bayesian-neural-network-mnist
bayesian-neural-network-mnist copied to clipboard
Published
20 hours ago •
paraschopra
paraschopra
Use log_softmax twice?
Hi, In model(x_data, y_data), lhat = log_softmax(lifted_reg_model(x_data)).
In give_uncertainities(x), yhats = [F.log_softmax(model(x.view(-1,28*28)).data, 1).detach().numpy() for model in sampled_models]
Does it mean you use log_softmax twice?
