rasmus johansson

Evaluating models usually goes faster with GPU enabled. This simple change enables model_weights_as_vector() and model_weights_as_dict() to work also when torch use GPU for computations.

repalced draw.textsize(text, font) with font.getbbox(text) as the for…

1

The function textsize() is deptricated and does not work on newer python (3.9) The new solutiuon is validated to work under python 3.9

Fix: adding import nececeary for using attention layers as bottlenecks

1

Adding the following import from fastai.layers import _get_norm in order for the following code to be able to run def BatchNormZero(nf, ndim=2, **kwargs):\n", " \"BatchNorm layer with `nf` features and...