From d3ebced165b0949afa5c3eaee8cbd1a76d224dc3 Mon Sep 17 00:00:00 2001
From: Samet Akcay <samet.akcay@intel.com>
Date: Thu, 20 Jul 2023 14:40:12 +0100
Subject: [PATCH] Revert "Add default values to algorithms " (#1193)

Revert "Add default values to algorithms  (#1169)"

This reverts commit 27876c851eb97a5b081b89a0059b7cbb2cad9688.
---
 CHANGELOG.md                                  |  1 -
 src/anomalib/models/cfa/lightning_model.py    | 14 +++++-----
 src/anomalib/models/cfa/torch_model.py        | 28 +++++++++----------
 src/anomalib/models/cflow/lightning_model.py  |  6 ++--
 src/anomalib/models/cflow/torch_model.py      |  6 ++--
 src/anomalib/models/csflow/lightning_model.py | 21 +++++++-------
 src/anomalib/models/csflow/torch_model.py     | 15 +++++-----
 src/anomalib/models/dfkde/lightning_model.py  |  9 +++---
 src/anomalib/models/dfkde/torch_model.py      | 14 ++++++----
 src/anomalib/models/dfm/lightning_model.py    | 19 ++++++-------
 src/anomalib/models/dfm/torch_model.py        | 14 +++++-----
 .../models/efficient_ad/lightning_model.py    |  9 +++---
 .../models/efficient_ad/torch_model.py        |  9 +++---
 src/anomalib/models/fastflow/config.yaml      | 10 +++----
 .../models/fastflow/lightning_model.py        | 18 ++++++------
 src/anomalib/models/fastflow/torch_model.py   | 18 ++++++------
 .../models/ganomaly/lightning_model.py        | 16 +++++------
 src/anomalib/models/ganomaly/torch_model.py   | 16 +++++------
 src/anomalib/models/padim/config.yaml         |  2 +-
 src/anomalib/models/padim/lightning_model.py  | 17 ++++++-----
 src/anomalib/models/padim/torch_model.py      | 16 +++++------
 .../models/patchcore/lightning_model.py       | 15 +++++-----
 src/anomalib/models/patchcore/torch_model.py  | 10 +++++--
 .../reverse_distillation/lightning_model.py   | 26 ++++++++---------
 .../reverse_distillation/torch_model.py       | 23 ++++++++-------
 src/anomalib/models/stfpm/config.yaml         |  2 +-
 src/anomalib/models/stfpm/lightning_model.py  | 13 ++++-----
 src/anomalib/models/stfpm/torch_model.py      |  6 ++--
 28 files changed, 186 insertions(+), 187 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index a80831317e..e5b17e8d51 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,7 +10,6 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Changed
 
-- Add default values to algorithms, based on the original papers.
 - Improve default settings of EfficientAD
 
 ### Deprecated
diff --git a/src/anomalib/models/cfa/lightning_model.py b/src/anomalib/models/cfa/lightning_model.py
index 4b3bd65333..0e9e983184 100644
--- a/src/anomalib/models/cfa/lightning_model.py
+++ b/src/anomalib/models/cfa/lightning_model.py
@@ -33,19 +33,19 @@ class Cfa(AnomalyModule):
     """CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization.
 
     Args:
-        input_size (tuple[int, int], optional): Size of the model input. Defaults to (224, 224).
-        backbone (str, optional): Backbone CNN network. Defaults to "wide_resnet50_2".
+        input_size (tuple[int, int]): Size of the model input.
+        backbone (str): Backbone CNN network
         gamma_c (int, optional): gamma_c value from the paper. Defaults to 1.
         gamma_d (int, optional): gamma_d value from the paper. Defaults to 1.
-        num_nearest_neighbors (int, optional): Number of nearest neighbors. Defaults to 3.
-        num_hard_negative_features (int, optional): Number of hard negative features. Defaults to 3.
-        radius (float, optional): Radius of the hypersphere to search the soft boundary. Defaults to 1e-5.
+        num_nearest_neighbors (int): Number of nearest neighbors.
+        num_hard_negative_features (int): Number of hard negative features.
+        radius (float): Radius of the hypersphere to search the soft boundary.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (224, 224),
-        backbone: str = "wide_resnet50_2",
+        input_size: tuple[int, int],
+        backbone: str,
         gamma_c: int = 1,
         gamma_d: int = 1,
         num_nearest_neighbors: int = 3,
diff --git a/src/anomalib/models/cfa/torch_model.py b/src/anomalib/models/cfa/torch_model.py
index 4afe2b52cb..cebc5297dd 100644
--- a/src/anomalib/models/cfa/torch_model.py
+++ b/src/anomalib/models/cfa/torch_model.py
@@ -82,24 +82,24 @@ class CfaModel(DynamicBufferModule):
     """Torch implementation of the CFA Model.
 
