mittagessen

This is an implementation for unsupervised pretraining of recognition model weights based on an image inpainting surrogate task that aims to reconstruct randomly sampled masked patches from the initial convolutional...

Validate VGSL spec before loading training data

2

Add a method to `lib.vgsl.TorchVGSLModel` to validate a (partial) spec, feeding a 'dummy' line/image into it depending on the input specification. This would allow aborting training before loading the training...