GeneralADTrain
Python template · sinapsis_anomalib.templates.anomalib_train
Overview
Training implementation for Anomalib models.
GeneralAD — inherited documentation
GeneralAD Lightning module.
Args: backbone: Timm backbone used as frozen feature extractor. layers: Backbone stages or transformer blocks used for patch features. hidden_dim: Hidden size of the patch discriminator. lr: Optimizer learning rate. lr_decay_factor: Final cosine annealing ratio. weight_decay: Optimizer weight decay. epochs: Number of epochs used to parameterize the LR scheduler. noise_std: Standard deviation for synthetic anomalous features. dsc_layers: Number of attention blocks in the discriminator. dsc_heads: Number of attention heads in the discriminator. dsc_dropout: Dropout rate in the discriminator. num_fake_patches: Maximum number of perturbed patches per image. fake_feature_type: Strategy for generating pseudo anomalies. top_k: Number of highest patch scores to average for image scoring. pre_trained: Whether to use pretrained backbone weights. pre_processor: Optional anomalib pre-processor. post_processor: Optional anomalib post-processor. evaluator: Optional anomalib evaluator. visualizer: Optional anomalib visualizer.
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
(TrainerConfig): General trainer arguments. For more details see: https://lightning.ai/docs/pytorch/stable/common/trainer.html#trainer-flags generalad_init backbone <class 'str'>: default: vit_la… Read full field description
(TrainerConfig): General trainer arguments. For more details see: https://lightning.ai/docs/pytorch/stable/common/trainer.html#trainer-flags generalad_init backbone <class 'str'>: default: vit_large_patch14_dinov2.lvd142m layers typing.Sequence[int]: default: (24,) hidden_dim <class 'int'>: default: 2048 lr <class 'float'>: default: 0.0005 lr_decay_factor <class 'float'>: default: 0.2 weight_decay <class 'float'>: default: 1e-05 epochs <class 'int'>: default: 160 noise_std <class 'float'>: default: 0.25 dsc_layers <class 'int'>: default: 1 dsc_heads <class 'int'>: default: 4 dsc_dropout <class 'float'>: default: 0.1 num_fake_patches <class 'int'>: default: -1 fake_feature_type typing.Any: default: random top_k <class 'int'>: default: 10 pre_trained <class 'bool'>: default: True pre_processor typing.Any: default: True post_processor typing.Any: default: True evaluator typing.Any: default: True visualizer typing.Any: 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
Required
Default: null
Optional
Default: 0.0005
Optional
Default: 10
Optional
Default: 160
Optional
Default: [24]
Optional
Default: "vit_large_patch14_dinov2.lvd142m"
Optional
Default: 4
Optional
Default: true
Optional
Default: 0.25
Optional
Default: 1
Optional
Default: 2048
Optional
Default: true
Optional
Default: 0.1
Optional
Default: true
Optional
Default: 0.00001
Optional
Default: true
Optional
Default: true
Optional
Default: 0.2
Optional
Default: -1
Optional
Default: "random"
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: "GeneralADTrain"
class_name: "GeneralADTrain"
attributes:
logger: null
callbacks: null
ckpt_path: null
threshold: null
train_root: null
trainer_args:
devices: "auto"
max_epochs: 5
min_epochs: 1
accelerator: "cpu"
image_metrics: null
normalization: null
pixel_metrics: null
generalad_init:
lr: 0.0005
top_k: 10
epochs: 160
layers: [24]
backbone: "vit_large_patch14_dinov2.lvd142m"
dsc_heads: 4
evaluator: true
noise_std: 0.25
dsc_layers: 1
hidden_dim: 2048
visualizer: true
dsc_dropout: 0.1
pre_trained: true
weight_decay: 0.00001
pre_processor: true
post_processor: true
lr_decay_factor: 0.2
num_fake_patches: -1
fake_feature_type: "random"
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 GeneralADTrain.
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.