     Args:
-        input_size: (tuple[int, int], optional): Input size of the image tensor. Defaults to (224, 224).
-        backbone (str, optional): Backbone CNN network. Defaults to "wide_resnet50_2".
-        gamma_c (int, optional): gamma_c parameter from the paper. Defaults to 1.
-        gamma_d (int, optional): gamma_d parameter from the paper. Defaults to 1.
-        num_nearest_neighbors (int, optional): Number of nearest neighbors. Defaults to 3.
-        num_hard_negative_features (int, optional): Number of hard negative features. Defaults to 3.
-        radius (float, optional): Radius of the hypersphere to search the soft boundary. Defaults to 1e-5.
+        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.
+        num_nearest_neighbors (int): Number of nearest neighbors.
+        num_hard_negative_features (int): Number of hard negative features.
+        radius (float): Radius of the hypersphere to search the soft boundary.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (224, 224),
-        backbone: str = "wide_resnet50_2",
-        gamma_c: int = 1,
-        gamma_d: int = 1,
-        num_nearest_neighbors: int = 3,
-        num_hard_negative_features: int = 3,
-        radius: float = 1e-5,
+        input_size: tuple[int, int],
+        backbone: str,
+        gamma_c: int,
+        gamma_d: int,
+        num_nearest_neighbors: int,
+        num_hard_negative_features: int,
+        radius: float,
     ) -> None:
         super().__init__()
         self.input_size = torch.Size(input_size)
diff --git a/src/anomalib/models/cflow/lightning_model.py b/src/anomalib/models/cflow/lightning_model.py
index a57371f6ac..f3b604b04f 100644
--- a/src/anomalib/models/cflow/lightning_model.py
+++ b/src/anomalib/models/cflow/lightning_model.py
@@ -29,9 +29,9 @@ class Cflow(AnomalyModule):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
+        input_size: tuple[int, int],
+        backbone: str,
+        layers: list[str],
         pre_trained: bool = True,
         fiber_batch_size: int = 64,
         decoder: str = "freia-cflow",
diff --git a/src/anomalib/models/cflow/torch_model.py b/src/anomalib/models/cflow/torch_model.py
index ed7ea570db..2c518475d1 100644
--- a/src/anomalib/models/cflow/torch_model.py
+++ b/src/anomalib/models/cflow/torch_model.py
@@ -21,9 +21,9 @@ class CflowModel(nn.Module):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
+        input_size: tuple[int, int],
+        backbone: str,
+        layers: list[str],
         pre_trained: bool = True,
         fiber_batch_size: int = 64,
         decoder: str = "freia-cflow",
diff --git a/src/anomalib/models/csflow/lightning_model.py b/src/anomalib/models/csflow/lightning_model.py
index eedb9b0927..6b829e712c 100644
--- a/src/anomalib/models/csflow/lightning_model.py
+++ b/src/anomalib/models/csflow/lightning_model.py
@@ -30,21 +30,20 @@ class Csflow(AnomalyModule):
     """Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection.
 
     Args:
-        input_size (tuple[int, int], optional): Size of the model input. Defaults to (768, 768).
-        cross_conv_hidden_channels (int, optional): Number of hidden channels in the cross convolution.
-            Defaults to 1024.
-        n_coupling_blocks (int, optional): Number of coupling blocks in the model. Defaults to 4.
-        clamp (int, optional): Clamp value for glow layer. Defaults to 3.
-        num_channels (int, optional): Number of channels in the model. Defaults to 3.
+        input_size (tuple[int, int]): Size of the model input.
+        n_coupling_blocks (int): Number of coupling blocks in the model.
+        cross_conv_hidden_channels (int): Number of hidden channels in the cross convolution.
+        clamp (int): Clamp value for glow layer.
+        num_channels (int): Number of channels in the model.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (768, 768),
-        cross_conv_hidden_channels: int = 1024,
-        n_coupling_blocks: int = 4,
-        clamp: int = 3,
-        num_channels: int = 3,
+        input_size: tuple[int, int],
+        cross_conv_hidden_channels: int,
+        n_coupling_blocks: int,
+        clamp: int,
+        num_channels: int,
     ) -> None:
         super().__init__()
         self.model: CsFlowModel = CsFlowModel(
diff --git a/src/anomalib/models/csflow/torch_model.py b/src/anomalib/models/csflow/torch_model.py
index 467cfbc01a..05129c076d 100644
--- a/src/anomalib/models/csflow/torch_model.py
+++ b/src/anomalib/models/csflow/torch_model.py
@@ -504,18 +504,17 @@ class CsFlowModel(nn.Module):
     """CS Flow Module.
 
