diff --git a/pyproject.toml b/pyproject.toml
index e478819245b56d510124f3958ee177765353e219..5fc0981beca79e63840a613fd2cb1d088aa27af2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -476,11 +476,11 @@ nih_cxr14_cm = "ptbench.configs.datasets.nih_cxr14_re.cardiomegaly"
# NIH CXR14 / PadChest aggregated dataset
nih_cxr14_pc_idiap = "ptbench.configs.datasets.nih_cxr14_re_pc.idiap"
# PadChest
-padchest_idiap = "ptbench.configs.datasets.padchest.idiap"
-padchest_tb_idiap = "ptbench.configs.datasets.padchest.tb_idiap"
-padchest_no_tb_idiap = "ptbench.configs.datasets.padchest.no_tb_idiap"
-padchest_tb_idiap_rgb = "ptbench.configs.datasets.padchest.tb_idiap_rgb"
-padchest_cm_idiap = "ptbench.configs.datasets.padchest.cardiomegaly_idiap"
+padchest_idiap = "ptbench.data.padchest.idiap"
+padchest_tb_idiap = "ptbench.data.padchest.tb_idiap"
+padchest_no_tb_idiap = "ptbench.data.padchest.no_tb_idiap"
+padchest_tb_idiap_rgb = "ptbench.data.padchest.tb_idiap_rgb"
+padchest_cm_idiap = "ptbench.data.padchest.cardiomegaly_idiap"
# extended PadChestTB dataset (with radiological signs)
padchest_tb_idiap_rs = "ptbench.configs.datasets.padchest_RS.tb_idiap"
diff --git a/src/ptbench/configs/datasets/padchest/__init__.py b/src/ptbench/configs/datasets/padchest/__init__.py
deleted file mode 100644
index 4ae4ebfb139353d7740cc49c9a741b07cbc20757..0000000000000000000000000000000000000000
--- a/src/ptbench/configs/datasets/padchest/__init__.py
+++ /dev/null
@@ -1,26 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-
-def _maker(protocol, resize_size=512, cc_size=512, RGB=True):
- import torchvision.transforms as transforms
-
- from ....data.padchest import dataset as raw
- from ....data.transforms import SingleAutoLevel16to8
- from .. import make_dataset as mk
-
- post_transforms = []
- if not RGB:
- post_transforms = [transforms.Lambda(lambda x: x.convert("L"))]
-
- return mk(
- [raw.subsets(protocol)],
- [
- SingleAutoLevel16to8(),
- transforms.Resize(resize_size),
- transforms.CenterCrop(cc_size),
- ],
- [transforms.RandomHorizontalFlip()],
- post_transforms,
- )
diff --git a/src/ptbench/configs/datasets/padchest/cardiomegaly_idiap.py b/src/ptbench/configs/datasets/padchest/cardiomegaly_idiap.py
deleted file mode 100644
index a12a6b402f29570d800ed347d62a13161cd174b1..0000000000000000000000000000000000000000
--- a/src/ptbench/configs/datasets/padchest/cardiomegaly_idiap.py
+++ /dev/null
@@ -1,17 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-"""Padchest cardiomegaly (idiap protocol) dataset for computer-aided diagnosis.
-
-The first 40 images with cardiomegaly.
-parameters: Label = "Normal", MethodLabel = "Physician", Projection = "PA"
-
-* Split reference: first 100% of cardiomegaly for "train"
-* See :py:mod:`ptbench.data.padchest` for dataset details
-* This configuration resolution: 512 x 512 (default)
-"""
-
-from . import _maker
-
-dataset = _maker("cardiomegaly_idiap", RGB=False)
diff --git a/src/ptbench/configs/datasets/padchest/idiap.py b/src/ptbench/configs/datasets/padchest/idiap.py
deleted file mode 100644
index b6ba25a3b287164bf45c1cdd4fecf43821ad2f33..0000000000000000000000000000000000000000
--- a/src/ptbench/configs/datasets/padchest/idiap.py
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-"""Padchest (idiap protocol) dataset for computer-aided diagnosis.
-
-* See :py:mod:`ptbench.data.padchest` for dataset details
-* This configuration resolution: 512 x 512 (default)
-"""
-
-from . import _maker
-
-dataset = _maker("idiap")
diff --git a/src/ptbench/configs/datasets/padchest/no_tb_idiap.py b/src/ptbench/configs/datasets/padchest/no_tb_idiap.py
deleted file mode 100644
index 333b95a878d28ec291d99c0a3ed3ca17b735d191..0000000000000000000000000000000000000000
--- a/src/ptbench/configs/datasets/padchest/no_tb_idiap.py
+++ /dev/null
@@ -1,24 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-"""Padchest tuberculosis (no TB idiap protocol) dataset for computer-aided
-diagnosis.
