def setup(self, stage=None):
super().setup(stage=stage)
cfg = self.cfg
if HydraConfig.initialized():
# Current directory changed!
# Update paths with original_cwd
csv_path = to_absolute_path(cfg.data.csv_path)
root_dir = to_absolute_path(cfg.data.root_dir)
else:
# Keep relative paths
csv_path = cfg.data.csv_path
root_dir = cfg.data.root_dir
df = pd.read_csv(csv_path)
df[["x", "y", "x1", "y1"]] = pd.DataFrame(
np.stack(df["box"].apply(ast.literal_eval)).astype(np.float32)
)
train_df = df.loc[df["fold"] != cfg.data.valid_fold].copy()
valid_df = df.loc[df["fold"] == cfg.data.valid_fold].copy()
self.train_dataset = PennFudanDataset(
train_df,
root_dir=root_dir,
transforms=self.train_transforms,
mode="train",
)
self.val_dataset = PennFudanDataset(
valid_df, root_dir=root_dir, transforms=self.val_transforms, mode="val"
)
def __init__(self, cfg: DictConfig, train_transforms=None, val_transforms=None):
super().__init__(
train_transforms=train_transforms,
val_transforms=val_transforms,
test_transforms=val_transforms,
)
self.train_transforms = train_transforms
self.val_transforms = val_transforms
self.cfg = cfg
if HydraConfig.initialized():
# Current directory changed!
# Update paths with original_cwd
self.data_csv_path = to_absolute_path(cfg.data.csv_path)
self.root_dir = to_absolute_path(cfg.data.root_dir)
else:
# Keep relative paths
self.data_csv_path = cfg.data.csv_path
self.root_dir = cfg.data.root_dir