Model requires reshaping data in the dataset to be (100,200,60) size. Use this file as follows in Julia:

model = create_parametric_model()
model_state = JLD2.load("../final_model2/trained_model.jld2", "model_state")
Flux.loadmodel!(model, model_state)

naughts=zeros(Int8, (100,200,60,1))
s0 = model(naughts)
il_of_nothing = 10 .* log.(sqrt.(s0[3,:,1].^2 + s0[4,:,1].^2))
plot(il_of_nothing, linewidth=2)

More info to follow.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train stephen-newberry/pcb-via-4layer-cnn-rev1