     Args:
-        input_size (tuple[int, int], optional): Size of the model input. Defaults to (768, 768).
-        cross_conv_hidden_channels (int, optional): Number of hidden channels in the cross convolution.
-            Defaults to 1024.
-        n_coupling_blocks (int, optional): Number of coupling blocks in the model. Defaults to 4.
-        clamp (int, optional): Clamp value for glow layer. Defaults to 3.
-        num_channels (int, optional): Number of channels in the model. Defaults to 3.
+        input_size (tuple[int, int]): Input image size.
+        cross_conv_hidden_channels (int): Number of hidden channels in the cross convolution.
+        n_coupling_blocks (int): Number of coupling blocks.
+        clamp (float): Clamp value for the coupling blocks.
+        num_channels (int): Number of channels in the input image.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (768, 768),
-        cross_conv_hidden_channels: int = 1024,
+        input_size: tuple[int, int],
+        cross_conv_hidden_channels: int,
         n_coupling_blocks: int = 4,
         clamp: int = 3,
         num_channels: int = 3,
diff --git a/src/anomalib/models/dfkde/lightning_model.py b/src/anomalib/models/dfkde/lightning_model.py
index 0ab9386cb1..0a63648fc6 100644
--- a/src/anomalib/models/dfkde/lightning_model.py
+++ b/src/anomalib/models/dfkde/lightning_model.py
@@ -24,9 +24,8 @@ class Dfkde(AnomalyModule):
     """DFKDE: Deep Feature Kernel Density Estimation.
 
     Args:
-        backbone (str, optional): Pre-trained model backbone. Defaults to "resnet18".
-        layers (list[str], optional): List of layers to extract features from. Defaults to ["layer4"].
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
+        backbone (str): Pre-trained model backbone.
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         max_training_points (int, optional): Number of training points to fit the KDE model.
             Defaults to 40000.
         pre_processing (str, optional): Preprocess features before passing to KDE.
@@ -39,8 +38,8 @@ class Dfkde(AnomalyModule):
 
     def __init__(
         self,
-        backbone: str = "resnet18",
-        layers: list[str] = ["layer4"],
+        layers: list[str],
+        backbone: str,
         pre_trained: bool = True,
         n_pca_components: int = 16,
         feature_scaling_method: FeatureScalingMethod = FeatureScalingMethod.SCALE,
diff --git a/src/anomalib/models/dfkde/torch_model.py b/src/anomalib/models/dfkde/torch_model.py
index 2c7996ac08..5746442820 100644
--- a/src/anomalib/models/dfkde/torch_model.py
+++ b/src/anomalib/models/dfkde/torch_model.py
@@ -12,7 +12,10 @@
 from torch import Tensor, nn
 
 from anomalib.models.components import FeatureExtractor
-from anomalib.models.components.classification import FeatureScalingMethod, KDEClassifier
+from anomalib.models.components.classification import (
+    FeatureScalingMethod,
+    KDEClassifier,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -21,9 +24,8 @@ class DfkdeModel(nn.Module):
     """Normality Model for the DFKDE algorithm.
 
     Args:
-        backbone (str, optional): Pre-trained model backbone. Defaults to "resnet18".
-        layers (list[str], optional): List of layers to extract features from. Defaults to ["layer4"].
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
+        backbone (str): Pre-trained model backbone.
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         n_comps (int, optional): Number of PCA components. Defaults to 16.
         pre_processing (str, optional): Preprocess features before passing to KDE.
             Options are between `norm` and `scale`. Defaults to "scale".
@@ -34,8 +36,8 @@ class DfkdeModel(nn.Module):
 
     def __init__(
         self,
-        backbone: str = "resnet18",
-        layers: list[str] = ["layer4"],
+        layers: list[str],
+        backbone: str,
         pre_trained: bool = True,
         n_pca_components: int = 16,
         feature_scaling_method: FeatureScalingMethod = FeatureScalingMethod.SCALE,
diff --git a/src/anomalib/models/dfm/lightning_model.py b/src/anomalib/models/dfm/lightning_model.py
index ba70b0b7a5..4910f4b041 100644
--- a/src/anomalib/models/dfm/lightning_model.py
+++ b/src/anomalib/models/dfm/lightning_model.py
@@ -23,25 +23,24 @@ class Dfm(AnomalyModule):
     """DFM: Deep Featured Kernel Density Estimation.
 
     Args:
-        input_size (tuple[int, int], optional): Input size for the model. Defaults to (256, 256).
-        backbone (str, optional): Backbone CNN network. Defaults to "resnet50".
-        layer (str, optional): Layer to extract features from the backbone CNN. Defaults to "layer3".
+        backbone (str): Backbone CNN network
+        layer (str): Layer to extract features from the backbone CNN
+        input_size (tuple[int, int]): Input size for the model.
         pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         pooling_kernel_size (int, optional): Kernel size to pool features extracted from the CNN.
             Defaults to 4.
         pca_level (float, optional): Ratio from which number of components for PCA are calculated.
             Defaults to 0.97.
-        score_type (str, optional): Scoring type. Options are `fre` and `nll`.
-            nll: for Gaussian modeling, fre: pca feature-reconstruction error. Anomaly segmentation is
-            supported with `fre` only. If using `nll`, set `task` in config.yaml to classification
-            Defaults to "fre".
+        score_type (str, optional): Scoring type. Options are `fre` and `nll`. Defaults to "fre".
+        nll: for Gaussian modeling, fre: pca feature-reconstruction error. Anomaly segmentation is
+        supported with `fre` only. If using `nll`, set `task` in config.yaml to classification
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "resnet50",
-        layer: str = "layer3",
+        backbone: str,
+        layer: str,
+        input_size: tuple[int, int],
         pre_trained: bool = True,
         pooling_kernel_size: int = 4,
         pca_level: float = 0.97,
diff --git a/src/anomalib/models/dfm/torch_model.py b/src/anomalib/models/dfm/torch_model.py
index 5c9ab47f04..05a61c37c8 100644
--- a/src/anomalib/models/dfm/torch_model.py
+++ b/src/anomalib/models/dfm/torch_model.py
@@ -75,9 +75,9 @@ class DFMModel(nn.Module):
     """Model for the DFM algorithm.
 
