FoundADTrain
Python template · sinapsis_anomalib.templates.anomalib_train
Overview
Training implementation for Anomalib models.
FoundAD — inherited documentation
FoundAD Lightning Module.
Trains a lightweight manifold projector on a frozen DINOv2 encoder with CutPaste augmentation. Only the projector parameters are learned.
Args: encoder_name: DINOv2 model name. Defaults to ``"dinov2_vit_base_14"``. pred_depth: Number of projector transformer blocks. Defaults to ``6``. pred_emb_dim: Projector internal dimension. Defaults to ``384``. n_layer: Encoder layer to extract features from (n-th from last). Defaults to ``3``. top_k: Top-K patches for image-level scoring. Defaults to ``10``. dropout: Dropout on features before projector. Defaults to ``0.2``. feat_normed: L2-normalize features. Defaults to ``False``. use_pos_embed: Use positional encoding in projector. Defaults to ``False``. image_size: Input image size. Defaults to ``518`` for DINOv2 (37*14, patch size 14) or ``512`` for DINOv3 (32*16, patch size 16) encoders. Smaller values like ``224`` speed up inference at cost of resolution, but must stay divisible by the encoder's patch size. lr: Learning rate. Defaults to ``1e-3``. weight_decay: Weight decay for AdamW. Defaults to ``1e-4``. color_jitter: CutPaste color jitter strength. Defaults to ``0.5``. use_few_shot_augmentation: Apply random orientation (flip/rotate) and appearance (color jitter/grayscale/blur) augmentation to the base training images before CutPaste. This matches the paper's default training protocol and is important for expanding the diversity of a tiny (1/2/4-shot) training set; disabling it will hurt few-shot results. Defaults to ``True``. pre_processor: Pre-processor configuration. post_processor: Post-processor configuration. evaluator: Evaluator configuration. visualizer: Visualizer configuration.
Example: >>> from anomalib.data import MVTecAD >>> from anomalib.models import FoundAD >>> from anomalib.engine import Engine
>>> model = FoundAD() >>> datamodule = MVTecAD() >>> engine = Engine() >>> engine.fit(model, datamodule=datamodule) # doctest: +SKIP
Capabilities
Capabilities: not setInstallation
Install the published package using pip or uv.
pip install sinapsis-anomalib==1.0.0uv pip install sinapsis-anomalib==1.0.0uv add sinapsis-anomalib==1.0.0Configuration
Effective fields from the inspector schema, including nested Pydantic model fields.
Optional
Default: null
Optional
Default: null
Optional
Default: null
Path to checkpoint for resuming training. If None, starts training from scratch.
Optional
Default: null
Optional
Default: null
Optional
Default: null
Required
Default: null
Optional
Default: 0.001
Optional
Default: 10
Optional
Default: 0.2
Optional
Default: 3
Optional
Default: true
Optional
Default: null
Optional
Default: 6
Optional
Default: true
Optional
Default: false
Optional
Default: 0.5
Optional
Default: "dinov2_vit_base_14"
Optional
Default: 384
Optional
Default: 0.0001
Optional
Default: true
Optional
Default: false
Optional
Default: true
Optional
Default: true
(TrainerConfig): General trainer arguments. For more details see: https://lightning.ai/docs/pytorch/stable/common/trainer.html#trainer-flags foundad_init encoder_name <class 'str'>: default: dinov2_vit_base_14… Read full field description
(TrainerConfig): General trainer arguments. For more details see: https://lightning.ai/docs/pytorch/stable/common/trainer.html#trainer-flags foundad_init encoder_name <class 'str'>: default: dinov2_vit_base_14 pred_depth <class 'int'>: default: 6 pred_emb_dim <class 'int'>: default: 384 n_layer <class 'int'>: default: 3 top_k <class 'int'>: default: 10 dropout <class 'float'>: default: 0.2 feat_normed <class 'bool'>: default: False use_pos_embed <class 'bool'>: default: False image_size typing.Optional[int]: default: None lr <class 'float'>: default: 0.001 weight_decay <class 'float'>: default: 0.0001 color_jitter <class 'float'>: default: 0.5 use_few_shot_augmentation <class 'bool'>: default: True pre_processor typing.Union[anomalib.pre_processing.pre_processor.PreProcessor, bool]: default: True post_processor typing.Union[anomalib.post_processing.post_processor.PostProcessor, bool]: default: True evaluator typing.Union[anomalib.metrics.evaluator.Evaluator, bool]: default: True visualizer typing.Union[anomalib.visualization.base.Visualizer, bool]: default: True
Optional
Default: null
The devices to use for training (e.g., 1, [0, 1], "auto"). Defaults to "auto".
