Create weights network with randomly initialized weights for Keras Models

I work with a tool for audio feature extraction which has several layers (DenseNet, etc) for the extraction. The default is to use pre-trained imagenet weights, however I want to evaluate the performance with randomly initialized weights.

I can use a path to the weight network (stored in h5), however I don't know how to create that weight network for a layer of which I do not know the exact dimensions/architecture.

I know how to create randomly initialized weights for a layer I designed myself, but is there a way to do that for a specific keras model?

The Keras implementation tells me that the argument weights takes one of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded, but not how to create those weights for the file.

Any help is much appreciated!