     Args:
-        input_size (tuple[int, int], optional): Input size for the model. Defaults to (256, 256).
-        backbone (str, optional): Backbone CNN network. Defaults to "resnet50".
-        layer (str, optional): Layer to extract features from the backbone CNN. Defaults to "layer3".
+        backbone (str): Pre-trained model backbone.
+        layer (str): Layer from which to extract features.
+        input_size (tuple[int, int]): Input size for the model.
         pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         pooling_kernel_size (int, optional): Kernel size to pool features extracted from the CNN.
         n_comps (float, optional): Ratio from which number of components for PCA are calculated. Defaults to 0.97.
@@ -87,14 +87,14 @@ class DFMModel(nn.Module):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "resnet50",
-        layer: str = "layer3",
+        backbone: str,
+        layer: str,
+        input_size: tuple[int, int],
         pre_trained: bool = True,
         pooling_kernel_size: int = 4,
         n_comps: float = 0.97,
         score_type: str = "fre",
-    ) -> None:
+    ):
         super().__init__()
         self.backbone = backbone
         self.pooling_kernel_size = pooling_kernel_size
diff --git a/src/anomalib/models/efficient_ad/lightning_model.py b/src/anomalib/models/efficient_ad/lightning_model.py
index e446f520a1..0927abed35 100644
--- a/src/anomalib/models/efficient_ad/lightning_model.py
+++ b/src/anomalib/models/efficient_ad/lightning_model.py
@@ -53,8 +53,9 @@ class EfficientAd(AnomalyModule):
     """PL Lightning Module for the EfficientAd algorithm.
 
     Args:
-        image_size (tuple): size of input images. Defaults to (256, 256).
-        teacher_out_channels (int): number of convolution output channels. Defaults to 384.
+        teacher_file_name (str): path to the pre-trained teacher model
+        teacher_out_channels (int): number of convolution output channels
+        image_size (tuple): size of input images
         model_size (str): size of student and teacher model
         lr (float): learning rate
         weight_decay (float): optimizer weight decay
@@ -66,8 +67,8 @@ class EfficientAd(AnomalyModule):
 
     def __init__(
         self,
-        image_size: tuple[int, int] = (256, 256),
-        teacher_out_channels: int = 384,
+        teacher_out_channels: int,
+        image_size: tuple[int, int],
         model_size: EfficientAdModelSize = EfficientAdModelSize.S,
         lr: float = 0.0001,
         weight_decay: float = 0.00001,
diff --git a/src/anomalib/models/efficient_ad/torch_model.py b/src/anomalib/models/efficient_ad/torch_model.py
index 6370a1478f..13aa56cdad 100644
--- a/src/anomalib/models/efficient_ad/torch_model.py
+++ b/src/anomalib/models/efficient_ad/torch_model.py
@@ -188,8 +188,9 @@ class EfficientAdModel(nn.Module):
     """EfficientAd model.
 
     Args:
-        input_size (tuple): size of input images. Default: (256, 256)
-        teacher_out_channels (int): number of convolution output channels of the pre-trained teacher model. Default: 384
+        teacher_out_channels (int): number of convolution output channels of the pre-trained teacher model
+        pretrained_models_dir (str): path to the pretrained model weights
+        input_size (tuple): size of input images
         model_size (str): size of student and teacher model
         padding (bool): use padding in convoluional layers
         pad_maps (bool): relevant if padding is set to False. In this case, pad_maps = True pads the
@@ -199,8 +200,8 @@ class EfficientAdModel(nn.Module):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        teacher_out_channels: int = 384,
+        teacher_out_channels: int,
+        input_size: tuple[int, int],
         model_size: EfficientAdModelSize = EfficientAdModelSize.S,
         padding=False,
         pad_maps=True,
diff --git a/src/anomalib/models/fastflow/config.yaml b/src/anomalib/models/fastflow/config.yaml
index 48ddbebbb8..525b6a3412 100644
--- a/src/anomalib/models/fastflow/config.yaml
+++ b/src/anomalib/models/fastflow/config.yaml
@@ -7,7 +7,7 @@ dataset:
   train_batch_size: 32
   eval_batch_size: 32
   num_workers: 8
-  image_size: 384 # dimensions to which images are resized (mandatory) options: [256, 256, 448, 384]
+  image_size: 256 # dimensions to which images are resized (mandatory) options: [256, 256, 448, 384]
   center_crop: null # dimensions to which images are center-cropped after resizing (optional)
   normalization: imagenet # data distribution to which the images will be normalized: [none, imagenet]
   transform_config:
@@ -27,11 +27,11 @@ dataset:
 
