📚Add how-to-guides and examples dir

[samet-akcay]

📝 Description

• Add how-to-guides showing tutorials about pre/post processing, evaluation and visualisation
• Add examples directory to consolidate api/cli/notebook examples

✨ Changes

Select what type of change your PR is:

• 🐞 Bug fix (non-breaking change which fixes an issue)
• 🔨 Refactor (non-breaking change which refactors the code base)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📚 Documentation update
• 🔒 Security update

✅ Checklist

Before you submit your pull request, please make sure you have completed the following steps:

• 📋 I have summarized my changes in the CHANGELOG and followed the guidelines for my type of change (skip for minor changes, documentation updates, and test enhancements).
• 📚 I have made the necessary updates to the documentation (if applicable).
• 🧪 I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).

For more information about code review checklists, see the Code Review Checklist.

[djdameln]

Suggested change

	gt_label=torch.tensor(0), # Normal (0) or anomalous (1)
	gt_label=0 # Normal (0 or False) or anomalous (1 or True)

[djdameln]

Suggested change

	print(item.gt_label.item()) # 0
	print(item.gt_label) # tensor(False)

[djdameln]

This method does not exist

[djdameln]

There seem to be several other examples in this guide that don't work. Would probably be good to check if these examples are up to date.

[djdameln]

transforms should be removed here and below

[djdameln]

Suggested change

	- Apply transforms
	- Apply data augmentations

[djdameln]

Not sure if we should mention the dataframe here, given that it may be replaced soon.

[djdameln]

Suggested change

transform=transform

[djdameln]

This is outdated now that we moved the stage-specific augmentations to the datamodule

[djdameln]

Suggested change

	model = Patchcore()
	model = Patchcore()
	print(model.pre_processor.transform)
	# Compose(
	# Resize(size=[256, 256], interpolation=InterpolationMode.BILINEAR, antialias=True)
	# CenterCrop(size=(224, 224))
	# Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], inplace=False)
	# )

[djdameln]

• train_transform --> transform to reflect most recent design.
• removed ToTensor to avoid confusing users.

Suggested change

	model = Patchcore(
	pre_processor=PreProcessor(
	transform=Compose([
	Resize((256, 256)),
	ToTensor()
	])
	)
	)
	print(model.pre_processor.train_transform)
	# Compose(
	# Resize(size=[256, 256], interpolation=InterpolationMode.BILINEAR, antialias=False)
	# ToTensor()
	# )
	model = Patchcore(
	pre_processor=PreProcessor(
	transform=Resize((256, 256)),
	)
	)
	print(model.pre_processor.transform)
	# Resize(size=[256, 256], interpolation=InterpolationMode.BILINEAR, antialias=False)