.path = paths.meta_path(tag)
log_path = paths.meta_log_path(tag)
super().__init__(tag + '_meta', log_path)
self.from_top = self._start_from_top(from_top)
def scrape(self) -> None:
if self.from_top is True or self.path.is_file() is False:
mode = 'w'
else:
mode = 'a'
with open(self.path, mode) as f_out:
pages = self._pages()
for page, progress_num in pages:
page_elements = self._page_elements(page)
for element in page_elements:
f_out.write(json.dumps(element) + '\n')
self.progress.write(progress_num)
self.logger.info(f'Completed scraping "{self.page_kind}"')
return
super().scrape()
def _pages(self) -> Generator[Tuple[BeautifulSoup, str], None, None]:
try:
page_num = int(self.last)
except ValueError:
self.logger.error(f'Last scraped value ({self.last})'
f' in .meta is not a number')
raise ValueError
if page_num == -1 or self.from_top is True:
page_num = 1
else:
page_num += 1
errors = 0
self.logger.info(f"Scraping: {self.base_url}")
try:
max_pages = self._total_pages()
except ConnectionError:
self.logger.error(f'Base URL: {self.base_url} Not found.')
raise ConnectionError(f"Error connecting to: {self.base_url}\n"
f"Could your fandom name be incorrect?")
except Exception as e:
self.logger.error(f'Base URL: {self.base_url} Not found.')
raise Exception(f"Other error: {e}")
while errors < cfg.MAX_ERRORS and page_num <= max_pages:
try:
url = self.base_url + str(page_num)
soup = self._get_soup(url)
except HTTPError:
# just move onto next page
self.logger.error(f'PAGE: {url} 404 Error. Skipping this work.'
f' {cfg.MAX_ERRORS-errors} attempts left.')
errors += 1
time.sleep(cfg.DELAY)
page_num += 1
url = self.base_url + str(page_num)
except ConnectTimeout:
# Try again
errors += 1
self.logger.error(f'PAGE: {url} Not found. '
f'{cfg.MAX_ERRORS-errors} attempts left.')
time.sleep(cfg.DELAY * errors) # exponential decay wait
else:
self.logger.info(f'Scraping PAGE: {str(page_num)}')
time.sleep(cfg.DELAY)
yield (soup, str(page_num))
page_num += 1
url = self.base_url + str(page_num)
def _page_elements(self,
page: BeautifulSoup) -> Generator[MetaJson, None, None]:
""" Find each HTML element and parse out the details into a row. """
time = datetime.datetime.now().strftime("%d/%b/%Y %H:%M")
meta: MetaJson = {} # type: ignore
works = page.find_all(class_="work blurb group")
for work in works:
meta.update(self._get_header(work))
meta.update(self._get_required_tags(work))
meta.update(self._get_tags(work))
meta.update(self._get_stats(work))
meta['fandom'] = self._get_fandoms(work)
meta['summary'] = self._get_summary(work)
meta['series_part'], meta['series_name'] = self._get_series(work)
meta['updated'] = self._get_updated(work)
meta['scrape_date'] = time
yield meta
def _total_pages(self) -> int:
''' Make max attempts at loading base url to get starting number'''
for attempts in range(cfg.MAX_ERRORS):
try:
soup = self._get_soup(self.base_url)
next_element = soup.find('li', class_='next')
max_pages = int(next_element.find_previous('li').text)
self.logger.info(f'Attempting to scrape up to '
f'{str(max_pages)} pages.')
return max_pages
except AttributeError:
self.logger.info('Attempting to scrape 1 page.')
return 1
except ConnectTimeout:
self.logger.error(f'Base URL: {self.base_url} Not found. '
f'{cfg.MAX_ERRORS-attempts} attempts left.')
raise ConnectTimeout
return 0
def _get_tags(self, meta: BeautifulSoup) -> Any:
"""Find relationships, characters, and freeforms tags"""
tag_dict = {} # type: Dict[str, Optional[List[str]]]
tags = ['relationships', 'characters', 'freeforms']
for tag in tags:
tag_dict[tag] = self._get_tag_info(tag, meta)
return tag_dict
def _get_tag_info(self, category: str, meta: BeautifulSoup) -> \
Optional[List[str]]:
""" Find relationships, characters, and freeforms tags."""
try:
tag_list = meta.find_all("li", class_=category)
except AttributeError:
return None
return [result.text for result in tag_list]
def _get_required_tags(self, work: BeautifulSoup) -> Any:
"""Finds required tags."""