 model:
   name: fastflow
-  backbone: deit_base_distilled_patch16_384 # options: [resnet18, wide_resnet50_2, cait_m48_448, deit_base_distilled_patch16_384]
+  backbone: resnet18 # options: [resnet18, wide_resnet50_2, cait_m48_448, deit_base_distilled_patch16_384]
   pre_trained: true
-  flow_steps: 20 # options: [8, 8, 20, 20] - for each supported backbone
-  hidden_ratio: 0.16 # options: [1.0, 1.0, 0.16, 0.16] - for each supported backbone
-  conv3x3_only: False # options: [True, False, False, False] - for each supported backbone
+  flow_steps: 8 # options: [8, 8, 20, 20] - for each supported backbone
+  hidden_ratio: 1.0 # options: [1.0, 1.0, 0.16, 0.16] - for each supported backbone
+  conv3x3_only: True # options: [True, False, False, False] - for each supported backbone
   lr: 0.001
   weight_decay: 0.00001
   early_stopping:
diff --git a/src/anomalib/models/fastflow/lightning_model.py b/src/anomalib/models/fastflow/lightning_model.py
index 80a839f576..c2d203b926 100644
--- a/src/anomalib/models/fastflow/lightning_model.py
+++ b/src/anomalib/models/fastflow/lightning_model.py
@@ -20,22 +20,22 @@ class Fastflow(AnomalyModule):
     """PL Lightning Module for the FastFlow algorithm.
 
     Args:
-        input_size (tuple[int, int]): Model input size. Defaults to (384, 384).
-        backbone (str): Backbone CNN network. Defaults to "deit_base_distilled_patch16_384".
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
-        flow_steps (int, optional): Flow steps. Defaults to 20.
-        hidden_ratio (float, optional): Ratio to calculate hidden var channels. Defaults to 0.16.
+        input_size (tuple[int, int]): Model input size.
+        backbone (str): Backbone CNN network
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
+        flow_steps (int, optional): Flow steps.
         conv3x3_only (bool, optinoal): Use only conv3x3 in fast_flow model. Defaults to False.
+        hidden_ratio (float, optional): Ratio to calculate hidden var channels. Defaults to 1.0.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (384, 384),
-        backbone: str = "deit_base_distilled_patch16_384",
+        input_size: tuple[int, int],
+        backbone: str,
         pre_trained: bool = True,
-        flow_steps: int = 20,
-        hidden_ratio: float = 0.16,
+        flow_steps: int = 8,
         conv3x3_only: bool = False,
+        hidden_ratio: float = 1.0,
     ) -> None:
         super().__init__()
 
diff --git a/src/anomalib/models/fastflow/torch_model.py b/src/anomalib/models/fastflow/torch_model.py
index 4edbeb8b93..1fbeba9564 100644
--- a/src/anomalib/models/fastflow/torch_model.py
+++ b/src/anomalib/models/fastflow/torch_model.py
@@ -98,12 +98,12 @@ class FastflowModel(nn.Module):
     Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows.
 
     Args:
-        input_size (tuple[int, int]): Model input size. Defaults to (384, 384).
-        backbone (str): Backbone CNN network. Defaults to "deit_base_distilled_patch16_384".
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
-        flow_steps (int, optional): Flow steps. Defaults to 20.
-        hidden_ratio (float, optional): Ratio to calculate hidden var channels. Defaults to 0.16.
+        input_size (tuple[int, int]): Model input size.
+        backbone (str): Backbone CNN network
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
+        flow_steps (int, optional): Flow steps.
         conv3x3_only (bool, optinoal): Use only conv3x3 in fast_flow model. Defaults to False.
+        hidden_ratio (float, optional): Ratio to calculate hidden var channels. Defaults to 1.0.
 
     Raises:
         ValueError: When the backbone is not supported.
@@ -111,12 +111,12 @@ class FastflowModel(nn.Module):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (384, 384),
-        backbone: str = "deit_base_distilled_patch16_384",
+        input_size: tuple[int, int],
+        backbone: str,
         pre_trained: bool = True,
-        flow_steps: int = 20,
-        hidden_ratio: float = 0.16,
+        flow_steps: int = 8,
         conv3x3_only: bool = False,
+        hidden_ratio: float = 1.0,
     ) -> None:
         super().__init__()
 
diff --git a/src/anomalib/models/ganomaly/lightning_model.py b/src/anomalib/models/ganomaly/lightning_model.py
index 9f8622e636..d8153fd6a5 100644
--- a/src/anomalib/models/ganomaly/lightning_model.py
+++ b/src/anomalib/models/ganomaly/lightning_model.py
@@ -28,10 +28,10 @@ class Ganomaly(AnomalyModule):
     """PL Lightning Module for the GANomaly Algorithm.
 
