pybnn
pybnn copied to clipboard
automl
Bayesian neural network package
unfortunately it is not clear as to what exactly the hyperparameters num_burn_in_steps and num_steps do from the paper itself. How should they be set for LCNet? in the test example,...
hello, why is it that the lcnet model takes as input only the configuration and not the learning curve? in the unit test example, there appears that y_train is composed...
When `print_every_n_steps` and `keep_every` are set to equal, the network is not updated properly Following the notebook example: ``` model = Bohamiann(print_every_n_steps=50) model.train(x[:, None], y, num_steps=20000, num_burn_in_steps=2000, keep_every=50, lr=1e-2, verbose=True)...
I'm a bit of a pytorch newbie, but was curious how difficult it would be to make a GPU compatible version of this code? My attempts of just adding ".to(device)"...
