WinClipExport
Python template · sinapsis_anomalib.templates.anomalib_export
Overview
Export functionality for trained Anomalib models.
WinClip — inherited documentation
WinCLIP Lightning model.
This model implements the WinCLIP algorithm for zero-/few-shot anomaly detection using CLIP embeddings and a sliding window approach. The model can perform both anomaly classification and segmentation by comparing image regions with normal reference examples.
Args: class_name (str | None, optional): Name of the object class used in the prompt ensemble. If not provided, will try to infer from the datamodule or use "object" as default. Defaults to ``None``. k_shot (int, optional): Number of reference images to use for few-shot inference. If 0, uses zero-shot approach. Defaults to ``0``. scales (tuple[int], optional): Scales of sliding windows used for multiscale anomaly detection. Defaults to ``(2, 3)``. few_shot_source (str | Path | None, optional): Path to folder containing reference images for few-shot inference. If not provided, reference images are sampled from training data. Defaults to ``None``. pre_processor (PreProcessor | bool, optional): Pre-processor instance or flag to use default. Used to pre-process input data before model inference. Defaults to ``True``. post_processor (PostProcessor | bool, optional): Post-processor instance or flag to use default. Used to post-process model predictions. Defaults to ``True``. evaluator (Evaluator | bool, optional): Evaluator instance or flag to use default. Used to compute metrics. Defaults to ``True``. visualizer (Visualizer | bool, optional): Visualizer instance or flag to use default. Used to create visualizations. Defaults to ``True``.
Example: >>> from anomalib.models.image import WinClip >>> # Zero-shot approach >>> model = WinClip() # doctest: +SKIP >>> # Few-shot with 5 reference images >>> model = WinClip(k_shot=5) # doctest: +SKIP >>> # Custom class name >>> model = WinClip(class_name="transistor") # doctest: +SKIP
Notes: - Input image size is fixed at 240x240 and cannot be modified - Uses a custom normalization transform specific to CLIP
See Also: - :class:`WinClipModel`: PyTorch implementation of the core model - :class:`PostProcessor`: Default post-processor used by WinCLIP
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
Metric used for compression calibration.
Optional
Default: null
OpenVINO-specific export arguments.
Optional
Default: null
Optional
Default: false
If True, compresses the model weights to FP16 precision. Defaults to None. Print detailed information about conversion.
Optional
Default: null
Optional
Default: null
Optional
Default: null
Explicit path to model checkpoint.
Optional
Default: null
Optional
Default: null
Expected input dimensions (height, width).
Optional
Default: null
Root directory for exported files.
Optional
Default: null
Target export format. Defaults to TORCH.
Optional
Default: "torch"
Required
Default: null
Optional
Default: 0
Optional
Default: [2,3]
Optional
Default: true
Optional
Default: null
Optional
Default: true
Optional
Default: true
Optional
Default: true
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
Quantization/compression method.
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
Key to retrieve training results. winclip_init class_name typing.Optional[str]: default: None k_shot <class 'int'>: default: 0 scales <class 'tuple'>: default: (2, 3) few_shot_source typing.Union[pathlib._local.Path,… Read full field description
Key to retrieve training results. winclip_init class_name typing.Optional[str]: default: None k_shot <class 'int'>: default: 0 scales <class 'tuple'>: default: (2, 3) few_shot_source typing.Union[pathlib._local.Path, str, NoneType]: default: None pre_processor typing.Union[torch.nn.modules.module.Module, bool]: default: True post_processor typing.Union[torch.nn.modules.module.Module, 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
Configuration example
Generated from documented defaults. Replace any placeholders and complete required nested settings before running.
templates:
- template_name: "WinClipExport"
class_name: "WinClipExport"
attributes:
logger: null
metric: null
ov_args:
verbose: false
compress_to_fp16: null
callbacks: null
ckpt_path: null
threshold: null
input_size: null
export_root: null
export_type: {}
winclip_init:
k_shot: 0
scales: {}
evaluator: true
class_name: null
visualizer: true
pre_processor: true
post_processor: true
few_shot_source: null
image_metrics: null
normalization: null
pixel_metrics: null
logger_configs: null
callback_configs: null
compression_type: 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
generic_key_chkpt: null
View original docstring example
The source example references CfaExport, not WinClipExport.
agent:
name: my_test_agent
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: CfaExport
class_name: CfaExport
template_input: InputTemplate
attributes:
folder_attributes_config_path: null
generic_key: 'my_generic_key'
callbacks: null
normalization: null
threshold: null
task: null
image_metrics: null
pixel_metrics: null
logger: null
callback_configs: null
logger_configs: null
export_type: 'openvino'
export_root: null
input_size: null
transform: null
compression_type: null
metric: null
ov_args: null
ckpt_path: null
generic_key_chkpt: 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
Notes:
- Supports multiple export formats via ExportType
- Enables model compression through CompressionType.
- Can load models from checkpoints or previous training results.Inheritance
sinapsis_anomalib.templates.anomalib_export.AnomalibExportEnvironment variables
Environment definitions belong to their canonical Python modules.