     Args:
-        batch_size (int, optional): Batch size. Defaults to 32.
-        input_size (tuple[int, int], optional): Input dimension. Defaults to (32, 32).
-        n_features (int, optional): Number of features layers in the CNNs. Defaults to 64.
-        latent_vec_size (int, optional): Size of autoencoder latent vector. Defaults to 100.
+        batch_size (int): Batch size.
+        input_size (tuple[int, int]): Input dimension.
+        n_features (int): Number of features layers in the CNNs.
+        latent_vec_size (int): Size of autoencoder latent vector.
         extra_layers (int, optional): Number of extra layers for encoder/decoder. Defaults to 0.
         add_final_conv_layer (bool, optional): Add convolution layer at the end. Defaults to True.
         wadv (int, optional): Weight for adversarial loss. Defaults to 1.
@@ -41,10 +41,10 @@ class Ganomaly(AnomalyModule):
 
     def __init__(
         self,
-        batch_size: int = 32,
-        input_size: tuple[int, int] = (32, 32),
-        n_features: int = 64,
-        latent_vec_size: int = 100,
+        batch_size: int,
+        input_size: tuple[int, int],
+        n_features: int,
+        latent_vec_size: int,
         extra_layers: int = 0,
         add_final_conv_layer: bool = True,
         wadv: int = 1,
diff --git a/src/anomalib/models/ganomaly/torch_model.py b/src/anomalib/models/ganomaly/torch_model.py
index 07d58704b5..bc707e9ab7 100644
--- a/src/anomalib/models/ganomaly/torch_model.py
+++ b/src/anomalib/models/ganomaly/torch_model.py
@@ -281,20 +281,20 @@ class GanomalyModel(nn.Module):
     """Ganomaly Model.
 
     Args:
-        input_size (tuple[int, int], optional): Input dimension. Defaults to (32, 32).
-        num_input_channels (int, optional): Number of input channels. Defaults to 3.
-        n_features (int, optional): Number of features layers in the CNNs. Defaults to 64.
-        latent_vec_size (int, optional): Size of autoencoder latent vector. Defaults to 100.
+        input_size (tuple[int, int]): Input dimension.
+        num_input_channels (int): Number of input channels.
+        n_features (int): Number of features layers in the CNNs.
+        latent_vec_size (int): Size of autoencoder latent vector.
         extra_layers (int, optional): Number of extra layers for encoder/decoder. Defaults to 0.
         add_final_conv_layer (bool, optional): Add convolution layer at the end. Defaults to True.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (32, 32),
-        num_input_channels: int = 3,
-        n_features: int = 64,
-        latent_vec_size: int = 100,
+        input_size: tuple[int, int],
+        num_input_channels: int,
+        n_features: int,
+        latent_vec_size: int,
         extra_layers: int = 0,
         add_final_conv_layer: bool = True,
     ) -> None:
diff --git a/src/anomalib/models/padim/config.yaml b/src/anomalib/models/padim/config.yaml
index 1cde9d4812..84b0d2d421 100644
--- a/src/anomalib/models/padim/config.yaml
+++ b/src/anomalib/models/padim/config.yaml
@@ -27,7 +27,7 @@ dataset:
 
 model:
   name: padim
-  backbone: wide_resnet50_2
+  backbone: resnet18
   pre_trained: true
   layers:
     - layer1
diff --git a/src/anomalib/models/padim/lightning_model.py b/src/anomalib/models/padim/lightning_model.py
index b97b1543e6..3e71163422 100644
--- a/src/anomalib/models/padim/lightning_model.py
+++ b/src/anomalib/models/padim/lightning_model.py
@@ -27,20 +27,19 @@ class Padim(AnomalyModule):
     """PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization.
 
     Args:
-        input_size (tuple[int, int], optional): Size of the model input. Default: (256, 256)
-        backbone (str, optional): Backbone CNN network. Default: "wide_resnet50_2"
-        layers (list[str], optional): Layers to extract features from the backbone CNN.
-            Default: ["layer1", "layer2", "layer3"]
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Default: True
+        layers (list[str]): Layers to extract features from the backbone CNN
+        input_size (tuple[int, int]): Size of the model input.
+        backbone (str): Backbone CNN network
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         n_features (int, optional): Number of features to retain in the dimension reduction step.
-            Default values from the paper are available for: resnet18 (100), wide_resnet50_2 (550).
+                                Default values from the paper are available for: resnet18 (100), wide_resnet50_2 (550).
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
+        layers: list[str],
+        input_size: tuple[int, int],
+        backbone: str,
         pre_trained: bool = True,
         n_features: int | None = None,
     ) -> None:
diff --git a/src/anomalib/models/padim/torch_model.py b/src/anomalib/models/padim/torch_model.py
index f481a4f49c..702a788bfb 100644
--- a/src/anomalib/models/padim/torch_model.py
+++ b/src/anomalib/models/padim/torch_model.py
@@ -50,19 +50,19 @@ class PadimModel(nn.Module):
     """Padim Module.
 
