Image generation support

[bcebere]

Description

• Add image dataloader, with the ability to resize the images internally to predefined shapes.
• Extend the core plugin for non-tabular inputs
• Add ConvNet classifier support, with some predefined architectures.
• Add Generator and Discriminators with predefined architectures for various image input sizes.
• Add Image GAN support on top of the Generators and Discriminators.
• Add Conditional GAN support for the Generators and Discriminators
• New metrics: FID score
• Adapt the detection and performance metrics for images
• Add Image Conditional GAN plugin
• Add Image AdsGAN plugin
• Add tutorial on top of MedMNIST
• Update docs and README

fixes #132

Checklist

• I have followed the Contribution Guidelines and Code of Conduct
• I have commented my code following the van der Schaar Lab Styleguide
• I have labeled this PR with the relevant Type labels
• My changes are covered by tests