-
-* Protocol ``no TB idiap``:
-
- * Training samples: 20'126
- * Validation samples: 1'500
- * Test samples: 0
-
-* Images path adapted to Idiap infrastructure
-
-* Labels:
- cardiomegaly, emphysema, effusion, hernia, infiltration,
- mass, nodule, atelectasis, pneumothorax, pleural thickening, pneumonia,
- fibrosis, edema and consolidation
-"""
-
-from . import _maker
-
-dataset = _maker("no_tb_idiap")
diff --git a/src/ptbench/configs/datasets/padchest/tb_idiap.py b/src/ptbench/configs/datasets/padchest/tb_idiap.py
deleted file mode 100644
index fd3690a57c5d20e7a7c9e0f8f255c1af76362d5d..0000000000000000000000000000000000000000
--- a/src/ptbench/configs/datasets/padchest/tb_idiap.py
+++ /dev/null
@@ -1,17 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-"""Padchest tuberculosis (idiap protocol) dataset for computer-aided diagnosis.
-
-The 125 healthy images are the first 125 padchest images with the following
-parameters: Label = "Normal", MethodLabel = "Physician", Projection = "PA"
-
-* Split reference: first 80% of TB and healthy CXR for "train", rest for "test"
-* See :py:mod:`ptbench.data.padchest` for dataset details
-* This configuration resolution: 512 x 512 (default)
-"""
-
-from . import _maker
-
-dataset = _maker("tb_idiap", RGB=False)
diff --git a/src/ptbench/configs/datasets/padchest/tb_idiap_rgb.py b/src/ptbench/configs/datasets/padchest/tb_idiap_rgb.py
deleted file mode 100644
index 44bc0d9abf33c563dc1f2fc2daeb68ad7bd06283..0000000000000000000000000000000000000000
--- a/src/ptbench/configs/datasets/padchest/tb_idiap_rgb.py
+++ /dev/null
@@ -1,18 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-"""Padchest tuberculosis (idiap protocol, rgb) dataset for computer-aided
-diagnosis.
-
-The 125 healthy images are the first 125 padchest images with the following
-parameters: Label = "Normal", MethodLabel = "Physician", Projection = "PA"
-
-* Split reference: first 80% of TB and healthy CXR for "train", rest for "test"
-* See :py:mod:`ptbench.data.padchest` for dataset details
-* This configuration resolution: 224 x 224 (default)
-"""
-
-from . import _maker
-
-dataset = _maker("tb_idiap", resize_size=256, cc_size=224)
diff --git a/src/ptbench/data/padchest/__init__.py b/src/ptbench/data/padchest/__init__.py
index e52b6dd6f44ea7077faf8214bb3319a2917f5b4e..af1dd3ec9f8cbaa1b3e32f5195363592602d94ac 100644
--- a/src/ptbench/data/padchest/__init__.py
+++ b/src/ptbench/data/padchest/__init__.py
@@ -226,6 +226,7 @@ import importlib.resources
import os
from ...utils.rc import load_rc
+from .. import make_dataset
from ..dataset import JSONDataset
from ..loader import load_pil, make_delayed
@@ -252,9 +253,30 @@ def _loader(context, sample):
return make_delayed(sample, _raw_data_loader)
-dataset = JSONDataset(
+json_dataset = JSONDataset(
protocols=_protocols,
fieldnames=("data", "label"),
loader=_loader,
)
"""Padchest dataset object."""
+
+
+def _maker(protocol, resize_size=512, cc_size=512, RGB=True):
+ import torchvision.transforms as transforms
+
+ from ..transforms import SingleAutoLevel16to8
+
+ post_transforms = []
+ if not RGB:
+ post_transforms = [transforms.Lambda(lambda x: x.convert("L"))]
+
+ return make_dataset(
+ [json_dataset.subsets(protocol)],
+ [
+ SingleAutoLevel16to8(),
+ transforms.Resize(resize_size),
+ transforms.CenterCrop(cc_size),
+ ],
+ [transforms.RandomHorizontalFlip()],
+ post_transforms,
+ )
diff --git a/src/ptbench/data/padchest/cardiomegaly_idiap.py b/src/ptbench/data/padchest/cardiomegaly_idiap.py
new file mode 100644
index 0000000000000000000000000000000000000000..25eaa6e8fd0ba15db3a46f4d14366bcf5bc91667
--- /dev/null
+++ b/src/ptbench/data/padchest/cardiomegaly_idiap.py
@@ -0,0 +1,49 @@
+# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
+#
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+"""Padchest cardiomegaly (idiap protocol) dataset for computer-aided diagnosis.
+
+The first 40 images with cardiomegaly.
+parameters: Label = "Normal", MethodLabel = "Physician", Projection = "PA"
+
+* Split reference: first 100% of cardiomegaly for "train"
+* See :py:mod:`ptbench.data.padchest` for dataset details
+* This configuration resolution: 512 x 512 (default)
+"""
+
+from clapper.logging import setup
+
+from .. import return_subsets
+from ..base_datamodule import BaseDataModule
+from . import _maker
+
+logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
+
+
+class DefaultModule(BaseDataModule):
+ def __init__(
+ self,
+ train_batch_size=1,
+ predict_batch_size=1,
+ drop_incomplete_batch=False,
+ multiproc_kwargs=None,
+ ):
+ super().__init__(
+ train_batch_size=train_batch_size,
+ predict_batch_size=predict_batch_size,
+ drop_incomplete_batch=drop_incomplete_batch,
+ multiproc_kwargs=multiproc_kwargs,
+ )
+
+ def setup(self, stage: str):
+ self.dataset = _maker("cardiomegaly_idiap", RGB=False)
+ (
+ self.train_dataset,
+ self.validation_dataset,
+ self.extra_validation_datasets,
+ self.predict_dataset,
+ ) = return_subsets(self.dataset)
+
+
+datamodule = DefaultModule
diff --git a/src/ptbench/data/padchest/idiap.py b/src/ptbench/data/padchest/idiap.py
new file mode 100644
index 0000000000000000000000000000000000000000..d91b552f39123cfc6e808dfe3bc8bab097448497
--- /dev/null
+++ b/src/ptbench/data/padchest/idiap.py
@@ -0,0 +1,45 @@
+# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
+#
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+"""Padchest (idiap protocol) dataset for computer-aided diagnosis.
+
+* See :py:mod:`ptbench.data.padchest` for dataset details
+* This configuration resolution: 512 x 512 (default)
+"""
+
+from clapper.logging import setup
+
+from .. import return_subsets
+from ..base_datamodule import BaseDataModule
+from . import _maker
+
+logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
+
+
+class DefaultModule(BaseDataModule):
+ def __init__(
+ self,
+ train_batch_size=1,
+ predict_batch_size=1,
+ drop_incomplete_batch=False,
+ multiproc_kwargs=None,
+ ):
+ super().__init__(
+ train_batch_size=train_batch_size,
+ predict_batch_size=predict_batch_size,
+ drop_incomplete_batch=drop_incomplete_batch,
+ multiproc_kwargs=multiproc_kwargs,
+ )
+
+ def setup(self, stage: str):
+ self.dataset = _maker("idiap")
+ (
+ self.train_dataset,
+ self.validation_dataset,
+ self.extra_validation_datasets,
+ self.predict_dataset,
+ ) = return_subsets(self.dataset)
+
+
+datamodule = DefaultModule
diff --git a/src/ptbench/data/padchest/no_tb_idiap.py b/src/ptbench/data/padchest/no_tb_idiap.py
new file mode 100644
index 0000000000000000000000000000000000000000..78155abf3c5a44de88920da1833ddfa09b6bb244
--- /dev/null
+++ b/src/ptbench/data/padchest/no_tb_idiap.py
@@ -0,0 +1,56 @@
+# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
+#
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+"""Padchest tuberculosis (no TB idiap protocol) dataset for computer-aided
+diagnosis.