     Args:
-        input_size (tuple[int, int] optional): Input size for the model. Defaults to (256, 256).
-        backbone (str, optional): Pre-trained model backbone. Defaults to "wide_resnet50_2".
-        layers (list[str], optional): Layers used for feature extraction. Defaults to ["layer1", "layer2", "layer3"].
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
+        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".
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         n_features (int, optional): Number of features to retain in the dimension reduction step.
-            Default values from the paper are available for: resnet18 (100), wide_resnet50_2 (550).
+                                Default values from the paper are available for: resnet18 (100), wide_resnet50_2 (550).
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
+        input_size: tuple[int, int],
+        layers: list[str],
+        backbone: str = "resnet18",
         pre_trained: bool = True,
         n_features: int | None = None,
     ) -> None:
diff --git a/src/anomalib/models/patchcore/lightning_model.py b/src/anomalib/models/patchcore/lightning_model.py
index c3d95edac6..fbdb8949a2 100644
--- a/src/anomalib/models/patchcore/lightning_model.py
+++ b/src/anomalib/models/patchcore/lightning_model.py
@@ -25,11 +25,10 @@ class Patchcore(AnomalyModule):
     """PatchcoreLightning Module to train PatchCore algorithm.
 
     Args:
-        input_size (tuple[int, int], optional): Size of the model input. Defaults to (224, 224).
-        backbone (str, optional): Backbone CNN network. Defaults to "wide_resnet50_2".
-        layers (list[str], optional): Layers to extract features from the backbone CNN.
-            Defaults to ["layer2", "layer3"].
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
+        input_size (tuple[int, int]): Size of the model input.
+        backbone (str): Backbone CNN network
+        layers (list[str]): Layers to extract features from the backbone CNN
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
         coreset_sampling_ratio (float, optional): Coreset sampling ratio to subsample embedding.
             Defaults to 0.1.
         num_neighbors (int, optional): Number of nearest neighbors. Defaults to 9.
@@ -37,9 +36,9 @@ class Patchcore(AnomalyModule):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (224, 224),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer2", "layer3"],
+        input_size: tuple[int, int],
+        backbone: str,
+        layers: list[str],
         pre_trained: bool = True,
         coreset_sampling_ratio: float = 0.1,
         num_neighbors: int = 9,
diff --git a/src/anomalib/models/patchcore/torch_model.py b/src/anomalib/models/patchcore/torch_model.py
index e269dd0720..7f4f11f5fc 100644
--- a/src/anomalib/models/patchcore/torch_model.py
+++ b/src/anomalib/models/patchcore/torch_model.py
@@ -9,7 +9,11 @@
 import torch.nn.functional as F
 from torch import Tensor, nn
 
-from anomalib.models.components import DynamicBufferModule, FeatureExtractor, KCenterGreedy
+from anomalib.models.components import (
+    DynamicBufferModule,
+    FeatureExtractor,
+    KCenterGreedy,
+)
 from anomalib.models.patchcore.anomaly_map import AnomalyMapGenerator
 from anomalib.pre_processing import Tiler
 
@@ -19,9 +23,9 @@ class PatchcoreModel(DynamicBufferModule, nn.Module):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (224, 224),
+        input_size: tuple[int, int],
+        layers: list[str],
         backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer2", "layer3"],
         pre_trained: bool = True,
         num_neighbors: int = 9,
     ) -> None:
diff --git a/src/anomalib/models/reverse_distillation/lightning_model.py b/src/anomalib/models/reverse_distillation/lightning_model.py
index 2a6fae1826..5489daab5b 100644
--- a/src/anomalib/models/reverse_distillation/lightning_model.py
+++ b/src/anomalib/models/reverse_distillation/lightning_model.py
@@ -24,26 +24,22 @@ class ReverseDistillation(AnomalyModule):
     """PL Lightning Module for Reverse Distillation Algorithm.
 
