[Bug]: AttributeError: 'numpy.ndarray' object has no attribute 'to'

[Septembit]

Describe the bug

Seems this bug still exists when I use torch inferencer in anomalib 1.2.0
Do anyone have a way to solve it?
thanks

Dataset

Folder

Model

FastFlow

Steps to reproduce the behavior

N/A

OS information

OS information:

• OS: [e.g. Ubuntu 20.04]
• Python version: [e.g. 3.10.0]
• Anomalib version: [e.g. 0.3.6]
• PyTorch version: [e.g. 1.9.0]
• CUDA/cuDNN version: [e.g. 11.1]
• GPU models and configuration: [e.g. 2x GeForce RTX 3090]
• Any other relevant information: [e.g. I'm using a custom dataset]

Expected behavior

N/A

Screenshots

No response

Pip/GitHub

pip

What version/branch did you use?

No response

Configuration YAML

N/A

Logs

def pre_process(self, image: np.ndarray) -> torch.Tensor:
        """Pre process the input image.

        Args:
            image (np.ndarray): Input image

        Returns:
            Tensor: pre-processed image.
        """
        if len(image) == 3:
            image = image.unsqueeze(0)

        return image.to(self.device)

Code of Conduct

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

[Sachin-NK]

can I take this issue and work on fixing it?

[Septembit]

Yes, thank you very much