Anomalib 1.0.0 YAML File

[yxteo2]

Hi guys, I meet some problem with the yaml file format, everything seems correct to me but it shows this error

ValueError: Not a valid subclass of AnomalibDataModule. Got value: {'init_args': {'name': 'mvtec', 'format':
'mvtec', 'class_path': 'anomalib.data.image.mvtec.MVTec', 'path': 'anomalib.data.image.mvtec.MVTec', 'task':
'segmentation', 'category': 'led', 'train_batch_size': 32, 'test_batch_size': 32, 'num_workers': 8, 'image_size':
[256, 256], 'center_crop': [224, 224], 'normalization': 'imagenet', 'transform_config': {'train': None, 'eval':
None}, 'test_split_mode': 'from_dir', 'test_split_ratio': 0.2, 'val_split_mode': 'same_as_test', 'val_split_ratio':
0.5, 'tiling': {'apply': False, 'tile_size': None, 'stride': None, 'remove_border_count': 0, 'use_random_tiling':
False, 'random_tile_count': 16}, 'init_args': {'image_size': [256, 256], 'center_crop': [224, 224]}}}
Subclass types expect one of:

• a class path (str)
• a dict with class_path entry
• a dict without class_path but with init_args entry (class path given previously)

data:
name: mvtec
format: mvtec
class_path: anomalib.data.image.mvtec.MVTec
path: anomalib.data.image.mvtec.MVTec
task: segmentation
category: led
train_batch_size: 32
test_batch_size: 32
num_workers: 8
image_size: # Updated to a sequence
- 256
- 256
center_crop: # Updated to a sequence
- 224
- 224
normalization: imagenet # data distribution to which the images will be normalized: [none, imagenet]
transform_config:
train: null
eval: null
test_split_mode: from_dir # options: [from_dir, synthetic]
test_split_ratio: 0.2 # fraction of train images held out testing (usage depends on test_split_mode)
val_split_mode: same_as_test # options: [same_as_test, from_test, synthetic]
val_split_ratio: 0.5 # fraction of train/test images held out for validation (usage depends on val_split_mode)
tiling:
apply: false
tile_size: null
stride: null
remove_border_count: 0
use_random_tiling: False
random_tile_count: 16
init_args: # Added init_args for data
# Include any initialization arguments required by the data class
image_size: # Also as a sequence
- 256
- 256
center_crop: # Also as a sequence
- 224
- 224

[blaz-r]

This seems to be an older version of config file you are using.
Refer to https://github.com/openvinotoolkit/anomalib/tree/main/configs/data for new versions of configs.
Also check dataset constructor arguments to see which values are accepted (center crop for example no longer is a part of dataset):

anomalib/src/anomalib/data/image/mvtec.py

Lines 307 to 324 in 404e896

	def __init__(
	self,
	root: Path | str = "./datasets/MVTec",
	category: str = "bottle",
	train_batch_size: int = 32,
	eval_batch_size: int = 32,
	num_workers: int = 8,
	task: TaskType | str = TaskType.SEGMENTATION,
	image_size: tuple[int, int] | None = None,
	transform: Transform | None = None,
	train_transform: Transform | None = None,
	eval_transform: Transform | None = None,
	test_split_mode: TestSplitMode | str = TestSplitMode.FROM_DIR,
	test_split_ratio: float = 0.2,
	val_split_mode: ValSplitMode | str = ValSplitMode.SAME_AS_TEST,
	val_split_ratio: float = 0.5,
	seed: int | None = None,
	) -> None:

Here's an example for mvtec (taken from here):

class_path: anomalib.data.MVTec
init_args:
  root: ./datasets/MVTec
  category: bottle
  train_batch_size: 32
  eval_batch_size: 32
  num_workers: 8
  task: segmentation
  transform: null
  train_transform: null
  eval_transform: null
  test_split_mode: from_dir
  test_split_ratio: 0.2
  val_split_mode: same_as_test
  val_split_ratio: 0.5
  seed: null

[samet-akcay]

One way to ensure you are using the right config structure is to use Anomalib CLI as follows:

anomalib train --data MVTec --print_config

which will return the following that you could modify

# anomalib==1.2.0dev
seed_everything: true
trainer:
  accelerator: auto
  strategy: auto
  devices: auto
  num_nodes: 1
  precision: null
  logger: null
  callbacks: null
  fast_dev_run: false
  max_epochs: null
  min_epochs: null
  max_steps: -1
  min_steps: null
  max_time: null
  limit_train_batches: null
  limit_val_batches: null
  limit_test_batches: null
  limit_predict_batches: null
  overfit_batches: 0.0
  val_check_interval: null
  check_val_every_n_epoch: 1
  num_sanity_val_steps: null
  log_every_n_steps: null
  enable_checkpointing: null
  enable_progress_bar: null
  enable_model_summary: null
  accumulate_grad_batches: 1
  gradient_clip_val: null
  gradient_clip_algorithm: null
  deterministic: null
  benchmark: null
  inference_mode: true
  use_distributed_sampler: true
  profiler: null
  detect_anomaly: false
  barebones: false
  plugins: null
  sync_batchnorm: false
  reload_dataloaders_every_n_epochs: 0
task: SEGMENTATION
metrics:
  image: null
  pixel: null
logging:
  log_graph: false
default_root_dir: results
ckpt_path: null
data:
  class_path: anomalib.data.MVTec
  init_args:
    root: datasets/MVTec
    category: bottle
    train_batch_size: 32
    eval_batch_size: 32
    num_workers: 8
    image_size: null
    transform: null
    train_transform: null
    eval_transform: null
    test_split_mode: FROM_DIR
    test_split_ratio: 0.2
    val_split_mode: SAME_AS_TEST
    val_split_ratio: 0.5
    seed: null

[yxteo2]

Hi Samet, with this it could work.
But when I try to add optimizer

optimizer:
  class_path: torch.optim.AdamW
  init_args:
    amsgrad: false
    betas:
    - 0.9
    - 0.999
    capturable: false
    differentiable: false
    eps: 1.0e-08
    foreach: null
    fused: null
    lr: 0.003
    maximize: false
    weight_decay: 0.01

it shows this error:
c:\Users\user.conda\envs\anomalib2\lib\site-packages\lightning_utilities\core\overrides.py:35 │
│ in is_overridden │
│ │
│ 32 │ if hasattr(parent_attr, "wrapped"): │
│ 33 │ │ parent_attr = parent_attr.wrapped │
│ 34 │ │
│ ❱ 35 │ return instance_attr.code != parent_attr.code │
│ 36 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
AttributeError: 'functools.partial' object has no attribute 'code'