def get_lexicon(self):
"""
Prepares the lexicon, creating it if needed and loads it.
:return: The loaded lexicon.
"""
self.logger.info("Preparing lexicon...")
current_dir = Path()
dir_path = current_dir / "data" / "break_data" / "lexicon_by_logical"
file_name = "lexicon"
if self.domain_split:
file_name += "_domain_split"
elif self.length_split:
file_name += "_length_split"
file_name += ".pkl"
if not (dir_path / file_name).is_file():
self.create_matching_lexicon(dir_path, file_name)
data = load_obj(dir_path, file_name)
# TODO delete this?
# for type in data:
# for ex in data[type]:
# data[type][ex] = ast.literal_eval(data[type][ex])
self.logger.info("Lexicon ready.")
return data
def load_vocab(dir_path, file_name):
"""
Loads a vocabulary from a file.
:param dir_path: The path of the directory.
:param file_name: The name of the vocab file.
:return: The loaded Vocab.
"""
properties = load_obj(dir_path, file_name)
vocab = Vocab(properties['counter'], specials=properties['specials'])
return vocab
def load_domain_split_dataset(self, data_dir, logger=None):
"""
Loads break dataset with domain split. Train - on text. val + test - on DB + images
:param data_dir: The path of the directory where the preprocessed dataset should be saved to or loaded from.
:param logger: A logger for logging events.
:return: The loaded dataset.
"""
current_dir = Path()
dir_path = current_dir / "data" / "break_data" / "preprocessed"
file_name = "dataset_preprocessed_domain_split.pkl"
if not (dir_path / file_name).is_file():
if logger:
logger.info('Creating domain split dataset...')
text_domain_dataset_prefixes = ('COMQA', 'CWQ', 'DROP', 'HOTP')
image_domain_dataset_prefixes = ('CLEVR', 'NLVR2')
DB_domain_dataset_prefixes = ('ACADEMIC', 'ATIS', 'GEO', 'SPIDER')
image_plus_DB = image_domain_dataset_prefixes + DB_domain_dataset_prefixes
train_filtererd = pd.DataFrame()
validation_filtererd = pd.DataFrame()
test_filtererd = pd.DataFrame()
for i, example in enumerate(self.dataset_logical['train']):
if example['question_id'].startswith(
text_domain_dataset_prefixes):
train_filtererd = train_filtererd.append(example,
ignore_index=True)
for i, example in enumerate(self.dataset_logical['validation']):
if example['question_id'].startswith(image_plus_DB):
validation_filtererd = validation_filtererd.append(
example, ignore_index=True)
for i, example in enumerate(self.dataset_logical['test']):
if example['question_id'].startswith(image_plus_DB):
test_filtererd = test_filtererd.append(example,
ignore_index=True)
# TODO delete this?
# train_dataset = self.dataset_logical['train'].filter(
# lambda example: example['question_id'].startswith(text_domain_dataset_prefixes))
# validation_dataset = self.dataset_logical['validation'].filter(
# lambda example: example['question_id'].startswith(image_plus_DB))
# test_dataset = self.dataset_logical['test'].filter(
# lambda example: example['question_id'].startswith(image_plus_DB))
# train_filtererd_ds = Dataset.from_pandas(train_filtererd)
to_save = {
'train': Dataset.from_pandas(train_filtererd),
'validation': Dataset.from_pandas(validation_filtererd),
'test': Dataset.from_pandas(test_filtererd)
}
save_obj(dir_path, to_save, file_name)
dataset = load_obj(dir_path, file_name)
return dataset
def get_programs(self):
"""
Loads the programs from a file.
:return: The loaded programs.
"""
self.logger.info("Preparing programs...")
current_dir = Path()
dir_path = current_dir / "data" / "break_data" / "programs"
file_name = "programs_" + self.dataset_split + ".pkl"
if not (dir_path / file_name).is_file():
self.create_matching_programs(dir_path, file_name)
data = load_obj(dir_path, file_name)
self.logger.info("Programs ready.")
return data
def load_length_split_dataset(self, data_dir, logger=None):
"""
Loads break dataset with length split based on number of operators.
Train - <= 4 steps.
val + test - on DB + images
:param data_dir: The path of the directory where the preprocessed dataset should be saved to or loaded from.
:param logger: A logger for logging events.
:return: The loaded dataset.
"""
# TODO datadir required in signature?
current_dir = Path()
dir_path = current_dir / "data" / "break_data" / "preprocessed"
file_name = "dataset_preprocessed_length_split.pkl"
if not (dir_path / file_name).is_file():
if logger:
logger.info('Creating length split dataset...')
threshold_amount_ops = 4
train_filtererd = pd.DataFrame()
validation_filtererd = pd.DataFrame()
test_filtererd = pd.DataFrame()
for i, example in enumerate(self.dataset_logical['train']):
if example['operators'].count(',') < threshold_amount_ops:
train_filtererd = train_filtererd.append(example,
ignore_index=True)
for i, example in enumerate(self.dataset_logical['validation']):
if example['operators'].count(',') >= threshold_amount_ops:
validation_filtererd = validation_filtererd.append(
example, ignore_index=True)
for i, example in enumerate(self.dataset_logical['test']):
if example['operators'].count(',') >= threshold_amount_ops:
test_filtererd = test_filtererd.append(example,
ignore_index=True)
to_save = {
'train': Dataset.from_pandas(train_filtererd),
'validation': Dataset.from_pandas(validation_filtererd),
'test': Dataset.from_pandas(test_filtererd)
}
save_obj(dir_path, to_save, file_name)
dataset = load_obj(dir_path, file_name)
return dataset
def load_dataset(data_dir, dataset_split, logger=None):
"""
loads the requested Break dataset from Hugging Face.
:param data_dir: The path of the directory where the preprocessed dataset should be saved to or loaded from.
:param dataset_split: The type of dataset to download from HF.
:param logger: A logger for logging events.
:return: The loaded dataset.
"""
current_dir = Path()
dir_path = current_dir / "data" / "break_data" / "preprocessed"
file_name = "dataset_preprocessed_" + dataset_split + ".pkl"
if not (dir_path / file_name).is_file():
# Download and preprocess the BREAK dataset (logical form and lexicon), and save the preprocessed data.
if logger:
logger.info('Downloading and preparing datasets...')
dataset_logical = load_dataset('break_data',
dataset_split,
cache_dir=data_dir)
save_obj(dir_path, dataset_logical, file_name)
# Load the saved preprocessed data.
dataset = load_obj(dir_path, file_name)
return dataset
saver_pose_seg_depth.restore(sess, restore_dir)
print('restore pose_seg_depth succeed')
else:
print('Restore pose_seg_depth failed')
raise SystemExit
restore_dir = tf.train.latest_checkpoint(params.normal_dir)
if restore_dir:
saver_normal.restore(sess, restore_dir)
print('restore normal succeed')
else:
print('Restore normal failed')
raise SystemExit
# Initialize datalist
meanstd = util.load_obj(params.meanRgb_dir)
dataset = glob.glob(params.test_dir + '/*.jpg')
img_batch = np.zeros((params.batch_size, 256, 256, 3), dtype=np.float32)
mask_batch = np.zeros((params.batch_size, 256, 256), dtype=np.bool)
segmap = np.zeros((params.batch_size, 256, 256), dtype=np.int32)
testimg = np.zeros((256, 256, 3), dtype=np.float32)
images = os.listdir(params.test_dir)
for each in images:
i = 0
imgname = os.path.join(params.test_dir, each)
try:
im = Image.open(imgname)
# do stuff
except IOError: