📝 Add benchmarking notebook

anomalib/data/__init__.py

@@ -19,10 +19,10 @@
 from omegaconf import DictConfig, ListConfig
 from pytorch_lightning import LightningDataModule
 
-from .btech import BTechDataModule
-from .folder import FolderDataModule
+from .btech import BTech
+from .folder import Folder
 from .inference import InferenceDataset
-from .mvtec import MVTecDataModule
+from .mvtec import MVTec
 
 
 def get_datamodule(config: Union[DictConfig, ListConfig]) -> LightningDataModule:
@@ -37,7 +37,7 @@ def get_datamodule(config: Union[DictConfig, ListConfig]) -> LightningDataModule
     datamodule: LightningDataModule
 
     if config.dataset.format.lower() == "mvtec":
-        datamodule = MVTecDataModule(
+        datamodule = MVTec(
             # TODO: Remove config values. IAAALD-211
             root=config.dataset.path,
             category=config.dataset.category,
@@ -52,7 +52,7 @@ def get_datamodule(config: Union[DictConfig, ListConfig]) -> LightningDataModule
             create_validation_set=config.dataset.create_validation_set,
         )
     elif config.dataset.format.lower() == "btech":
-        datamodule = BTechDataModule(
+        datamodule = BTech(
             # TODO: Remove config values. IAAALD-211
             root=config.dataset.path,
             category=config.dataset.category,
@@ -67,7 +67,7 @@ def get_datamodule(config: Union[DictConfig, ListConfig]) -> LightningDataModule
             create_validation_set=config.dataset.create_validation_set,
         )
     elif config.dataset.format.lower() == "folder":
-        datamodule = FolderDataModule(
+        datamodule = Folder(
             root=config.dataset.path,
             normal_dir=config.dataset.normal_dir,
             abnormal_dir=config.dataset.abnormal_dir,
@@ -97,8 +97,8 @@ def get_datamodule(config: Union[DictConfig, ListConfig]) -> LightningDataModule
 
 __all__ = [
     "get_datamodule",
-    "BTechDataModule",
-    "FolderDataModule",
+    "BTech",
+    "Folder",
     "InferenceDataset",
-    "MVTecDataModule",
+    "MVTec",
 ]

anomalib/data/btech.py

@@ -141,7 +141,7 @@ def make_btech_dataset(
     return samples
 
 
-class BTech(VisionDataset):
+class BTechDataset(VisionDataset):
     """BTech PyTorch Dataset."""
 
     def __init__(
@@ -166,10 +166,10 @@ def __init__(
             create_validation_set: Create a validation subset in addition to the train and test subsets
 
         Examples:
-            >>> from anomalib.data.btech import BTech
+            >>> from anomalib.data.btech import BTechDataset
             >>> from anomalib.data.transforms import PreProcessor
             >>> pre_process = PreProcessor(image_size=256)
-            >>> dataset = BTech(
+            >>> dataset = BTechDataset(
             ...     root='./datasets/BTech',
             ...     category='leather',
             ...     pre_process=pre_process,
@@ -257,7 +257,7 @@ def __getitem__(self, index: int) -> Dict[str, Union[str, Tensor]]:
         return item
 
 
-class BTechDataModule(LightningDataModule):
+class BTech(LightningDataModule):
     """BTechDataModule Lightning Data Module."""
 
     def __init__(
@@ -291,8 +291,8 @@ def __init__(
             create_validation_set: Create a validation subset in addition to the train and test subsets
 
         Examples
-            >>> from anomalib.data import BTechDataModule
-            >>> datamodule = BTechDataModule(
+            >>> from anomalib.data import BTech
+            >>> datamodule = BTech(
             ...     root="./datasets/BTech",
             ...     category="leather",
             ...     image_size=256,
@@ -398,7 +398,7 @@ def setup(self, stage: Optional[str] = None) -> None:
         """
         logger.info("Setting up train, validation, test and prediction datasets.")
         if stage in (None, "fit"):
-            self.train_data = BTech(
+            self.train_data = BTechDataset(
                 root=self.root,
                 category=self.category,
                 pre_process=self.pre_process_train,
@@ -409,7 +409,7 @@ def setup(self, stage: Optional[str] = None) -> None:
             )
 
         if self.create_validation_set:
-            self.val_data = BTech(
+            self.val_data = BTechDataset(
                 root=self.root,
                 category=self.category,
                 pre_process=self.pre_process_val,
@@ -419,7 +419,7 @@ def setup(self, stage: Optional[str] = None) -> None:
                 create_validation_set=self.create_validation_set,
             )
 
-        self.test_data = BTech(
+        self.test_data = BTechDataset(
             root=self.root,
             category=self.category,
             pre_process=self.pre_process_val,

anomalib/data/folder.py

@@ -301,7 +301,7 @@ def __getitem__(self, index: int) -> Dict[str, Union[str, Tensor]]:
         return item
 
 
-class FolderDataModule(LightningDataModule):
+class Folder(LightningDataModule):
     """Folder Lightning Data Module."""
 