Optional
Default: "auto"
The maximum number of epochs to train for. Defaults to 5.
Optional
Default: 5
The minimum number of epochs to train for. Defaults to 1.
Optional
Default: 1
The hardware accelerator to use. Defaults to "auto".
Optional
Default: "cpu"
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
A descriptive name for the dataset.
Required
Default: null
The root directory where the dataset is located.
Optional
Default: null
A random seed for reproducibility in data splitting.
Optional
Default: null
Optional
Default: null
Optional
Default: null
Path to the directory containing normal images.
Required
Default: null
The number of subprocesses to use for data loading. Defaults to 8.
Optional
Default: 8
Path to the directory for abnormal images.
Optional
Default: null
Optional
Default: "from_test"
The number of samples per batch for evaluation. Defaults to 32.
Optional
Default: 32
Optional
Default: null
Optional
Default: "from_dir"
Optional
Default: 0.5
Optional
Default: 0.2
The number of samples per batch for training. Defaults to 32.
Optional
Default: 32
Optional
Default: 0.2
Configuration example
Generated from documented defaults. Replace any placeholders and complete required nested settings before running.
templates:
- template_name: "FoundADTrain"
class_name: "FoundADTrain"
attributes:
logger: null
callbacks: null
ckpt_path: null
threshold: null
train_root: null
foundad_init:
lr: 0.001
top_k: 10
dropout: 0.2
n_layer: 3
evaluator: true
image_size: null
pred_depth: 6
visualizer: true
feat_normed: false
color_jitter: 0.5
encoder_name: "dinov2_vit_base_14"
pred_emb_dim: 384
weight_decay: 0.0001
pre_processor: true
use_pos_embed: false
post_processor: true
use_few_shot_augmentation: true
trainer_args:
devices: "auto"
max_epochs: 5
min_epochs: 1
accelerator: "cpu"
image_metrics: null
normalization: null
pixel_metrics: null
logger_configs: null
callback_configs: null
folder_attributes:
name: "<required>"
root: null
seed: null
mask_dir: null
extensions: null
normal_dir: "<required>"
num_workers: 8
abnormal_dir: null
val_split_mode: "from_test"
eval_batch_size: 32
normal_test_dir: null
test_split_mode: "from_dir"
val_split_ratio: 0.5
test_split_ratio: 0.2
train_batch_size: 32
normal_split_ratio: 0.2
View original docstring example
The source example references CfaTrain, not FoundADTrain.
agent:
name: my_test_agent
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: CfaTrain
class_name: CfaTrain
template_input: InputTemplate
attributes:
folder_attributes_config_path: 'path/to/config.yaml'
generic_key: 'my_generic_key'
callbacks: null
normalization: null
threshold: null
image_metrics: null
pixel_metrics: null
logger: null
callback_configs: null
logger_configs: null
ckpt_path: null
trainer_args:
devices: "0"
accelerator: gpu
max_epochs: null
cfa_init:
backbone: wide_resnet50_2
gamma_c: 1
gamma_d: 1
num_nearest_neighbors: 3
num_hard_negative_features: 3
radius: 1.0e-05
For a full list of options use the sinapsis cli: sinapsis info --all-template-names.
If you want to see all available models, please visit:
https://anomalib.readthedocs.io/en/v1.2.0/markdown/guides/reference/models/image/index.html.Inheritance
sinapsis_anomalib.templates.anomalib_train.AnomalibTrainEnvironment variables
Environment definitions belong to their canonical Python modules.