Remove input_size argument from models #1827

src/anomalib/models/image/cfa/lightning_model.py

@@ -30,8 +30,6 @@ class Cfa(AnomalyModule):
     """CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization.
 
     Args:
-        input_size (tuple[int, int]): Size of the model input.
-            Defaults to ``(256, 256)``.
         backbone (str): Backbone CNN network
             Defaults to ``"wide_resnet50_2"``.
         gamma_c (int, optional): gamma_c value from the paper.

src/anomalib/models/image/cfa/torch_model.py

@@ -85,7 +85,6 @@ class CfaModel(DynamicBufferMixin):
     """Torch implementation of the CFA Model.
 
     Args:
-        input_size: (tuple[int, int]): Input size of the image tensor.
         backbone (str): Backbone CNN network.
         gamma_c (int): gamma_c parameter from the paper.
         gamma_d (int): gamma_d parameter from the paper.

src/anomalib/models/image/cflow/lightning_model.py

@@ -32,8 +32,6 @@ class Cflow(AnomalyModule):
     """PL Lightning Module for the CFLOW algorithm.
 
     Args:
-        input_size (tuple[int, int], optional): Input image size.
-            Defaults to ``(256, 256)``.
         backbone (str, optional): Backbone CNN architecture.
             Defaults to ``"wide_resnet50_2"``.
         layers (Sequence[str], optional): Layers to extract features from.

src/anomalib/models/image/cflow/torch_model.py

@@ -20,7 +20,6 @@ class CflowModel(nn.Module):
     """CFLOW: Conditional Normalizing Flows.
 
     Args:
-        input_size (tuple[int, int]): Input image size.
         backbone (str): Backbone CNN architecture.
         layers (Sequence[str]): Layers to extract features from.
         pre_trained (bool): Whether to use pre-trained weights.

src/anomalib/models/image/csflow/lightning_model.py

@@ -28,8 +28,6 @@ class Csflow(AnomalyModule):
     """Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection.
 
     Args:
-        input_size (tuple[int, int]): Size of the model input.
-            Defaults to ``(256, 256)``.
         n_coupling_blocks (int): Number of coupling blocks in the model.
             Defaults to ``4``.
         cross_conv_hidden_channels (int): Number of hidden channels in the cross convolution.
@@ -60,7 +58,7 @@ def __init__(
 
     def _setup(self) -> None:
         if self.input_size is None:
-            msg = "Csflow needs input size to build torch model."
+            msg = "CsFlow needs input size to build torch model."
             raise ValueError(msg)
 
         self.model = CsFlowModel(

src/anomalib/models/image/fastflow/lightning_model.py

@@ -24,8 +24,6 @@ class Fastflow(AnomalyModule):
     """PL Lightning Module for the FastFlow algorithm.
 
     Args:
-        input_size (tuple[int, int]): Model input size.
-            Defaults to ``(256, 256)``.
         backbone (str): Backbone CNN network
             Defaults to ``resnet18``.
         pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.

src/anomalib/models/image/ganomaly/lightning_model.py

@@ -27,8 +27,6 @@ class Ganomaly(AnomalyModule):
     """PL Lightning Module for the GANomaly Algorithm.
 
     Args:
-        input_size (tuple[int, int]): Input dimension.
-            Defaults to ``(256, 256)``.
         batch_size (int): Batch size.
             Defaults to ``32``.
         n_features (int): Number of features layers in the CNNs.
@@ -94,7 +92,7 @@ def __init__(
 
     def _setup(self) -> None:
         if self.input_size is None:
-            msg = "CSflow needs input size to build torch model."
+            msg = "GANomaly needs input size to build torch model."
             raise ValueError(msg)
 
         self.model = GanomalyModel(

src/anomalib/models/image/padim/lightning_model.py

@@ -27,8 +27,6 @@ class Padim(MemoryBankMixin, AnomalyModule):
     """PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization.
 
     Args:
-        input_size (tuple[int, int]): Size of the model input.
-            Defaults to ``(256, 256)``.
         backbone (str): Backbone CNN network
             Defaults to ``resnet18``.
         layers (list[str]): Layers to extract features from the backbone CNN

src/anomalib/models/image/padim/torch_model.py

@@ -55,7 +55,6 @@ class PadimModel(nn.Module):
     """Padim Module.
 
