Make visualization configurable

[jschneider]

Hey,

we are using this code, which works fine:

dataset = PredictDataset(image_path)
dataloader = DataLoader(dataset, num_workers=15)

model = get_model("Patchcore")

output = engine.predict(
  model=model,
  ckpt_path=model_path,
  dataloaders=[dataloader],
)

The output contains everything I expect, everything is fine.

But:
I have a lot of pictures, I want to analyze - and performance matters:

• Therefore, it would be great if I was able to load the model only once and use it for multiple images.
• It would be great to avoid generating the debug picture (containing the heat map, mask etc).

I am sure I am missing a simple way to achieve this. Any help appreciated ;-)

[JohannesSteinle]

I have had the same problem and did not find a fix. Looking forward to a solution!

[samet-akcay]

it is currently not configurable, but we will enable it in v1.1.0. For now, you could disable these lines to not visualize the outputs
https://github.com/openvinotoolkit/anomalib/blob/ca90807f0b3464e91dac765f33d574467f3d3353/src/anomalib/engine/engine.py#L412-L418

[jschneider]

Great! Thanks.

Will it be possible to load the model just once and call "predict" several times?

[samet-akcay]

yes, ideally it should be possible. Let us know if it does not work

[jschneider]

I can't find a way to load the model once and reuse the loaded model.
Could you give me a hint? I am quite new in this area, so might be a bit blind here...

[watertianyi]

@samet-akcay
from anomalib.visualization.image import ImageVisualizer
ModuleNotFoundError: No module named 'anomalib.visualization'

[samet-akcay]

@watertianyi, note that this has not been merged to main branch yet. It is in feature/v2, and will be released within v2, which is scheduled to be mid-December