[Bug]: Regular tiling in some doesn't work due to wrong shape setup.

[blaz-r]

Describe the bug

For Padim, PatchCore and Reverse Distillation, the tiling doesn't work at the moment.
This happens as the input_tensor is used to tell the shape of anomaly map:

anomalib/src/anomalib/models/image/padim/torch_model.py

Lines 141 to 148 in 09cbade

	else:
	output = self.anomaly_map_generator(
	embedding=embeddings,
	mean=self.gaussian.mean,
	inv_covariance=self.gaussian.inv_covariance,
	image_size=input_tensor.shape[-2:],
	)
	return output

but input_tensor is overwriten in case of tiler:

anomalib/src/anomalib/models/image/padim/torch_model.py

Lines 129 to 130 in 09cbade

	if self.tiler:
	input_tensor = self.tiler.tile(input_tensor)

which leads to shape mismatch.

Dataset

MVTec

Model

Other (please specify in the field below)

Steps to reproduce the behavior

from anomalib.data import MVTec
from anomalib.engine import Engine
from anomalib.models import Padim
from anomalib.callbacks import TilerConfigurationCallback

# Initialize the datamodule and model
datamodule = MVTec(num_workers=0, image_size=(128, 128))
model = Padim()

# prepare tiling configuration callback
tiler_config_callback = TilerConfigurationCallback(enable=True, tile_size=[128, 64], stride=64)

# pass the tiling configuration callback to engine
engine = Engine(image_metrics=["AUROC"], pixel_metrics=["AUROC"], callbacks=[tiler_config_callback])

# train the model (tiling is seamlessly utilized in the background)
engine.fit(datamodule=datamodule, model=model)

OS information

OS information:

• OS: Windows 10
• Python version: 3.10
• Anomalib version: 1.1.0dev
• PyTorch version: 2.1
• GPU models and configuration: gtx 1060

Expected behavior

The procedure works even with tiler present

Screenshots

No response

Pip/GitHub

GitHub

What version/branch did you use?

No response

Configuration YAML

/

Logs

RuntimeError: Predictions and targets are expected to have the same shape, but got torch.Size([262144]) and torch.Size([524288]).

Code of Conduct

• I agree to follow this project's Code of Conduct