     Args:
-        input_size (tuple[int, int]): Input size for the model.
         layers (list[str]): Layers used for feature extraction
         backbone (str, optional): Pre-trained model backbone. Defaults to "resnet18".
             Defaults to ``resnet18``.

src/anomalib/models/image/patchcore/anomaly_map.py

@@ -15,8 +15,7 @@ class AnomalyMapGenerator(nn.Module):
     """Generate Anomaly Heatmap.
 
     Args:
-        input_size (ListConfig, tuple): Size of the input image.
-            The anomaly map is upsampled to this dimension.
+        The anomaly map is upsampled to this dimension.
         sigma (int, optional): Standard deviation for Gaussian Kernel.
             Defaults to ``4``.
     """
@@ -65,7 +64,7 @@ def forward(
                 Defaults to None.
 
         Example:
-            >>> anomaly_map_generator = AnomalyMapGenerator(input_size=input_size)
+            >>> anomaly_map_generator = AnomalyMapGenerator()
             >>> map = anomaly_map_generator(patch_scores=patch_scores)
 
         Returns:

src/anomalib/models/image/patchcore/lightning_model.py

@@ -26,8 +26,6 @@ class Patchcore(MemoryBankMixin, AnomalyModule):
     """PatchcoreLightning Module to train PatchCore algorithm.
 
     Args:
-        input_size (tuple[int, int]): Size of the model input.
-            Defaults to ``(224, 224)``.
         backbone (str): Backbone CNN network
             Defaults to ``wide_resnet50_2``.
         layers (list[str]): Layers to extract features from the backbone CNN

src/anomalib/models/image/patchcore/torch_model.py

@@ -22,7 +22,6 @@ class PatchcoreModel(DynamicBufferMixin, nn.Module):
     """Patchcore Module.
 
     Args:
-        input_size (tuple[int, int]): Input size for the model.
         layers (list[str]): Layers used for feature extraction
         backbone (str, optional): Pre-trained model backbone.
             Defaults to ``resnet18``.

src/anomalib/models/image/reverse_distillation/lightning_model.py

@@ -26,8 +26,6 @@ class ReverseDistillation(AnomalyModule):
     """PL Lightning Module for Reverse Distillation Algorithm.
 
     Args:
-        input_size (tuple[int, int]): Size of model input
-            Defaults to ``(256, 256)``.
         backbone (str): Backbone of CNN network
             Defaults to ``wide_resnet50_2``.
         layers (list[str]): Layers to extract features from the backbone CNN

src/anomalib/models/image/reverse_distillation/torch_model.py

@@ -26,8 +26,8 @@ class ReverseDistillationModel(nn.Module):
         self.encoder = torchvision.models.wide_resnet50_2(pretrained=True)
 
     Args:
-        backbone (str): Name of the backbone used for encoder and decoder
-        input_size (tuple[int, int]): Size of input image
+        backbone (str): Name of the backbone used for encoder and decoder.
+        input_size (tuple[int, int]): Size of input image.
         layers (list[str]): Name of layers from which the features are extracted.
         anomaly_map_mode (str): Mode used to generate anomaly map. Options are between ``multiply`` and ``add``.
         pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.

src/anomalib/models/image/stfpm/lightning_model.py

@@ -27,8 +27,6 @@ class Stfpm(AnomalyModule):
     """PL Lightning Module for the STFPM algorithm.
 
     Args:
-        input_size (tuple[int, int]): Size of the model input.
-            Defaults to ``(256, 256)``.
         backbone (str): Backbone CNN network
             Defaults to ``resnet18``.
         layers (list[str]): Layers to extract features from the backbone CNN

src/anomalib/models/image/stfpm/torch_model.py

@@ -22,8 +22,7 @@ class STFPMModel(nn.Module):
     """STFPM: Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection.
 
     Args:
-        layers (list[str]): Layers used for feature extraction
-        input_size (tuple[int, int]): Input size for the model.
+        layers (list[str]): Layers used for feature extraction.
         backbone (str, optional): Pre-trained model backbone.
             Defaults to ``resnet18``.
     """

src/anomalib/models/image/uflow/lightning_model.py

@@ -41,7 +41,6 @@ def __init__(
         """Uflow model.
 
         Args:
-            input_size (tuple[int, int]): Input image size.
             backbone (str): Backbone name.
             flow_steps (int): Number of flow steps.
             affine_clamp (float): Affine clamp.