     Args:
-        input_size (tuple[int, int], optional): Size of model input. Defaults to (256, 256).
-        backbone (str, optional): Backbone of CNN network. Defaults to "wide_resnet50_2".
-        layers (list[str], optional): Layers to extract features from the backbone CNN.
-            Defaults to ["layer1", "layer2", "layer3"].
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
-        lr (float, optional): Learning rate for the optimizer. Defaults to 0.005.
-        beta1 (float, optional): Beta1 for the optimizer. Defaults to 0.5.
-        beta2 (float, optional): Beta2 for the optimizer. Defaults to 0.99.
+        input_size (tuple[int, int]): Size of model input
+        backbone (str): Backbone of CNN network
+        layers (list[str]): Layers to extract features from the backbone CNN
+        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
-        anomaly_map_mode: AnomalyMapGenerationMode = AnomalyMapGenerationMode.MULTIPLY,
+        input_size: tuple[int, int],
+        backbone: str,
+        layers: list[str],
+        anomaly_map_mode: AnomalyMapGenerationMode,
+        lr: float,
+        beta1: float,
+        beta2: float,
         pre_trained: bool = True,
-        lr: float = 0.005,
-        beta1: float = 0.5,
-        beta2: float = 0.99,
     ) -> None:
         super().__init__()
         self.model = ReverseDistillationModel(
diff --git a/src/anomalib/models/reverse_distillation/torch_model.py b/src/anomalib/models/reverse_distillation/torch_model.py
index 178fee9ed1..5ada84573e 100644
--- a/src/anomalib/models/reverse_distillation/torch_model.py
+++ b/src/anomalib/models/reverse_distillation/torch_model.py
@@ -9,7 +9,10 @@
 
 from anomalib.models.components import FeatureExtractor
 from anomalib.models.reverse_distillation.anomaly_map import AnomalyMapGenerator
-from anomalib.models.reverse_distillation.components import get_bottleneck_layer, get_decoder
+from anomalib.models.reverse_distillation.components import (
+    get_bottleneck_layer,
+    get_decoder,
+)
 from anomalib.pre_processing import Tiler
 
 from .anomaly_map import AnomalyMapGenerationMode
@@ -19,19 +22,19 @@ class ReverseDistillationModel(nn.Module):
     """Reverse Distillation Model.
 
     Args:
-        input_size (tuple[int, int], optional): Size of model input. Defaults to (256, 256).
-        backbone (str, optional): Backbone of CNN network. Defaults to "wide_resnet50_2".
-        layers (list[str], optional): Layers to extract features from the backbone CNN.
-            Defaults to ["layer1", "layer2", "layer3"].
-        pre_trained (bool, optional): Boolean to check whether to use a pre_trained backbone. Defaults to True.
+        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.
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
-        anomaly_map_mode: AnomalyMapGenerationMode = AnomalyMapGenerationMode.MULTIPLY,
+        backbone: str,
+        input_size: tuple[int, int],
+        layers: list[str],
+        anomaly_map_mode: AnomalyMapGenerationMode,
         pre_trained: bool = True,
     ) -> None:
         super().__init__()
diff --git a/src/anomalib/models/stfpm/config.yaml b/src/anomalib/models/stfpm/config.yaml
index 6c1616300c..1f92f3a187 100644
--- a/src/anomalib/models/stfpm/config.yaml
+++ b/src/anomalib/models/stfpm/config.yaml
@@ -28,7 +28,7 @@ dataset:
 
 model:
   name: stfpm
-  backbone: wide_resnet50_2
+  backbone: resnet18
   layers:
     - layer1
     - layer2
diff --git a/src/anomalib/models/stfpm/lightning_model.py b/src/anomalib/models/stfpm/lightning_model.py
index 6383138536..e05f0aa783 100644
--- a/src/anomalib/models/stfpm/lightning_model.py
+++ b/src/anomalib/models/stfpm/lightning_model.py
@@ -25,17 +25,16 @@ class Stfpm(AnomalyModule):
     """PL Lightning Module for the STFPM algorithm.
 
     Args:
-        input_size (tuple[int, int], optional): Size of the model input. Defaults to (256, 256).
-        backbone (str, optional): Backbone CNN network. Defaults to "wide_resnet50_2".
-        layers (list[str], optional): Layers to extract features from the backbone CNN.
-            Defaults to ["layer1", "layer2", "layer3"].
+        input_size (tuple[int, int]): Size of the model input.
+        backbone (str): Backbone CNN network
+        layers (list[str]): Layers to extract features from the backbone CNN
     """
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
+        input_size: tuple[int, int],
+        backbone: str,
+        layers: list[str],
     ) -> None:
         super().__init__()
 
diff --git a/src/anomalib/models/stfpm/torch_model.py b/src/anomalib/models/stfpm/torch_model.py
index 7235e0d40e..a730c1fe50 100644
--- a/src/anomalib/models/stfpm/torch_model.py
+++ b/src/anomalib/models/stfpm/torch_model.py
@@ -23,9 +23,9 @@ class STFPMModel(nn.Module):
 
     def __init__(
         self,
-        input_size: tuple[int, int] = (256, 256),
-        backbone: str = "wide_resnet50_2",
-        layers: list[str] = ["layer1", "layer2", "layer3"],
+        layers: list[str],
+        input_size: tuple[int, int],
+        backbone: str = "resnet18",
     ) -> None:
         super().__init__()
         self.tiler: Tiler | None = None