     def __init__(
@@ -359,8 +359,8 @@ def __init__(
 
         Examples:
             Assume that we use Folder Dataset for the MVTec/bottle/broken_large category. We would do:
-            >>> from anomalib.data import FolderDataModule
-            >>> datamodule = FolderDataModule(
+            >>> from anomalib.data import Folder
+            >>> datamodule = Folder(
             ...     root="./datasets/MVTec/bottle/test",
             ...     normal="good",
             ...     abnormal="broken_large",
@@ -379,7 +379,7 @@ def __init__(
             The dataset expects that mask annotation filenames must be same as the original filename.
             To this end, we modified mask filenames in MVTec AD bottle category.
             Now we could try folder data module using the mvtec bottle broken large category
-            >>> datamodule = FolderDataModule(
+            >>> datamodule = Folder(
             ...     root="./datasets/bottle/test",
             ...     normal="good",
             ...     abnormal="broken_large",
@@ -401,7 +401,7 @@ def __init__(
             By default, Folder Data Module does not create a validation set. If a validation set
             is needed it could be set as follows:
 
-            >>> datamodule = FolderDataModule(
+            >>> datamodule = Folder(
             ...     root="./datasets/bottle/test",
             ...     normal="good",
             ...     abnormal="broken_large",

anomalib/data/mvtec.py

@@ -164,7 +164,7 @@ def make_mvtec_dataset(
     return samples
 
 
-class MVTec(VisionDataset):
+class MVTecDataset(VisionDataset):
     """MVTec AD PyTorch Dataset."""
 
     def __init__(
@@ -189,10 +189,10 @@ def __init__(
             create_validation_set: Create a validation subset in addition to the train and test subsets
 
         Examples:
-            >>> from anomalib.data.mvtec import MVTec
+            >>> from anomalib.data.mvtec import MVTecDataset
             >>> from anomalib.data.transforms import PreProcessor
             >>> pre_process = PreProcessor(image_size=256)
-            >>> dataset = MVTec(
+            >>> dataset = MVTecDataset(
             ...     root='./datasets/MVTec',
             ...     category='leather',
             ...     pre_process=pre_process,
@@ -280,7 +280,7 @@ def __getitem__(self, index: int) -> Dict[str, Union[str, Tensor]]:
         return item
 
 
-class MVTecDataModule(LightningDataModule):
+class MVTec(LightningDataModule):
     """MVTec AD Lightning Data Module."""
 
     def __init__(
@@ -314,8 +314,8 @@ def __init__(
             create_validation_set: Create a validation subset in addition to the train and test subsets
 
         Examples
-            >>> from anomalib.data import MVTecDataModule
-            >>> datamodule = MVTecDataModule(
+            >>> from anomalib.data import MVTec
+            >>> datamodule = MVTec(
             ...     root="./datasets/MVTec",
             ...     category="leather",
             ...     image_size=256,
@@ -404,7 +404,7 @@ def setup(self, stage: Optional[str] = None) -> None:
         """
         logger.info("Setting up train, validation, test and prediction datasets.")
         if stage in (None, "fit"):
-            self.train_data = MVTec(
+            self.train_data = MVTecDataset(
                 root=self.root,
                 category=self.category,
                 pre_process=self.pre_process_train,
@@ -415,7 +415,7 @@ def setup(self, stage: Optional[str] = None) -> None:
             )
 
         if self.create_validation_set:
-            self.val_data = MVTec(
+            self.val_data = MVTecDataset(
                 root=self.root,
                 category=self.category,
                 pre_process=self.pre_process_val,
@@ -425,7 +425,7 @@ def setup(self, stage: Optional[str] = None) -> None:
                 create_validation_set=self.create_validation_set,
             )
 
-        self.test_data = MVTec(
+        self.test_data = MVTecDataset(
             root=self.root,
             category=self.category,
             pre_process=self.pre_process_val,

anomalib/models/draem/config.yaml

@@ -45,8 +45,11 @@ metrics:
 project:
   seed: 42
   path: ./results
-  log_images_to: ["local"]
-  logger: false # options: [tensorboard, wandb, csv] or combinations.
+
+logging:
+  log_images_to: ["local"] # options: [wandb, tensorboard, local]. Make sure you also set logger with using wandb or tensorboard.
+  logger: [] # options: [tensorboard, wandb, csv] or combinations.
+  log_graph: false # Logs the model graph to respective logger.
 
 optimization:
   openvino:

anomalib/models/fastflow/config.yaml

@@ -47,10 +47,13 @@ metrics:
     adaptive: true
 
 project:
-  seed: 0
+  seed: 42
   path: ./results
-  log_images_to: [local]
-  logger: false # options: [tensorboard, wandb, csv] or combinations.
+
+logging:
+  log_images_to: ["local"] # options: [wandb, tensorboard, local]. Make sure you also set logger with using wandb or tensorboard.
+  logger: [] # options: [tensorboard, wandb, csv] or combinations.
+  log_graph: false # Logs the model graph to respective logger.
 
 # PL Trainer Args. Don't add extra parameter here.
 trainer: