def __init__(self,
data: str,
split: str,
extension: str,
length: Optional[int] = None):
self.datapath = wsl_data_dir / data
self.data = data
if data in known_extensions.keys():
self.extension = known_extensions[data]
else:
self.extension = extension
self.names = pd.read_csv(wsl_csv_dir / data /
f'{split}.csv').Id.tolist()
if length is not None:
self.names = random.sample(self.names, min(len(self.names),
length))
self.new_size = (224, 224)
self.image_transforms = Compose([
Resize(self.new_size),
RepeatChannel(repeats=3),
CastToType(dtype=np.float32),
ToTensor()
])
def __init__(self, data: str, split: str, extension: str,
classes: int, col_name: str,
regression: bool, debug: bool = False):
if regression and classes != 1:
print('Support for multi-class regression is not available.')
sys.exit(1)
self.datapath = wsl_data_dir / data
self.data = data
self.classes = classes
known_extensions = {'rsna': 'dcm', 'chexpert': 'jpg'}
if data in known_extensions.keys():
self.extension = known_extensions[data]
else:
self.extension = extension
df = pd.read_csv(wsl_csv_dir / data / 'info.csv', converters={col_name: literal_eval})
self.df = df
df = df.drop_duplicates(subset='Id', keep='first', ignore_index=True)
Ids = pd.read_csv(wsl_csv_dir / data / f'{split}.csv').Id.tolist()
df = df[df.Id.isin(Ids)]
self.names = df.Id.to_list()
self.labels = df[col_name].tolist()
if debug:
self.names = self.names[0:100]
self.labels = self.labels[0:100]
self.image_transforms = Compose([
Resize((224, 224)),
RepeatChannel(repeats=3),
CastToType(dtype=np.float32),
ToTensor()])
if regression:
self.lmax = df[col_name].max()
self.lmin = df[col_name].min()
self.labels = [[round((x - self.lmin) / self.lmax, 2)] for x in self.labels]
else:
if classes == 1:
self.labels = [[x] for x in self.labels]
else:
self.class_names = self.labels[0].keys()
self.labels = [list(x.values()) for x in self.labels]
self.pos_weight = [round((len(col) - sum(col)) / sum(col), 2) for col in zip(*self.labels)]
def __init__(self,
data: str,
split: str,
extension: str,
classes: int,
column: str,
debug: bool = False):
self.datapath = wsl_data_dir / data
self.data = data
self.classes = classes
self.column = column
if data in known_extensions.keys():
self.extension = known_extensions[data]
else:
self.extension = extension
df = pd.read_csv(wsl_csv_dir / data / 'info.csv',
converters={
column: literal_eval,
'box': literal_eval
})
self.df = df
Ids = pd.read_csv(wsl_csv_dir / data / f'{split}.csv').Id.tolist()
df = df[df.Id.isin(Ids)]
self.max_boxes = df['Id'].value_counts().max()
self.names = list(set(df.Id.to_list()))
if debug:
self.names = self.names[0:100]
self.image_transforms = Compose([
# Resize((224, 224)),
RepeatChannel(repeats=3),
CastToType(dtype=np.float32),
ToTensor()
])
def __init__(self,
data: str,
split: str,
extension: str,
classes: int,
column: str,
variable_type: str,
augmentation: bool = False,
debug: bool = False):
if classes != 1:
print('Note: Ensure all labels are of a single type.')
self.datapath = wsl_data_dir / data
self.data = data
self.classes = classes
if data in known_extensions.keys():
self.extension = known_extensions[data]
else:
self.extension = extension
df = pd.read_csv(wsl_csv_dir / data / 'info.csv',
converters={
column: literal_eval,
'box': literal_eval
})
self.df = df
df = df.drop_duplicates(subset='Id', keep='first', ignore_index=True)
Ids = pd.read_csv(wsl_csv_dir / data / f'{split}.csv').Id.tolist()
df = df[df.Id.isin(Ids)]
self.names = df.Id.to_list()
self.labels = df[column].tolist()
self.variable_type = variable_type
if debug:
self.names = self.names[0:100]
self.labels = self.labels[0:100]
self.new_size = (224, 224)
self.image_transforms = Compose([
Resize(self.new_size),
RepeatChannel(repeats=3),
CastToType(dtype=np.float32),
ToTensor()
])
self.augmentation = augmentation
if augmentation:
self.augmentation = Affine(rotate_params=np.pi / 6,
scale_params=(1.2, 1.2),
translate_params=(50, 50),
padding_mode='zeros')
else:
self.augmentation = None
if self.variable_type != 'categorical':
if classes == 1:
self.labels = [[x] for x in self.labels]
else:
self.class_names = self.labels[0].keys()
print('\nClass List: ', self.class_names)
self.labels = [list(x.values()) for x in self.labels]
# only matters for balanced case for binary variable type
self.pos_weight = [
round((len(col) - sum(col)) / sum(col), 2)
for col in zip(*self.labels)
]
def test_shape(self, input_param, input_data, expected_shape):
result = RepeatChannel(**input_param)(input_data)
self.assertEqual(result.shape, expected_shape)