[Bug]: OpenVINO IR Export default is not FP16

[junxnone]

Describe the bug

compress_to_fp16 is False, but the comment say that fp16 compression is enabled by default, it is confused.

https://github.com/openvinotoolkit/anomalib/blob/e5b91d6a32c469ec0b9c4c161272b68114ba6fa3/src/anomalib/models/components/base/export_mixin.py#L155-L164

https://github.com/openvinotoolkit/anomalib/blob/e5b91d6a32c469ec0b9c4c161272b68114ba6fa3/src/anomalib/models/components/base/export_mixin.py#L253-L255

Dataset

MVTec

Model

Other (please specify in the field below)

Steps to reproduce the behavior

• run the OpenVINO IR export
• get the log

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

same as the comment

Screenshots

No response

Pip/GitHub

pip

What version/branch did you use?

main

Configuration YAML

None

Logs

Source path:... 
test_anomalib/anomalib/src/anomalib/models/components/base/export_mixin.py
Starting var:.. self = WinClip(  (model): WinClipModel(    (clip): CLIP...0,), eps=1e-05, elementwise_affine=True)    )  ))
Starting var:.. export_root = PosixPath('testfp16')
Starting var:.. input_size = None
Starting var:.. transform = None
Starting var:.. compression_type = None
Starting var:.. datamodule = None
Starting var:.. ov_args = None
Starting var:.. task = <TaskType.SEGMENTATION: 'segmentation'>
11:01:25.264373 call       156     def to_openvino(

...
...

11:03:08.462087 line       257             compress_to_fp16 = compression_type == CompressionType.FP16
New var:....... compress_to_fp16 = False
11:03:08.463238 line       258             ov.save_model(model, ov_model_path, compress_to_fp16=compress_to_fp16)

Code of Conduct

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