req_dict = {}
try:
req_tags = work.find(class_='required-tags').find_all('a')
req_dict['rating'] = req_tags[0].text
req_dict['warnings'] = req_tags[1].text.split(',')
req_dict['category'] = req_tags[2].text.split(',')
req_dict['status'] = req_tags[3].text
except Exception:
req_dict['rating'] = None
req_dict['warnings'] = []
req_dict['category'] = []
req_dict['status'] = None
return req_dict
def _get_stats(self, work: BeautifulSoup) -> Any:
"""
Find stats (language, published, status, date status, words, chapters,
comments, kudos, bookmarks, hits
"""
str_categories = ['language', 'chapters']
num_categories = [
'collections', 'words', 'comments', 'kudos', 'bookmarks', 'hits'
]
stats = {}
for s_cat in str_categories:
try:
stats[s_cat] = work.find("dd", class_=s_cat).text
except AttributeError:
stats[s_cat] = None
for n_cat in num_categories:
try:
str_num = work.find("dd", class_=n_cat).text
stats[n_cat] = int(str_num.replace(',', ''))
except (AttributeError, ValueError):
stats[n_cat] = 0
return stats
def _get_header(self, work: BeautifulSoup) -> Any:
'''Finds header information
(work_id, title, author, gifted to user).'''
header_dict = {}
result = work.find('h4', class_='heading').find_all('a')
header_dict['work_id'] = result[0].get('href').strip('/works/')
header_dict['title'] = result[0].text
auth_list = []
header_text = work.find('h4', class_='heading').text
if "Anonymous" in header_text:
header_dict['author'] = ["Anonymous"]
else:
authors = work.find_all('a', rel='author')
for author in authors:
auth_list.append(author.text)
header_dict['author'] = auth_list
gift_list = []
for link in result:
href = link.get('href')
if 'gifts' in href:
gift_list.append(link.text)
if len(gift_list) == 0:
header_dict['gifted'] = []
else:
header_dict['gifted'] = gift_list
return header_dict
def _get_fandoms(self, work: BeautifulSoup) -> List[str]:
""" Find the list of fandoms."""
try:
tag_list = work.find('h5', class_='fandoms heading').find_all('a')
fan_list = [x.text for x in tag_list]
return fan_list
except AttributeError:
return []
def _get_summary(self, work: BeautifulSoup) -> Optional[str]:
""" Find summary description and return as list of strings. """
try:
summary_string = work.find('blockquote',
class_='userstuff summary')
summary = summary_string.text.strip().replace('\n', ' ')
except AttributeError:
summary = None
return summary
def _get_updated(self, work: BeautifulSoup) -> Optional[str]:
""" Find update date. Return as list of strings. """
try:
date = work.find('p', class_='datetime').text
except AttributeError:
date = None
return date
def _get_series(self, work: BeautifulSoup) \
-> Tuple[Optional[str], Optional[str]]:
""" Find series info and return as list. """
try:
series = work.find('ul', class_='series')
part = series.find('strong').text
s_name = series.find('a').text
except AttributeError:
part, s_name = None, None
return part, s_name
def _start_from_top(self, from_top: bool) -> bool:
if from_top is True:
self.logger.info("Scraping from the top.")
return True
elif self.last == self.progress.unscraped_flag:
self.logger.info(
f"Last scraped unknown: {self.progress.unscraped_flag}. "
f"Scraping from the top.")
return True
else:
self.logger.info(f"Picking up from {self.last} ")
return False
def extract_smp(filelist, savedir, descobj, njobs=None, verbose=False):
""" Extract features/descriptors from a batch of images. Multi-threaded.
This function calls an image descripor object on a batch of images in order
to extract the images descripor. If a feature/descriptor file already exists
for the image, it is skipped. This is a multi-threaded (SMP) pipeline
suitable for running on a single computer.
Arguments:
filelist: A list of files of image names including their paths of images
to read and extract descriptors from
savedir: A directory in which to save all of the image features. They
are pickled objects (protocol 2) with the same name as the
image file. The object that is pickled is the return from
descobj.extract().
decobj: An image descriptor object which does the actual extraction
work. the method called is descobj.extract(image). See
descriptors.Descriptor for an abstract base class.
njobs: int, Number of threads to use. If None, then the number of
threads is chosen to be the same as the number of cores.
verbose: bool, display progress?
Returns:
True if there we any errors extracting image features. False otherwise.
If there is a problem extracting any image descriptors, a file
"errors.log" is created in the savedir directory with a list of file
names, error number and messages.
"""
# Try to make the save path
if not os.path.exists(savedir):
os.mkdir(savedir)
# Set up parallel job
pool = mp.Pool(processes=njobs)
# Iterate through all of the images in filelist and extract features
result = pool.map_async(
__extract_star, itertools.izip(filelist, itertools.repeat(savedir), itertools.repeat(descobj))
)
# Set up progess updates
nfiles = len(filelist)
progbar = Progress(nfiles, title="Extracting descriptors", verbose=verbose)
# Get the status
while (result.ready() is not True) and (verbose == True):
approx_rem = nfiles - result._number_left * result._chunksize
progbar.update(max(0, approx_rem))
time.sleep(5)
progbar.finished()
# Get notification of errors
errflag = any(result.get())
pool.close()
pool.join()
if errflag == True:
print('Done, with errors. See the "errors.log" file in ' + savedir)
def embed_tweets_hashtags(self, tweets, hashtags):
with Progress("Calculating hashtag and tweet embeddings",
len(hashtags) + len(tweets)) as up:
[up(self.tweet_embedding(t)) for t in tweets]
[up(self.hashtag_embedding(h)) for h in hashtags]