+
+* Protocol ``no TB idiap``:
+
+ * Training samples: 20'126
+ * Validation samples: 1'500
+ * Test samples: 0
+
+* Images path adapted to Idiap infrastructure
+
+* Labels:
+ cardiomegaly, emphysema, effusion, hernia, infiltration,
+ mass, nodule, atelectasis, pneumothorax, pleural thickening, pneumonia,
+ fibrosis, edema and consolidation
+"""
+
+from clapper.logging import setup
+
+from .. import return_subsets
+from ..base_datamodule import BaseDataModule
+from . import _maker
+
+logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
+
+
+class DefaultModule(BaseDataModule):
+ def __init__(
+ self,
+ train_batch_size=1,
+ predict_batch_size=1,
+ drop_incomplete_batch=False,
+ multiproc_kwargs=None,
+ ):
+ super().__init__(
+ train_batch_size=train_batch_size,
+ predict_batch_size=predict_batch_size,
+ drop_incomplete_batch=drop_incomplete_batch,
+ multiproc_kwargs=multiproc_kwargs,
+ )
+
+ def setup(self, stage: str):
+ self.dataset = _maker("no_tb_idiap")
+ (
+ self.train_dataset,
+ self.validation_dataset,
+ self.extra_validation_datasets,
+ self.predict_dataset,
+ ) = return_subsets(self.dataset)
+
+
+datamodule = DefaultModule
diff --git a/src/ptbench/data/padchest/tb_idiap.py b/src/ptbench/data/padchest/tb_idiap.py
new file mode 100644
index 0000000000000000000000000000000000000000..51428935d728d243b34eec4e54c2d1fcc911224b
--- /dev/null
+++ b/src/ptbench/data/padchest/tb_idiap.py
@@ -0,0 +1,49 @@
+# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
+#
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+"""Padchest tuberculosis (idiap protocol) dataset for computer-aided diagnosis.
+
+The 125 healthy images are the first 125 padchest images with the following
+parameters: Label = "Normal", MethodLabel = "Physician", Projection = "PA"
+
+* Split reference: first 80% of TB and healthy CXR for "train", rest for "test"
+* See :py:mod:`ptbench.data.padchest` for dataset details
+* This configuration resolution: 512 x 512 (default)
+"""
+
+from clapper.logging import setup
+
+from .. import return_subsets
+from ..base_datamodule import BaseDataModule
+from . import _maker
+
+logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
+
+
+class DefaultModule(BaseDataModule):
+ def __init__(
+ self,
+ train_batch_size=1,
+ predict_batch_size=1,
+ drop_incomplete_batch=False,
+ multiproc_kwargs=None,
+ ):
+ super().__init__(
+ train_batch_size=train_batch_size,
+ predict_batch_size=predict_batch_size,
+ drop_incomplete_batch=drop_incomplete_batch,
+ multiproc_kwargs=multiproc_kwargs,
+ )
+
+ def setup(self, stage: str):
+ self.dataset = _maker("tb_idiap", RGB=False)
+ (
+ self.train_dataset,
+ self.validation_dataset,
+ self.extra_validation_datasets,
+ self.predict_dataset,
+ ) = return_subsets(self.dataset)
+
+
+datamodule = DefaultModule
diff --git a/src/ptbench/data/padchest/tb_idiap_rgb.py b/src/ptbench/data/padchest/tb_idiap_rgb.py
new file mode 100644
index 0000000000000000000000000000000000000000..f13876f725a0610ca2babbadb4011d56c2b8599f
--- /dev/null
+++ b/src/ptbench/data/padchest/tb_idiap_rgb.py
@@ -0,0 +1,50 @@
+# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
+#
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+"""Padchest tuberculosis (idiap protocol, rgb) dataset for computer-aided
+diagnosis.
+
+The 125 healthy images are the first 125 padchest images with the following
+parameters: Label = "Normal", MethodLabel = "Physician", Projection = "PA"
+
+* Split reference: first 80% of TB and healthy CXR for "train", rest for "test"
+* See :py:mod:`ptbench.data.padchest` for dataset details
+* This configuration resolution: 224 x 224 (default)
+"""
+
+from clapper.logging import setup
+
+from .. import return_subsets
+from ..base_datamodule import BaseDataModule
+from . import _maker
+
+logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
+
+
+class DefaultModule(BaseDataModule):
+ def __init__(
+ self,
+ train_batch_size=1,
+ predict_batch_size=1,
+ drop_incomplete_batch=False,
+ multiproc_kwargs=None,
+ ):
+ super().__init__(
+ train_batch_size=train_batch_size,
+ predict_batch_size=predict_batch_size,
+ drop_incomplete_batch=drop_incomplete_batch,
+ multiproc_kwargs=multiproc_kwargs,
+ )
+
+ def setup(self, stage: str):
+ self.dataset = _maker("tb_idiap", resize_size=256, cc_size=224)
+ (
+ self.train_dataset,
+ self.validation_dataset,
+ self.extra_validation_datasets,
+ self.predict_dataset,
+ ) = return_subsets(self.dataset)
+
+
+datamodule = DefaultModule